WorldWideScience

Sample records for network forecasting system

  1. Time Series Forecasting of Daily Reference Evapotranspiration by Neural Network Ensemble Learning for Irrigation System

    Science.gov (United States)

    Manikumari, N.; Murugappan, A.; Vinodhini, G.

    2017-07-01

    Time series forecasting has gained remarkable interest of researchers in the last few decades. Neural networks based time series forecasting have been employed in various application areas. Reference Evapotranspiration (ETO) is one of the most important components of the hydrologic cycle and its precise assessment is vital in water balance and crop yield estimation, water resources system design and management. This work aimed at achieving accurate time series forecast of ETO using a combination of neural network approaches. This work was carried out using data collected in the command area of VEERANAM Tank during the period 2004 – 2014 in India. In this work, the Neural Network (NN) models were combined by ensemble learning in order to improve the accuracy for forecasting Daily ETO (for the year 2015). Bagged Neural Network (Bagged-NN) and Boosted Neural Network (Boosted-NN) ensemble learning were employed. It has been proved that Bagged-NN and Boosted-NN ensemble models are better than individual NN models in terms of accuracy. Among the ensemble models, Boosted-NN reduces the forecasting errors compared to Bagged-NN and individual NNs. Regression co-efficient, Mean Absolute Deviation, Mean Absolute Percentage error and Root Mean Square Error also ascertain that Boosted-NN lead to improved ETO forecasting performance.

  2. Prospects of application of artificial neural networks for forecasting of cargo transportation volume in transport systems

    Directory of Open Access Journals (Sweden)

    D. T. Yakupov

    2017-01-01

    Full Text Available The purpose of research – to identify the prospects for the use of neural network approach in relation to the tasks of economic forecasting of logistics performance, in particular of volume freight traffic in the transport system promiscuous regional freight traffic, as well as to substantiate the effectiveness of the use of artificial neural networks (ANN, as compared with the efficiency of traditional extrapolative methods of forecasting. The authors consider the possibility of forecasting to use ANN for these economic indicators not as an alternative to the traditional methods of statistical forecasting, but as one of the available simple means for solving complex problems.Materials and methods. When predicting the ANN, three methods of learning were used: 1 the Levenberg-Marquardt algorithm-network training stops when the generalization ceases to improve, which is shown by the increase in the mean square error of the output value; 2 Bayes regularization method - network training is stopped in accordance with the minimization of adaptive weights; 3 the method of scaled conjugate gradients, which is used to find the local extremum of a function on the basis of information about its values and gradient. The Neural Network Toolbox package is used for forecasting. The neural network model consists of a hidden layer of neurons with a sigmoidal activation function and an output neuron with a linear activation function, the input values of the dynamic time series, and the predicted value is removed from the output. For a more objective assessment of the prospects of the ANN application, the results of the forecast are presented in comparison with the results obtained in predicting the method of exponential smoothing.Results. When predicting the volumes of freight transportation by rail, satisfactory indicators of the verification of forecasting by both the method of exponential smoothing and ANN had been obtained, although the neural network

  3. A space weather forecasting system with multiple satellites based on a self-recognizing network.

    Science.gov (United States)

    Tokumitsu, Masahiro; Ishida, Yoshiteru

    2014-05-05

    This paper proposes a space weather forecasting system at geostationary orbit for high-energy electron flux (>2 MeV). The forecasting model involves multiple sensors on multiple satellites. The sensors interconnect and evaluate each other to predict future conditions at geostationary orbit. The proposed forecasting model is constructed using a dynamic relational network for sensor diagnosis and event monitoring. The sensors of the proposed model are located at different positions in space. The satellites for solar monitoring equip with monitoring devices for the interplanetary magnetic field and solar wind speed. The satellites orbit near the Earth monitoring high-energy electron flux. We investigate forecasting for typical two examples by comparing the performance of two models with different numbers of sensors. We demonstrate the prediction by the proposed model against coronal mass ejections and a coronal hole. This paper aims to investigate a possibility of space weather forecasting based on the satellite network with in-situ sensing.

  4. A Space Weather Forecasting System with Multiple Satellites Based on a Self-Recognizing Network

    Directory of Open Access Journals (Sweden)

    Masahiro Tokumitsu

    2014-05-01

    Full Text Available This paper proposes a space weather forecasting system at geostationary orbit for high-energy electron flux (>2 MeV. The forecasting model involves multiple sensors on multiple satellites. The sensors interconnect and evaluate each other to predict future conditions at geostationary orbit. The proposed forecasting model is constructed using a dynamic relational network for sensor diagnosis and event monitoring. The sensors of the proposed model are located at different positions in space. The satellites for solar monitoring equip with monitoring devices for the interplanetary magnetic field and solar wind speed. The satellites orbit near the Earth monitoring high-energy electron flux. We investigate forecasting for typical two examples by comparing the performance of two models with different numbers of sensors. We demonstrate the prediction by the proposed model against coronal mass ejections and a coronal hole. This paper aims to investigate a possibility of space weather forecasting based on the satellite network with in-situ sensing.

  5. Recurrent networks for wave forecasting

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Prabaharan, N.

    , merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper presents an application of the Artificial Neural Network, namely Backpropagation Recurrent Neural Network (BRNN) with rprop update algorithm for wave forecasting...

  6. CITY TRANSPORT SYSTEM ECOLOGICAL STATE FORECASTING WITH THE USE OF NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Andrey Lyamzin

    2017-11-01

    Full Text Available Purpose: The purpose of this work is to develop an effective model for city transport system ecological state assessment using neural networks general concept. Methods: The proposed model is based on two neural networks work, taking into account the traffic density effect and the transit capacity level on urban areas. Results: Based on the synthesis of the fuzzy sets theory and neural networks basic principles, the city transport system ecological state assessing model is developed. The graphical representation of the model is given. A forecast reliability high degree is provided even at low learning rates and high dynamics of changing statistical data in the city transit traffic conditions. Conclusions: The use of fuzzy neural networks makes it possible to state a complete correspondence between fuzzy inference procedure mathematical representation and the urban transport system structure. The proposed model allows to formulate well-defined environmental guidelines when making decisions in the transit traffic field, taking into account the interests of enterprises, transport and the urban population, with the subsequent distribution of traffic flows in time and geographical space of the city industrial areas.

  7. LOAD FORECASTING FOR POWER SYSTEM PLANNING AND OPERATION USING ARTIFICIAL NEURAL NETWORK AT AL BATINAH REGION OMAN

    Directory of Open Access Journals (Sweden)

    HUSSEIN A. ABDULQADER

    2012-08-01

    Full Text Available Load forecasting is essential part for the power system planning and operation. In this paper the modeling and design of artificial neural network for load forecasting is carried out in a particular region of Oman. Neural network approach helps to reduce the problem associated with conventional method and has the advantage of learning directly from the historical data. The neural network here uses data such as past load; weather information like humidity and temperatures. Once the neural network is trained for the past set of data it can give a prediction of future load. This reduces the capital investment reducing the equipments to be installed. The actual data are taken from the Mazoon Electrical Company, Oman. The data of load for the year 2007, 2008 and 2009 are collected for a particular region called Al Batinah in Oman and trained using neural networks to forecast the future. The main objective is to forecast the amount of electricity needed for better load distribution in the areas of this region in Oman. The load forecasting is done for the year 2010 and is validated for the accuracy.

  8. COST ES0602: towards a European network on chemical weather forecasting and information systems

    Directory of Open Access Journals (Sweden)

    J. Kukkonen

    2009-04-01

    Full Text Available The COST ES0602 action provides a forum for benchmarking approaches and practices in data exchange and multi-model capabilities for chemical weather forecasting and near real-time information services in Europe. The action includes approximately 30 participants from 19 countries, and its duration is from 2007 to 2011 (http://www.chemicalweather.eu/. Major efforts have been dedicated in other actions and projects to the development of infrastructures for data flow. We have therefore aimed for collaboration with ongoing actions towards developing near real-time exchange of input data for air quality forecasting. We have collected information on the operational air quality forecasting models on a regional and continental scale in a structured form, and inter-compared and evaluated the physical and chemical structure of these models. We have also constructed a European chemical weather forecasting portal that includes links to most of the available chemical weather forecasting systems in Europe. The collaboration also includes the examination of the case studies that have been organized within COST-728, in order to inter-compare and evaluate the models against experimental data. We have also constructed an operational model forecasting ensemble. Data from a representative set of regional background stations have been selected, and the operational forecasts for this set of sites will be inter-compared and evaluated. The Action has investigated, analysed and reviewed existing chemical weather information systems and services, and will provide recommendations on best practices concerning the presentation and dissemination of chemical weather information towards the public and decision makers.

  9. World Area Forecast System (WAFS)

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The World Area Forecast System (WAFS) is a worldwide system by which world area forecast centers provide aeronautical meteorological en-route forecasts in uniform...

  10. WSN system design by using an innovative neural network model to perform thermals forecasting in a urban canyon scenario

    Science.gov (United States)

    Giuseppina, Nicolosi; Salvatore, Tirrito

    2015-12-01

    Wireless Sensor Networks (WSNs) were studied by researchers in order to manage Heating, Ventilating and Air-Conditioning (HVAC) indoor systems. WSN can be useful specially to regulate indoor confort in a urban canyon scenario, where the thermal parameters vary rapidly, influenced by outdoor climate changing. This paper shows an innovative neural network approach, by using WSN data collected, in order to forecast the indoor temperature to varying the outdoor conditions based on climate parameters and boundary conditions typically of urban canyon. In this work more attention will be done to influence of traffic jam and number of vehicles in queue.

  11. Short-term wind speed forecasting by an adaptive network-based fuzzy inference system (ANFIS: an attempt towards an ensemble forecasting method

    Directory of Open Access Journals (Sweden)

    Moslem Yousefi

    2015-12-01

    Full Text Available Accurate Wind speed forecasting has a vital role in efficient utilization of wind farms. Wind forecasting could be performed for long or short time horizons. Given the volatile nature of wind and its dependent on many geographical parameters, it is difficult for traditional methods to provide a reliable forecast of wind speed time series. In this study, an attempt is made to establish an efficient adaptive network-based fuzzy interference (ANFIS for short-term wind speed forecasting. Using the available data sets in the literature, the ANFIS network is constructed, tested and the results are compared with that of a regular neural network, which has been forecasted the same set of dataset in previous studies. To avoid trial-and-error process for selection of the ANFIS input data, the results of autocorrelation factor (ACF and partial auto correlation factor (PACF on the historical wind speed data are employed. The available data set is divided into two parts. 50% for training and 50% for testing and validation. The testing part of data set will be merely used for assessing the performance of the neural network which guarantees that only unseen data is used to evaluate the forecasting performance of the network. On the other hand, validation data could be used for parameter-setting of the network if required. The results indicate that ANFIS could not outperform ANN in short-term wind speed forecasting though its results are competitive. The two methods are hybridized, though simply by weightage, and the hybrid methods shows slight improvement comparing to both ANN and ANFIS results. Therefore, the goal of future studies could be implementing ANFIS and ANNs in a more comprehensive ensemble method which could be ultimately more robust and accurate

  12. Interactive Forecasting with the National Weather Service River Forecast System

    Science.gov (United States)

    Smith, George F.; Page, Donna

    1993-01-01

    The National Weather Service River Forecast System (NWSRFS) consists of several major hydrometeorologic subcomponents to model the physics of the flow of water through the hydrologic cycle. The entire NWSRFS currently runs in both mainframe and minicomputer environments, using command oriented text input to control the system computations. As computationally powerful and graphically sophisticated scientific workstations became available, the National Weather Service (NWS) recognized that a graphically based, interactive environment would enhance the accuracy and timeliness of NWS river and flood forecasts. Consequently, the operational forecasting portion of the NWSRFS has been ported to run under a UNIX operating system, with X windows as the display environment on a system of networked scientific workstations. In addition, the NWSRFS Interactive Forecast Program was developed to provide a graphical user interface to allow the forecaster to control NWSRFS program flow and to make adjustments to forecasts as necessary. The potential market for water resources forecasting is immense and largely untapped. Any private company able to market the river forecasting technologies currently developed by the NWS Office of Hydrology could provide benefits to many information users and profit from providing these services.

  13. Technology forecasting for space communication. [analysis of systems for application to Spacecraft Data and Tracking Network

    Science.gov (United States)

    1973-01-01

    A study was conducted to determine techniques for application to space communication. The subjects considered are as follows: (1) optical communication systems, (2) laser communications for data acquisition networks, (3) spacecraft data rate requirements, (4) telemetry, command, and data handling, (5) spacecraft tracking and data network antenna and preamplifier cost tradeoff study, and (6) spacecraft communication terminal evaluation.

  14. Using Artificial Intelligence to Retrieve the Optimal Parameters and Structures of Adaptive Network-Based Fuzzy Inference System for Typhoon Precipitation Forecast Modeling

    Directory of Open Access Journals (Sweden)

    Chien-Lin Huang

    2015-01-01

    Full Text Available This study aims to construct a typhoon precipitation forecast model providing forecasts one to six hours in advance using optimal model parameters and structures retrieved from a combination of the adaptive network-based fuzzy inference system (ANFIS and artificial intelligence. To enhance the accuracy of the precipitation forecast, two structures were then used to establish the precipitation forecast model for a specific lead-time: a single-model structure and a dual-model hybrid structure where the forecast models of higher and lower precipitation were integrated. In order to rapidly, automatically, and accurately retrieve the optimal parameters and structures of the ANFIS-based precipitation forecast model, a tabu search was applied to identify the adjacent radius in subtractive clustering when constructing the ANFIS structure. The coupled structure was also employed to establish a precipitation forecast model across short and long lead-times in order to improve the accuracy of long-term precipitation forecasts. The study area is the Shimen Reservoir, and the analyzed period is from 2001 to 2009. Results showed that the optimal initial ANFIS parameters selected by the tabu search, combined with the dual-model hybrid method and the coupled structure, provided the favors in computation efficiency and high-reliability predictions in typhoon precipitation forecasts regarding short to long lead-time forecasting horizons.

  15. Seasonal rainfall forecasting by adaptive network-based fuzzy inference system (ANFIS) using large scale climate signals

    Science.gov (United States)

    Mekanik, F.; Imteaz, M. A.; Talei, A.

    2016-05-01

    Accurate seasonal rainfall forecasting is an important step in the development of reliable runoff forecast models. The large scale climate modes affecting rainfall in Australia have recently been proven useful in rainfall prediction problems. In this study, adaptive network-based fuzzy inference systems (ANFIS) models are developed for the first time for southeast Australia in order to forecast spring rainfall. The models are applied in east, center and west Victoria as case studies. Large scale climate signals comprising El Nino Southern Oscillation (ENSO), Indian Ocean Dipole (IOD) and Inter-decadal Pacific Ocean (IPO) are selected as rainfall predictors. Eight models are developed based on single climate modes (ENSO, IOD, and IPO) and combined climate modes (ENSO-IPO and ENSO-IOD). Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Pearson correlation coefficient (r) and root mean square error in probability (RMSEP) skill score are used to evaluate the performance of the proposed models. The predictions demonstrate that ANFIS models based on individual IOD index perform superior in terms of RMSE, MAE and r to the models based on individual ENSO indices. It is further discovered that IPO is not an effective predictor for the region and the combined ENSO-IOD and ENSO-IPO predictors did not improve the predictions. In order to evaluate the effectiveness of the proposed models a comparison is conducted between ANFIS models and the conventional Artificial Neural Network (ANN), the Predictive Ocean Atmosphere Model for Australia (POAMA) and climatology forecasts. POAMA is the official dynamic model used by the Australian Bureau of Meteorology. The ANFIS predictions certify a superior performance for most of the region compared to ANN and climatology forecasts. POAMA performs better in regards to RMSE and MAE in east and part of central Victoria, however, compared to ANFIS it shows weaker results in west Victoria in terms of prediction errors and RMSEP skill

  16. Improved Local Weather Forecasts Using Artificial Neural Networks

    DEFF Research Database (Denmark)

    Wollsen, Morten Gill; Jørgensen, Bo Nørregaard

    2015-01-01

    Solar irradiance and temperature forecasts are used in many different control systems. Such as intelligent climate control systems in commercial greenhouses, where the solar irradiance affects the use of supplemental lighting. This paper proposes a novel method to predict the forthcoming weather...... using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show...... that the network outperforms the commercial forecast for lower step aheads (forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution....

  17. GEOS-5 seasonal forecast system

    Science.gov (United States)

    Borovikov, Anna; Cullather, Richard; Kovach, Robin; Marshak, Jelena; Vernieres, Guillaume; Vikhliaev, Yury; Zhao, Bin; Li, Zhao

    2017-09-01

    Ensembles of numerical forecasts based on perturbed initial conditions have long been used to improve estimates of both weather and climate forecasts. The Goddard Earth Observing System (GEOS) Atmosphere-Ocean General Circulation Model, Version 5 (GEOS-5 AOGCM) Seasonal-to-Interannual Forecast System has been used routinely by the GMAO since 2008, the current version since 2012. A coupled reanalysis starting in 1980 provides the initial conditions for the 9-month experimental forecasts. Once a month, sea surface temperature from a suite of 11 ensemble forecasts is contributed to the North American Multi-Model Ensemble (NMME) consensus project, which compares and distributes seasonal forecasts of ENSO events. Since June 2013, GEOS-5 forecasts of the Arctic sea-ice distribution were provided to the Sea-Ice Outlook project. The seasonal forecast output data includes surface fields, atmospheric and ocean fields, as well as sea ice thickness and area, and soil moisture variables. The current paper aims to document the characteristics of the GEOS-5 seasonal forecast system and to highlight forecast biases and skills of selected variables (sea surface temperature, air temperature at 2 m, precipitation and sea ice extent) to be used as a benchmark for the future GMAO seasonal forecast systems and to facilitate comparison with other global seasonal forecast systems.

  18. Broadband Traffic Forecasting in the Transport Network

    Directory of Open Access Journals (Sweden)

    Valentina Radojičić

    2012-07-01

    Full Text Available This paper proposes a modification of traffic forecast model generated by residential and small business (SOHO, Small Office Home Office users. The model includes forecasted values of different relevant factors and competition on broadband market. It allows forecasting the number of users for various broadband technologies and interaction impact of long-standing technologies as well as the impact of the new technology entrant on the market. All the necessary parameters are evaluated for the Serbian broadband market. The long-term forecasted results of broadband traffic are given. The analyses and evaluations performed are important inputs for the transport network resources planning.

  19. Daily Average Wind Power Interval Forecasts Based on an Optimal Adaptive-Network-Based Fuzzy Inference System and Singular Spectrum Analysis

    Directory of Open Access Journals (Sweden)

    Zhongrong Zhang

    2016-01-01

    Full Text Available Wind energy has increasingly played a vital role in mitigating conventional resource shortages. Nevertheless, the stochastic nature of wind poses a great challenge when attempting to find an accurate forecasting model for wind power. Therefore, precise wind power forecasts are of primary importance to solve operational, planning and economic problems in the growing wind power scenario. Previous research has focused efforts on the deterministic forecast of wind power values, but less attention has been paid to providing information about wind energy. Based on an optimal Adaptive-Network-Based Fuzzy Inference System (ANFIS and Singular Spectrum Analysis (SSA, this paper develops a hybrid uncertainty forecasting model, IFASF (Interval Forecast-ANFIS-SSA-Firefly Alogorithm, to obtain the upper and lower bounds of daily average wind power, which is beneficial for the practical operation of both the grid company and independent power producers. To strengthen the practical ability of this developed model, this paper presents a comparison between IFASF and other benchmarks, which provides a general reference for this aspect for statistical or artificially intelligent interval forecast methods. The comparison results show that the developed model outperforms eight benchmarks and has a satisfactory forecasting effectiveness in three different wind farms with two time horizons.

  20. Coalbed Methane Production System Simulation and Deliverability Forecasting: Coupled Surface Network/Wellbore/Reservoir Calculation

    Directory of Open Access Journals (Sweden)

    Jun Zhou

    2017-01-01

    Full Text Available As an unconventional energy, coalbed methane (CBM mainly exists in coal bed with adsorption, whose productivity is different from conventional gas reservoir. This paper explains the wellbore pressure drop, surface pipeline network simulation, and reservoir calculation model of CBM. A coupled surface/wellbore/reservoir calculation architecture was presented, to coordinate the gas production in each calculation period until the balance of surface/wellbore/reservoir. This coupled calculation method was applied to a CBM field for predicting production. The daily gas production increased year by year at the first time and then decreased gradually after several years, while the daily water production was reduced all the time with the successive decline of the formation pressure. The production of gas and water in each well is almost the same when the structure is a star. When system structure is a dendritic surface system, the daily gas production ranked highest at the well which is the nearest to the surface system collection point and lowest at the well which is the farthest to the surface system collection point. This coupled calculation method could be used to predict the water production, gas production, and formation pressure of a CBM field during a period of time.

  1. Flood Forecasting in River System Using ANFIS

    Science.gov (United States)

    Ullah, Nazrin; Choudhury, P.

    2010-10-01

    The aim of the present study is to investigate applicability of artificial intelligence techniques such as ANFIS (Adaptive Neuro-Fuzzy Inference System) in forecasting flood flow in a river system. The proposed technique combines the learning ability of neural network with the transparent linguistic representation of fuzzy system. The technique is applied to forecast discharge at a downstream station using flow information at various upstream stations. A total of three years data has been selected for the implementation of this model. ANFIS models with various input structures and membership functions are constructed, trained and tested to evaluate efficiency of the models. Statistical indices such as Root Mean Square Error (RMSE), Correlation Coefficient (CORR) and Coefficient of Efficiency (CE) are used to evaluate performance of the ANFIS models in forecasting river flood. The values of the indices show that ANFIS model can accurately and reliably be used to forecast flood in a river system.

  2. Network Bandwidth Utilization Forecast Model on High Bandwidth Network

    Energy Technology Data Exchange (ETDEWEB)

    Yoo, Wucherl; Sim, Alex

    2014-07-07

    With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology, our forecast model reduces computation time by 83.2percent. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.

  3. Network bandwidth utilization forecast model on high bandwidth networks

    Energy Technology Data Exchange (ETDEWEB)

    Yoo, Wuchert (William) [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Sim, Alex [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

    2015-03-30

    With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology, our forecast model reduces computation time by 83.2%. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.

  4. Artificial Neural Network for Short-Term Load Forecasting in Distribution Systems

    Directory of Open Access Journals (Sweden)

    Luis Hernández

    2014-03-01

    Full Text Available The new paradigms and latest developments in the Electrical Grid are based on the introduction of distributed intelligence at several stages of its physical layer, giving birth to concepts such as Smart Grids, Virtual Power Plants, microgrids, Smart Buildings and Smart Environments. Distributed Generation (DG is a philosophy in which energy is no longer produced exclusively in huge centralized plants, but also in smaller premises which take advantage of local conditions in order to minimize transmission losses and optimize production and consumption. This represents a new opportunity for renewable energy, because small elements such as solar panels and wind turbines are expected to be scattered along the grid, feeding local installations or selling energy to the grid depending on their local generation/consumption conditions. The introduction of these highly dynamic elements will lead to a substantial change in the curves of demanded energy. The aim of this paper is to apply Short-Term Load Forecasting (STLF in microgrid environments with curves and similar behaviours, using two different data sets: the first one packing electricity consumption information during four years and six months in a microgrid along with calendar data, while the second one will be just four months of the previous parameters along with the solar radiation from the site. For the first set of data different STLF models will be discussed, studying the effect of each variable, in order to identify the best one. That model will be employed with the second set of data, in order to make a comparison with a new model that takes into account the solar radiation, since the photovoltaic installations of the microgrid will cause the power demand to fluctuate depending on the solar radiation.

  5. Black Sea coastal forecasting system

    Directory of Open Access Journals (Sweden)

    A. I. Kubryakov

    2012-03-01

    Full Text Available The Black Sea coastal nowcasting and forecasting system was built within the framework of EU FP6 ECOOP (European COastalshelf sea OPerational observing and forecasting system project for five regions: the south-western basin along the coasts of Bulgaria and Turkey, the north-western shelf along the Romanian and Ukrainian coasts, coastal zone around of the Crimea peninsula, the north-eastern Russian coastal zone and the coastal zone of Georgia. The system operates in the real-time mode during the ECOOP project and afterwards. The forecasts include temperature, salinity and current velocity fields. Ecosystem model operates in the off-line mode near the Crimea coast.

  6. Intelligent systems for demand forecasting

    Energy Technology Data Exchange (ETDEWEB)

    Majithia, S.; Kiernan, L.; Hannan, J.

    1997-12-31

    The electricity industry is a huge and growing business, centring around the supply and demand of electricity. There are many benefits in knowing the future load on the system by way of forecasting future demand for electricity. Demand forecasts are of use in a wide range of issues relating to system control, maintenance and planning. Short term demand forecasting (1-7 days ahead) allows unit scheduling to be planned, preparing the industry to meet the demand for electricity. There are large financial benefits in improving forecasts even by a small percentage, so it is always worth investigating new techniques that may help the forecaster. ISs offer a range of new approaches that can help improve demand forecasts. There are two major benefits of using ISs rather than the more traditional modelling techniques. Firstly, intelligent systems offer powerful modelling techniques with very different strengths from those currently available. ESs can be used to encapsulate knowledge and experience, to track not just the general trends in demand but also many of the irregularities. They can easily be updated to include any new relationships. Fuzzy sets permit the linguistic rules that are often present in human descriptions to be incorporated into the model. ANNs offer the ability to model the non-linearities that are known to be part of the demand pattern. The second benefit is the ability of intelligent systems to automate the process of constructing a forecasting model. (UK)

  7. Global Ensemble Forecast System (GEFS) [1 Deg.

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Global Ensemble Forecast System (GEFS) is a weather forecast model made up of 21 separate forecasts, or ensemble members. The National Centers for Environmental...

  8. Drought forecasting monitoring system

    Science.gov (United States)

    Mendicino, G.; Senatore, A.; Versace, P.

    2003-04-01

    The main characteristics of an integrated system aimed to predict space-time variations of water deficit occurring in southern Italy are described in this note. The system, running since the year 2000, has been developed within the European INTERREG IIC Programme. It is based on an embedded coupling of GIS and models connected with a Data Acquisition System aimed at storing real time data recorded by the Regional tele-metering hydro-meteorological network (Centro Funzionale Meteo Idrologico della Regione Calabria). This network has been strengthened with a great number of stations, most of which are aimed at measuring specific quantities (rainfall, water level, groundwater level, temperature, solar radiation, evaporation, wind speed and direction, soil moisture and soil water matric potential) to be directly used for the estimate of water balance on the southern Italy regions. Geographic information are stored within a GIS according to raster and vector data structures; spatially distributed hydrological quantities are elaborated, managed and stored using a raster data structure, characterised by a 250 m square grid spatial resolution equal to that utilised for the southern Italy Digital Terrain Model. Hydrological coverages are directly obtained by linking GIS with hydrological databases. Specifically, hydro-meteorological information is managed considering two different data types. The first is based on daily hydro-meteorological values recorded by all gauge stations (historic DB) starting from 1925. The latter is based on real time data recorded by tele-metering stations with a 20-minute time step (real time DB). The interaction with databases has been improved realising some Windows-based software applications capable of guaranteeing a more simple and flexible data query, and allowing the user to extract synthetic graphs and reports. These user-DB interfaces can work both autonomously and directly inside the GIS by simple graphical selections on the gauge

  9. Wind Speed Forecasting by Wavelet Neural Networks: A Comparative Study

    Directory of Open Access Journals (Sweden)

    Chuanan Yao

    2013-01-01

    Full Text Available Due to the environmental degradation and depletion of conventional energy, much attention has been devoted to wind energy in many countries. The intermittent nature of wind power has had a great impact on power grid security. Accurate forecasting of wind speed plays a vital role in power system stability. This paper presents a comparison of three wavelet neural networks for short-term forecasting of wind speed. The first two combined models are two types of basic combinations of wavelet transform and neural network, namely, compact wavelet neural network (CWNN and loose wavelet neural network (LWNN in this study, and the third model is a new hybrid method based on the CWNN and LWNN models. The efficiency of the combined models has been evaluated by using actual wind speed from two test stations in North China. The results show that the forecasting performances of the CWNN and LWNN models are unstable and are affected by the test stations selected; the third model is far more accurate than the other forecasting models in spite of the drawback of lower computational efficiency.

  10. The Invasive Species Forecasting System

    Science.gov (United States)

    Schnase, John; Most, Neal; Gill, Roger; Ma, Peter

    2011-01-01

    The Invasive Species Forecasting System (ISFS) provides computational support for the generic work processes found in many regional-scale ecosystem modeling applications. Decision support tools built using ISFS allow a user to load point occurrence field sample data for a plant species of interest and quickly generate habitat suitability maps for geographic regions of management concern, such as a national park, monument, forest, or refuge. This type of decision product helps resource managers plan invasive species protection, monitoring, and control strategies for the lands they manage. Until now, scientists and resource managers have lacked the data-assembly and computing capabilities to produce these maps quickly and cost efficiently. ISFS focuses on regional-scale habitat suitability modeling for invasive terrestrial plants. ISFS s component architecture emphasizes simplicity and adaptability. Its core services can be easily adapted to produce model-based decision support tools tailored to particular parks, monuments, forests, refuges, and related management units. ISFS can be used to build standalone run-time tools that require no connection to the Internet, as well as fully Internet-based decision support applications. ISFS provides the core data structures, operating system interfaces, network interfaces, and inter-component constraints comprising the canonical workflow for habitat suitability modeling. The predictors, analysis methods, and geographic extents involved in any particular model run are elements of the user space and arbitrarily configurable by the user. ISFS provides small, lightweight, readily hardened core components of general utility. These components can be adapted to unanticipated uses, are tailorable, and require at most a loosely coupled, nonproprietary connection to the Web. Users can invoke capabilities from a command line; programmers can integrate ISFS's core components into more complex systems and services. Taken together, these

  11. An artificial neural network to assess the impact of neighbouring photovoltaic systems in power forecasting in Utrecht, the Netherlands

    NARCIS (Netherlands)

    Vaz, A. G R; Elsinga, B.|info:eu-repo/dai/nl/372629601; van Sark, W. G J H M|info:eu-repo/dai/nl/074628526; Brito, M. C.

    2016-01-01

    In order to perform predictions of a photovoltaic (PV) system power production, a neural network architecture system using the Nonlinear Autoregressive with eXogenous inputs (NARX) model is implemented using not only local meteorological data but also measurements of neighbouring PV systems as

  12. Hybrid Forecasting Approach Based on GRNN Neural Network and SVR Machine for Electricity Demand Forecasting

    Directory of Open Access Journals (Sweden)

    Weide Li

    2017-01-01

    Full Text Available Accurate electric power demand forecasting plays a key role in electricity markets and power systems. The electric power demand is usually a non-linear problem due to various unknown reasons, which make it difficult to get accurate prediction by traditional methods. The purpose of this paper is to propose a novel hybrid forecasting method for managing and scheduling the electricity power. EEMD-SCGRNN-PSVR, the proposed new method, combines ensemble empirical mode decomposition (EEMD, seasonal adjustment (S, cross validation (C, general regression neural network (GRNN and support vector regression machine optimized by the particle swarm optimization algorithm (PSVR. The main idea of EEMD-SCGRNN-PSVR is respectively to forecast waveform and trend component that hidden in demand series to substitute directly forecasting original electric demand. EEMD-SCGRNN-PSVR is used to predict the one week ahead half-hour’s electricity demand in two data sets (New South Wales (NSW and Victorian State (VIC in Australia. Experimental results show that the new hybrid model outperforms the other three models in terms of forecasting accuracy and model robustness.

  13. Climate Forecast System Version 2 (CFSv2) Operational Forecasts

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Climate Forecast System Version 2 (CFSv2) produced by the NOAA National Centers for Environmental Prediction (NCEP) is a fully coupled model representing the...

  14. Neural network versus classical time series forecasting models

    Science.gov (United States)

    Nor, Maria Elena; Safuan, Hamizah Mohd; Shab, Noorzehan Fazahiyah Md; Asrul, Mohd; Abdullah, Affendi; Mohamad, Nurul Asmaa Izzati; Lee, Muhammad Hisyam

    2017-05-01

    Artificial neural network (ANN) has advantage in time series forecasting as it has potential to solve complex forecasting problems. This is because ANN is data driven approach which able to be trained to map past values of a time series. In this study the forecast performance between neural network and classical time series forecasting method namely seasonal autoregressive integrated moving average models was being compared by utilizing gold price data. Moreover, the effect of different data preprocessing on the forecast performance of neural network being examined. The forecast accuracy was evaluated using mean absolute deviation, root mean square error and mean absolute percentage error. It was found that ANN produced the most accurate forecast when Box-Cox transformation was used as data preprocessing.

  15. Global Forecast System (GFS) [1 Deg.

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Global Forecast System (GFS) is a weather forecast model produced by the National Centers for Environmental Prediction (NCEP). Dozens of atmospheric and...

  16. Sea level forecasts using neural networks

    Science.gov (United States)

    Röske, Frank

    1997-03-01

    In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the

  17. On Efficient Data Reduction for Network Partition Forecasting in WSNs

    Directory of Open Access Journals (Sweden)

    Faisal Karim Shaikh

    2011-04-01

    Full Text Available WSNs (Wireless Sensor Networks are generally deployed for long-lived missions. However, they rely on finite energy resources which lead to network partitioning. Network partitioning limits the dependability of WSN by making relevant spatial regions disconnected thus requiring the maintenance of the network. The network maintenance necessitates early warning and consequently forecasting of the network partitioning such that some early action can be taken to mitigate the problem. There exist approaches allowing for detection of network partitioning but none for its forecasting. We present an efficient approach for a proactive network ParFor (Partition Forecasting based on energy maps. ParFor implements spatial and temporal suppression mechanisms such that from energy weak regions only a few nodes report short alarms to the sink. Using these alarms the forecasting is done centrally at the sink. Using simulations we highlight the efficiency and accuracy of ParFor.

  18. Forecasting PM10 in Algiers: efficacy of multilayer perceptron networks.

    Science.gov (United States)

    Abderrahim, Hamza; Chellali, Mohammed Reda; Hamou, Ahmed

    2016-01-01

    Air quality forecasting system has acquired high importance in atmospheric pollution due to its negative impacts on the environment and human health. The artificial neural network is one of the most common soft computing methods that can be pragmatic for carving such complex problem. In this paper, we used a multilayer perceptron neural network to forecast the daily averaged concentration of the respirable suspended particulates with aerodynamic diameter of not more than 10 μm (PM10) in Algiers, Algeria. The data for training and testing the network are based on the data sampled from 2002 to 2006 collected by SAMASAFIA network center at El Hamma station. The meteorological data, air temperature, relative humidity, and wind speed, are used as inputs network parameters in the formation of model. The training patterns used correspond to 41 days data. The performance of the developed models was evaluated on the basis index of agreement and other statistical parameters. It was seen that the overall performance of model with 15 neurons is better than the ones with 5 and 10 neurons. The results of multilayer network with as few as one hidden layer and 15 neurons were quite reasonable than the ones with 5 and 10 neurons. Finally, an error around 9% has been reached.

  19. Magnetogram Forecast: An All-Clear Space Weather Forecasting System

    Science.gov (United States)

    Barghouty, Nasser; Falconer, David

    2015-01-01

    Solar flares and coronal mass ejections (CMEs) are the drivers of severe space weather. Forecasting the probability of their occurrence is critical in improving space weather forecasts. The National Oceanic and Atmospheric Administration (NOAA) currently uses the McIntosh active region category system, in which each active region on the disk is assigned to one of 60 categories, and uses the historical flare rates of that category to make an initial forecast that can then be adjusted by the NOAA forecaster. Flares and CMEs are caused by the sudden release of energy from the coronal magnetic field by magnetic reconnection. It is believed that the rate of flare and CME occurrence in an active region is correlated with the free energy of an active region. While the free energy cannot be measured directly with present observations, proxies of the free energy can instead be used to characterize the relative free energy of an active region. The Magnetogram Forecast (MAG4) (output is available at the Community Coordinated Modeling Center) was conceived and designed to be a databased, all-clear forecasting system to support the operational goals of NASA's Space Radiation Analysis Group. The MAG4 system automatically downloads nearreal- time line-of-sight Helioseismic and Magnetic Imager (HMI) magnetograms on the Solar Dynamics Observatory (SDO) satellite, identifies active regions on the solar disk, measures a free-energy proxy, and then applies forecasting curves to convert the free-energy proxy into predicted event rates for X-class flares, M- and X-class flares, CMEs, fast CMEs, and solar energetic particle events (SPEs). The forecast curves themselves are derived from a sample of 40,000 magnetograms from 1,300 active region samples, observed by the Solar and Heliospheric Observatory Michelson Doppler Imager. Figure 1 is an example of MAG4 visual output

  20. Forecasting Energy Commodity Prices Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Massimo Panella

    2012-01-01

    Full Text Available A new machine learning approach for price modeling is proposed. The use of neural networks as an advanced signal processing tool may be successfully used to model and forecast energy commodity prices, such as crude oil, coal, natural gas, and electricity prices. Energy commodities have shown explosive growth in the last decade. They have become a new asset class used also for investment purposes. This creates a huge demand for better modeling as what occurred in the stock markets in the 1970s. Their price behavior presents unique features causing complex dynamics whose prediction is regarded as a challenging task. The use of a Mixture of Gaussian neural network may provide significant improvements with respect to other well-known models. We propose a computationally efficient learning of this neural network using the maximum likelihood estimation approach to calibrate the parameters. The optimal model is identified using a hierarchical constructive procedure that progressively increases the model complexity. Extensive computer simulations validate the proposed approach and provide an accurate description of commodities prices dynamics.

  1. Assessment of reservoir system variable forecasts

    Science.gov (United States)

    Kistenmacher, Martin; Georgakakos, Aris P.

    2015-05-01

    Forecast ensembles are a convenient means to model water resources uncertainties and to inform planning and management processes. For multipurpose reservoir systems, forecast types include (i) forecasts of upcoming inflows and (ii) forecasts of system variables and outputs such as reservoir levels, releases, flood damage risks, hydropower production, water supply withdrawals, water quality conditions, navigation opportunities, and environmental flows, among others. Forecasts of system variables and outputs are conditional on forecasted inflows as well as on specific management policies and can provide useful information for decision-making processes. Unlike inflow forecasts (in ensemble or other forms), which have been the subject of many previous studies, reservoir system variable and output forecasts are not formally assessed in water resources management theory or practice. This article addresses this gap and develops methods to rectify potential reservoir system forecast inconsistencies and improve the quality of management-relevant information provided to stakeholders and managers. The overarching conclusion is that system variable and output forecast consistency is critical for robust reservoir management and needs to be routinely assessed for any management model used to inform planning and management processes. The above are demonstrated through an application from the Sacramento-American-San Joaquin reservoir system in northern California.

  2. Forecasting Water Levels Using Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Shreenivas N. Londhe

    2011-06-01

    Full Text Available For all Ocean related activities it is necessary to predict the actual water levels as accurate as possible. The present work aims at predicting the water levels with a lead time of few hours to a day using the technique of artificial neural networks. Instead of using the previous and current values of observed water level time series directly as input and output the water level anomaly (difference between the observed water level and harmonically predicted tidal level is calculated for each hour and the ANN model is developed using this time series. The network predicted anomaly is then added to harmonic tidal level to predict the water levels. The exercise is carried out at six locations, two in The Gulf of Mexico, two in The Gulf of Maine and two in The Gulf of Alaska along the USA coastline. The ANN models performed reasonably well for all forecasting intervals at all the locations. The ANN models were also run in real time mode for a period of eight months. Considering the hurricane season in Gulf of Mexico the models were also tested particularly during hurricanes.

  3. Wind Resource Assessment and Forecast Planning with Neural Networks

    Directory of Open Access Journals (Sweden)

    Nicolus K. Rotich

    2014-06-01

    Full Text Available In this paper we built three types of artificial neural networks, namely: Feed forward networks, Elman networks and Cascade forward networks, for forecasting wind speeds and directions. A similar network topology was used for all the forecast horizons, regardless of the model type. All the models were then trained with real data of collected wind speeds and directions over a period of two years in the municipal of Puumala, Finland. Up to 70th percentile of the data was used for training, validation and testing, while 71–85th percentile was presented to the trained models for validation. The model outputs were then compared to the last 15% of the original data, by measuring the statistical errors between them. The feed forward networks returned the lowest errors for wind speeds. Cascade forward networks gave the lowest errors for wind directions; Elman networks returned the lowest errors when used for short term forecasting.

  4. An Electrical Energy Consumption Monitoring and Forecasting System

    Directory of Open Access Journals (Sweden)

    J. L. Rojas-Renteria

    2016-10-01

    Full Text Available Electricity consumption is currently an issue of great interest for power companies that need an as much as accurate profile for controlling the installed systems but also for designing future expansions and alterations. Detailed monitoring has proved to be valuable for both power companies and consumers. Further, as smart grid technology is bound to result to increasingly flexible rates, an accurate forecast is bound to prove valuable in the future. In this paper, a monitoring and forecasting system is investigated. The monitoring system was installed in an actual building and the recordings were used to design and evaluate the forecasting system, based on an artificial neural network. Results show that the system can provide detailed monitoring and also an accurate forecast for a building’s consumption.

  5. Probabilistic Wind Power Forecasting with Hybrid Artificial Neural Networks

    DEFF Research Database (Denmark)

    Wan, Can; Song, Yonghua; Xu, Zhao

    2016-01-01

    The uncertainty of wind power generation imposes significant challenges to optimal operation and control of electricity networks with increasing wind power penetration. To effectively address the uncertainties in wind power forecasts, probabilistic forecasts that can quantify the associated...... via a bootstrap technique. Subsequently, the maximum likelihood estimation method is employed to construct a distinct neural network to estimate the noise variance of forecasting results. The proposed approach has been tested on multi-step forecasting of high-resolution (10-min) wind power using...... actual wind power data from Denmark. The numerical results demonstrate that the proposed hybrid artificial neural network approach is effective and efficient for probabilistic forecasting of wind power and has high potential in practical applications....

  6. Improving Artificial Neural Network Forecasts with Kalman Filtering ...

    African Journals Online (AJOL)

    In this paper, we examine the use of the artificial neural network method as a forecasting technique in financial time series and the application of a Kalman filter algorithm to improve the accuracy of the model. Forecasting accuracy criteria are used to compare the two models over different set of data from different companies ...

  7. Data Driven Broiler Weight Forecasting using Dynamic Neural Network Models

    DEFF Research Database (Denmark)

    Johansen, Simon Vestergaard; Bendtsen, Jan Dimon; Riisgaard-Jensen, Martin

    2017-01-01

    In this article, the dynamic influence of environmental broiler house conditions and broiler growth is investigated. Dynamic neural network forecasting models have been trained on farm-scale broiler batch production data from 12 batches from the same house. The model forecasts future broiler weight...

  8. Improving Artificial Neural Network Forecasts with Kalman Filtering ...

    African Journals Online (AJOL)

    ... used to compare the two models over different set of data from different companies over a period of 750 trading days. In all the cases we find that the Kalman filter algorithm significantly adds value to the forecasting process. Keywords: Artificial Neural Networks, Kalman filter, Stock prices, Forecasting, Back propagation ...

  9. Forecasting Baltic Dirty Tanker Index by Applying Wavelet Neural Networks

    DEFF Research Database (Denmark)

    Fan, Shuangrui; JI, TINGYUN; Bergqvist, Rickard

    2013-01-01

    modeling techniques used in freight rate forecasting. At the same time research in shipping index forecasting e.g. BDTI applying artificial intelligent techniques is scarce. This analyses the possibilities to forecast the BDTI by applying Wavelet Neural Networks (WNN). Firstly, the characteristics......Baltic Exchange Dirty Tanker Index (BDTI) is an important assessment index in world dirty tanker shipping industry. Actors in the industry sector can gain numerous benefits from accurate forecasting of the BDTI. However, limitations exist in traditional stochastic and econometric explanation...

  10. A Bayesian regularized artificial neural network for adaptive optics forecasting

    Science.gov (United States)

    Sun, Zhi; Chen, Ying; Li, Xinyang; Qin, Xiaolin; Wang, Huiyong

    2017-01-01

    Real-time adaptive optics is a technology for enhancing the resolution of ground-based optical telescopes and overcoming the disturbance of atmospheric turbulence. The performance of the system is limited by delay errors induced by the servo system and photoelectrons noise of wavefront sensor. In order to cut these delay errors, this paper proposes a novel model to forecast the future control voltages of the deformable mirror. The predictive model is constructed by a multi-layered back propagation network with Bayesian regularization (BRBP). For the purpose of parallel computation and less disturbance, we adopt a number of sub-BP neural networks to substitute the whole network. The Bayesian regularized network assigns a probability to the network weights, allowing the network to automatically and optimally penalize excessively complex models. The simulation results show that the BRBP introduces smaller mean absolute percentage error (MAPE) and mean square errors (MSE) than other typical algorithms. Meanwhile, real data analysis results show that the BRBP model has strong generalization capability and parallelism.

  11. Daily Nigerian peak load forecasting using artificial neural network ...

    African Journals Online (AJOL)

    A daily peak load forecasting technique that uses artificial neural network with seasonal indices is presented in this paper. A neural network of relatively smaller size than the main prediction network is used to predict the daily peak load for a period of one year over which the actual daily load data are available using one ...

  12. New Neural Network Methods for Forecasting Regional Employment

    NARCIS (Netherlands)

    Patuelli, R.; Reggiani, A; Nijkamp, P.; Blien, U.

    2006-01-01

    In this paper, a set of neural network (NN) models is developed to compute short-term forecasts of regional employment patterns in Germany. Neural networks are modern statistical tools based on learning algorithms that are able to process large amounts of data. Neural networks are enjoying

  13. Forecasting Global Point Rainfall using ECMWF's Ensemble Forecasting System

    Science.gov (United States)

    Pillosu, Fatima; Hewson, Timothy; Zsoter, Ervin; Baugh, Calum

    2017-04-01

    ECMWF (the European Centre for Medium range Weather Forecasts), in collaboration with the EFAS (European Flood Awareness System) and GLOFAS (GLObal Flood Awareness System) teams, has developed a new operational system that post-processes grid box rainfall forecasts from its ensemble forecasting system to provide global probabilistic point-rainfall predictions. The project attains a higher forecasting skill by applying an understanding of how different rainfall generation mechanisms lead to different degrees of sub-grid variability in rainfall totals. In turn this approach facilitates identification of cases in which very localized extreme totals are much more likely. This approach aims also to improve the rainfall input required in different hydro-meteorological applications. Flash flood forecasting, in particular in urban areas, is a good example. In flash flood scenarios precipitation is typically characterised by high spatial variability and response times are short. In this case, to move beyond radar based now casting, the classical approach has been to use very high resolution hydro-meteorological models. Of course these models are valuable but they can represent only very limited areas, may not be spatially accurate and may give reasonable results only for limited lead times. On the other hand, our method aims to use a very cost-effective approach to downscale global rainfall forecasts to a point scale. It needs only rainfall totals from standard global reporting stations and forecasts over a relatively short period to train it, and it can give good results even up to day 5. For these reasons we believe that this approach better satisfies user needs around the world. This presentation aims to describe two phases of the project: The first phase, already completed, is the implementation of this new system to provide 6 and 12 hourly point-rainfall accumulation probabilities. To do this we use a limited number of physically relevant global model parameters (i

  14. Inflow forecasting using Artificial Neural Networks for reservoir operation

    Directory of Open Access Journals (Sweden)

    C. Chiamsathit

    2016-05-01

    Full Text Available In this study, multi-layer perceptron (MLP artificial neural networks have been applied to forecast one-month-ahead inflow for the Ubonratana reservoir, Thailand. To assess how well the forecast inflows have performed in the operation of the reservoir, simulations were carried out guided by the systems rule curves. As basis of comparison, four inflow situations were considered: (1 inflow known and assumed to be the historic (Type A; (2 inflow known and assumed to be the forecast (Type F; (3 inflow known and assumed to be the historic mean for month (Type M; and (4 inflow is unknown with release decision only conditioned on the starting reservoir storage (Type N. Reservoir performance was summarised in terms of reliability, resilience, vulnerability and sustainability. It was found that Type F inflow situation produced the best performance while Type N was the worst performing. This clearly demonstrates the importance of good inflow information for effective reservoir operation.

  15. (MRF) analysis-forecast system

    Indian Academy of Sciences (India)

    R. Narasimhan (Krishtel eMaging) 1461 1996 Oct 15 13:05:22

    Systematic and random error and their growth rate and different components of growth rate bud- get in energy/variance form are investigated at wavenumber domain for medium range tropical. (30◦S–30◦N) weather forecast using daily horizontal wind field of 850 hPa up to 5-day forecast for the month of June, 2000 of NCEP ...

  16. Confidence intervals in Flow Forecasting by using artificial neural networks

    Science.gov (United States)

    Panagoulia, Dionysia; Tsekouras, George

    2014-05-01

    variable of different ANN structures [3]. The performance of each ANN structure is evaluated by the voting analysis based on eleven criteria, which are the root mean square error (RMSE), the correlation index (R), the mean absolute percentage error (MAPE), the mean percentage error (MPE), the mean percentage error (ME), the percentage volume in errors (VE), the percentage error in peak (MF), the normalized mean bias error (NMBE), the normalized root mean bias error (NRMSE), the Nash-Sutcliffe model efficiency coefficient (E) and the modified Nash-Sutcliffe model efficiency coefficient (E1). The next day flow for the test set is calculated using the best ANN structure's model. Consequently, the confidence intervals of various confidence levels for training, evaluation and test sets are compared in order to explore the generalisation dynamics of confidence intervals from training and evaluation sets. [1] H.S. Hippert, C.E. Pedreira, R.C. Souza, "Neural networks for short-term load forecasting: A review and evaluation," IEEE Trans. on Power Systems, vol. 16, no. 1, 2001, pp. 44-55. [2] G. J. Tsekouras, N.E. Mastorakis, F.D. Kanellos, V.T. Kontargyri, C.D. Tsirekis, I.S. Karanasiou, Ch.N. Elias, A.D. Salis, P.A. Kontaxis, A.A. Gialketsi: "Short term load forecasting in Greek interconnected power system using ANN: Confidence Interval using a novel re-sampling technique with corrective Factor", WSEAS International Conference on Circuits, Systems, Electronics, Control & Signal Processing, (CSECS '10), Vouliagmeni, Athens, Greece, December 29-31, 2010. [3] D. Panagoulia, I. Trichakis, G. J. Tsekouras: "Flow Forecasting via Artificial Neural Networks - A Study for Input Variables conditioned on atmospheric circulation", European Geosciences Union, General Assembly 2012 (NH1.1 / AS1.16 - Extreme meteorological and hydrological events induced by severe weather and climate change), Vienna, Austria, 22-27 April 2012.

  17. Toward a Marine Ecological Forecasting System

    Science.gov (United States)

    2010-06-01

    coral bleaching , living resource distribution, and pathogen progression). An operational ecological forecasting system depends upon the assimilation of...space scales (e.g., harmful algal blooms, dissolved oxygen concentration (hypoxia), water quality/beach closures, coral bleaching , living resource...advance. Two beaches in Lake Michigan have been selected for initial implementation. Forecasting Coral Bleaching in relation to Ocean Temperatures

  18. Advances in Global Flood Forecasting Systems

    Science.gov (United States)

    Thielen-del Pozo, J.; Pappenberger, F.; Burek, P.; Alfieri, L.; Kreminski, B.; Muraro, D.

    2012-12-01

    A trend of increasing number of heavy precipitation events over many regions in the world during the past century has been observed (IPCC, 2007), but conclusive results on a changing frequency or intensity of floods have not yet been established. However, the socio-economic impact particularly of floods is increasing at an alarming trend. Thus anticipation of severe events is becoming a key element of society to react timely to effectively reduce socio-economic damage. Anticipation is essential on local as well as on national or trans-national level since management of response and aid for major disasters requires a substantial amount of planning and information on different levels. Continental and trans-national flood forecasting systems already exist. The European Flood Awareness System (EFAS) has been developed in close collaboration with the National services and is going operational in 2012, enhancing the national forecasting centres with medium-range probabilistic added value information while at the same time providing the European Civil Protection with harmonised information on ongoing and upcoming floods for improved aid management. Building on experiences and methodologies from EFAS, a Global Flood Awareness System (GloFAS) has now been developed jointly between researchers from the European Commission Joint Research Centre (JRC) and the European Centre for Medium-Range Weather Forecast (ECWMF). The prototype couples HTESSEL, the land-surface scheme of the ECMWF NWP model with the LISFLOOD hydrodynamic model for the flow routing in the river network. GloFAS is set-up on global scale with horizontal grid spacing of 0.1 degree. The system is driven with 51 ensemble members from VAREPS with a time horizon of 15 days. In order to allow for the routing in the large rivers, the coupled model is run for 45 days assuming zero rainfall after day 15. Comparison with observations have shown that in some rivers the system performs quite well while in others the hydro

  19. Deep Neural Network Based Demand Side Short Term Load Forecasting

    Directory of Open Access Journals (Sweden)

    Seunghyoung Ryu

    2016-12-01

    Full Text Available In the smart grid, one of the most important research areas is load forecasting; it spans from traditional time series analyses to recent machine learning approaches and mostly focuses on forecasting aggregated electricity consumption. However, the importance of demand side energy management, including individual load forecasting, is becoming critical. In this paper, we propose deep neural network (DNN-based load forecasting models and apply them to a demand side empirical load database. DNNs are trained in two different ways: a pre-training restricted Boltzmann machine and using the rectified linear unit without pre-training. DNN forecasting models are trained by individual customer’s electricity consumption data and regional meteorological elements. To verify the performance of DNNs, forecasting results are compared with a shallow neural network (SNN, a double seasonal Holt–Winters (DSHW model and the autoregressive integrated moving average (ARIMA. The mean absolute percentage error (MAPE and relative root mean square error (RRMSE are used for verification. Our results show that DNNs exhibit accurate and robust predictions compared to other forecasting models, e.g., MAPE and RRMSE are reduced by up to 17% and 22% compared to SNN and 9% and 29% compared to DSHW.

  20. Short-Term Load Forecasting Based Automatic Distribution Network Reconfiguration: Preprint

    Energy Technology Data Exchange (ETDEWEB)

    Jiang, Huaiguang [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Ding, Fei [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Zhang, Yingchen [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Jiang, Huaiguang [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Ding, Fei [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Zhang, Yingchen [National Renewable Energy Laboratory (NREL), Golden, CO (United States)

    2017-07-26

    In the traditional dynamic network reconfiguration study, the optimal topology is determined at every scheduled time point by using the real load data measured at that time. The development of load forecasting technique can provide accurate prediction of load power that will happen in future time and provide more information about load changes. With the inclusion of load forecasting, the optimal topology can be determined based on the predicted load conditions during the longer time period instead of using the snapshot of load at the time when the reconfiguration happens, and thus it can provide information to the distribution system operator (DSO) to better operate the system reconfiguration to achieve optimal solutions. Thus, this paper proposes a short-term load forecasting based approach for automatically reconfiguring distribution systems in a dynamic and pre-event manner. Specifically, a short-term and high-resolution distribution system load forecasting approach is proposed with support vector regression (SVR) based forecaster and parallel parameters optimization. And the network reconfiguration problem is solved by using the forecasted load continuously to determine the optimal network topology with the minimum loss at the future time. The simulation results validate and evaluate the proposed approach.

  1. Short-Term Load Forecasting-Based Automatic Distribution Network Reconfiguration

    Energy Technology Data Exchange (ETDEWEB)

    Jiang, Huaiguang [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Ding, Fei [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Zhang, Yingchen [National Renewable Energy Laboratory (NREL), Golden, CO (United States)

    2017-08-23

    In a traditional dynamic network reconfiguration study, the optimal topology is determined at every scheduled time point by using the real load data measured at that time. The development of the load forecasting technique can provide an accurate prediction of the load power that will happen in a future time and provide more information about load changes. With the inclusion of load forecasting, the optimal topology can be determined based on the predicted load conditions during a longer time period instead of using a snapshot of the load at the time when the reconfiguration happens; thus, the distribution system operator can use this information to better operate the system reconfiguration and achieve optimal solutions. This paper proposes a short-term load forecasting approach to automatically reconfigure distribution systems in a dynamic and pre-event manner. Specifically, a short-term and high-resolution distribution system load forecasting approach is proposed with a forecaster based on support vector regression and parallel parameters optimization. The network reconfiguration problem is solved by using the forecasted load continuously to determine the optimal network topology with the minimum amount of loss at the future time. The simulation results validate and evaluate the proposed approach.

  2. Optimal Control and Forecasting of Complex Dynamical Systems

    CERN Document Server

    Grigorenko, Ilya

    2006-01-01

    This important book reviews applications of optimization and optimal control theory to modern problems in physics, nano-science and finance. The theory presented here can be efficiently applied to various problems, such as the determination of the optimal shape of a laser pulse to induce certain excitations in quantum systems, the optimal design of nanostructured materials and devices, or the control of chaotic systems and minimization of the forecast error for a given forecasting model (for example, artificial neural networks). Starting from a brief review of the history of variational calcul

  3. Improving real time flood forecasting using fuzzy inference system

    Science.gov (United States)

    Lohani, Anil Kumar; Goel, N. K.; Bhatia, K. K. S.

    2014-02-01

    In order to improve the real time forecasting of foods, this paper proposes a modified Takagi Sugeno (T-S) fuzzy inference system termed as threshold subtractive clustering based Takagi Sugeno (TSC-T-S) fuzzy inference system by introducing the concept of rare and frequent hydrological situations in fuzzy modeling system. The proposed modified fuzzy inference systems provide an option of analyzing and computing cluster centers and membership functions for two different hydrological situations, i.e. low to medium flows (frequent events) as well as high to very high flows (rare events) generally encountered in real time flood forecasting. The methodology has been applied for flood forecasting using the hourly rainfall and river flow data of upper Narmada basin, Central India. The available rainfall-runoff data has been classified in frequent and rare events and suitable TSC-T-S fuzzy model structures have been suggested for better forecasting of river flows. The performance of the model during calibration and validation is evaluated by performance indices such as root mean square error (RMSE), model efficiency and coefficient of correlation (R). In flood forecasting, it is very important to know the performance of flow forecasting model in predicting higher magnitude flows. The above described performance criteria do not express the prediction ability of the model precisely from higher to low flow region. Therefore, a new model performance criterion termed as peak percent threshold statistics (PPTS) is proposed to evaluate the performance of a flood forecasting model. The developed model has been tested for different lead periods using hourly rainfall and discharge data. Further, the proposed fuzzy model results have been compared with artificial neural networks (ANN), ANN models for different classes identified by Self Organizing Map (SOM) and subtractive clustering based Takagi Sugeno fuzzy model (SC-T-S fuzzy model). It has been concluded from the study that the

  4. Day-Ahead Electricity Price Forecasting Using a Hybrid Principal Component Analysis Network

    Directory of Open Access Journals (Sweden)

    Ching-Ping Wu

    2012-11-01

    Full Text Available Bidding competition is one of the main transaction approaches in a deregulated electricity market. Locational marginal prices (LMPs resulting from bidding competition and system operation conditions indicate electricity values at a node or in an area. The LMP reveals important information for market participants in developing their bidding strategies. Moreover, LMP is also a vital indicator for the Security Coordinator to perform market redispatch for congestion management. This paper presents a method using a principal component analysis (PCA network cascaded with a multi-layer feedforward (MLF network for forecasting LMPs in a day-ahead market. The PCA network extracts essential features from periodic information in the market. These features serve as inputs to the MLF network for forecasting LMPs. The historical LMPs in the PJM market are employed to test the proposed method. It is found that the proposed method is capable of forecasting day-ahead LMP values efficiently.

  5. Global Ensemble Forecast System (GEFS) [2.5 Deg.

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Global Ensemble Forecast System (GEFS) is a weather forecast model made up of 21 separate forecasts, or ensemble members. The National Centers for Environmental...

  6. WOD - Weather On Demand forecasting system

    Science.gov (United States)

    Rognvaldsson, Olafur; Ragnarsson, Logi; Stanislawska, Karolina

    2017-04-01

    The backbone of the Belgingur forecasting system (called WOD - Weather On Demand) is the WRF-Chem atmospheric model, with a number of in-house customisations. Initial and boundary data are taken from the Global Forecasting System, operated by the National Oceanic and Atmospheric Administration (NOAA). Operational forecasts use cycling of a number of parameters, mainly deep soil and surface fields. This is done to minimise spin-up effects and to ensure proper book-keeping of hydrological fields such as snow accumulation and runoff, as well as the constituents of various chemical parameters. The WOD system can be used to create conventional short- to medium-range weather forecasts for any location on the globe. The WOD system can also be used for air quality purposes (e.g. dispersion forecasts from volcanic eruptions) and as a tool to provide input to other modelling systems, such as hydrological models. A wide variety of post-processing options are also available, making WOD an ideal tool for creating highly customised output that can be tailored to the specific needs of individual end-users. The most recent addition to the WOD system is an integrated verification system where forecasts can be compared to surface observations from chosen locations. Forecast visualisation, such as weather charts, meteograms, weather icons and tables, is done via number of web components that can be configured to serve the varying needs of different end-users. The WOD system itself can be installed in an automatic way on hardware running a range of Linux based OS. System upgrades can also be done in semi-automatic fashion, i.e. upgrades and/or bug-fixes can be pushed to the end-user hardware without system downtime. Importantly, the WOD system requires only rudimentary knowledge of the WRF modelling, and the Linux operating systems on behalf of the end-user, making it an ideal NWP tool in locations with limited IT infrastructure.

  7. Solar and wind forecasting by NARX neural networks

    Directory of Open Access Journals (Sweden)

    Di Piazza Annalisa

    2016-01-01

    Full Text Available The nonlinear autoregressive network with exogenous input (NARX is used to perform hourly solar irradiation and wind speed forecasting, according to a multi-step ahead approach. Temperature has been considered as the exogenous variable. The NARX topology selection is supported by a combined use of two techniques: (1 a genetic algorithm (GA-based optimization technique and (2 a method that determines the optimal network architecture by pruning (optimal brain surgeon (OBS strategy. The considered variables are observed at hourly scale in a seven year dataset and the forecasting is done for several time horizons in the range from 8 to 24 h ahead.

  8. Flood Forecasting via Time Lag Forward Network; Kelantan, Malaysia

    Science.gov (United States)

    Jajarmizadeh, Milad; Mohd Sidek, Lariyah; Bte Basri, Hidayah; Shakira Jaffar, Aminah

    2016-03-01

    Forecasting water level is one of the critical issues in Malaysia for Kelantan region. Based on the flood events in 2014, this study investigates the hourly-forecasting of water level in one station namely Kg Jenob in Kelantan. For this issue, Time Lag Forward Network (TLFN) is evaluated for forecasting the water level as dynamic model. Heuristic method in stepwise forward methodology is performed. Rainfall and water level are the input and output of the modelling respectively. For selected flood period 15/12/2014 to 30/12/2014, 8 scenarios are developed to obtain a minimum error in water level forecasting. By monitoring the error, it will show that the optimum configuration of network has 2 processors in hidden layer and 7 lags have enough contribution on the result of hourly forecasting. Transfer functions in hidden and output layers are is Tangent hyperbolic and bias. Observed and simulated data are compared with usual error criteria called Mean Square Error (MSE) and Root Mean Square Error (RMSE) which obtained 0.005 and 0.07 respectively. In conclusion, this study will be as a baseline for Kelantan to show that TLFN has promising result to forecast the flood events.

  9. Weather modeling and forecasting of PV systems operation

    CERN Document Server

    Paulescu, Marius; Gravila, Paul; Badescu, Viorel

    2012-01-01

    In the past decade, there has been a substantial increase of grid-feeding photovoltaic applications, thus raising the importance of solar electricity in the energy mix. This trend is expected to continue and may even increase. Apart from the high initial investment cost, the fluctuating nature of the solar resource raises particular insertion problems in electrical networks. Proper grid managing demands short- and long-time forecasting of solar power plant output. Weather modeling and forecasting of PV systems operation is focused on this issue. Models for predicting the state of the sky, nowc

  10. Long forecast horizon to improve Real Time Control of urban drainage systems

    DEFF Research Database (Denmark)

    Courdent, Vianney Augustin Thomas; Vezzaro, Luca; Mikkelsen, Peter Steen

    2014-01-01

    on DORA’s approach, this study investigated the implementation of long forecast horizon using an ensemble forecast from a Numerical Weather Prediction (NWP) model. The uncertainty of the prediction is characterized by an ensemble of 25 forecast scenarios. According to the status of the UDS......) strategy was developed to operate Urban Drainage Systems (UDS) in order to minimize the expected overflow risk by considering the water volume presently stored in the drainage network, the expected runoff volume based on a 2-hours radar forecast model and an estimated uncertainty of the runoff forecast...... and the forecasted runoff volumes, the objectives for the control strategies might vary from optimization of water volumes to reduction of CSO risk. Thus different modes are implemented in DORA-LF (Long Forecast) in order to adjust the control strategies to the situations. In order to handle the long forecast...

  11. Using ensemble weather forecast in a risk based real time optimization of urban drainage systems

    DEFF Research Database (Denmark)

    Courdent, Vianney Augustin Thomas; Vezzaro, Luca; Mikkelsen, Peter Steen

    2015-01-01

    on DORA's approach, this study investigated the implementation of long forecast horizon using an ensemble forecast from a Numerical Weather Prediction (NWP) model. The uncertainty of the prediction is characterized by an ensemble of 25 forecast scenarios. According to the status of the UDS......) strategy was developed to operate Urban Drainage Systems (UDS) in order to minimize the expected overflow risk by considering the water volume presently stored in the drainage network, the expected runoff volume based on a 2-hours radar forecast model and an estimated uncertainty of the runoff forecast...... and the forecasted runoff volumes, the objectives for the control strategies might vary from optimization of water volumes to reduction of CSO risk. Thus different modes are implemented in DORA-LF (Long Forecast) in order to adjust the control strategies to the situations. In order to handle the long forecast...

  12. Multi nodal load forecasting in electric power systems using a radial basis neural network; Previsao de carga multinodal em sistemas eletricos de potencia usando uma rede neural de base radial

    Energy Technology Data Exchange (ETDEWEB)

    Altran, A.B.; Lotufo, A.D.P.; Minussi, C.R. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil). Dept. de Engenharia Eletrica], Emails: lealtran@yahoo.com.br, annadiva@dee.feis.unesp.br, minussi@dee.feis.unesp.br; Lopes, M.L.M. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil). Dept. de Matematica], E-mail: mara@mat.feis.unesp.br

    2009-07-01

    This paper presents a methodology for electrical load forecasting, using radial base functions as activation function in artificial neural networks with the training by backpropagation algorithm. This methodology is applied to short term electrical load forecasting (24 h ahead). Therefore, results are presented analyzing the use of radial base functions substituting the sigmoid function as activation function in multilayer perceptron neural networks. However, the main contribution of this paper is the proposal of a new formulation of load forecasting dedicated to the forecasting in several points of the electrical network, as well as considering several types of users (residential, commercial, industrial). It deals with the MLF (Multimodal Load Forecasting), with the same processing time as the GLF (Global Load Forecasting). (author)

  13. Short-term load forecasting of power system

    Science.gov (United States)

    Xu, Xiaobin

    2017-05-01

    In order to ensure the scientific nature of optimization about power system, it is necessary to improve the load forecasting accuracy. Power system load forecasting is based on accurate statistical data and survey data, starting from the history and current situation of electricity consumption, with a scientific method to predict the future development trend of power load and change the law of science. Short-term load forecasting is the basis of power system operation and analysis, which is of great significance to unit combination, economic dispatch and safety check. Therefore, the load forecasting of the power system is explained in detail in this paper. First, we use the data from 2012 to 2014 to establish the partial least squares model to regression analysis the relationship between daily maximum load, daily minimum load, daily average load and each meteorological factor, and select the highest peak by observing the regression coefficient histogram Day maximum temperature, daily minimum temperature and daily average temperature as the meteorological factors to improve the accuracy of load forecasting indicators. Secondly, in the case of uncertain climate impact, we use the time series model to predict the load data for 2015, respectively, the 2009-2014 load data were sorted out, through the previous six years of the data to forecast the data for this time in 2015. The criterion for the accuracy of the prediction is the average of the standard deviations for the prediction results and average load for the previous six years. Finally, considering the climate effect, we use the BP neural network model to predict the data in 2015, and optimize the forecast results on the basis of the time series model.

  14. Forecasting the Short-Term Passenger Flow on High-Speed Railway with Neural Networks

    Directory of Open Access Journals (Sweden)

    Mei-Quan Xie

    2014-01-01

    Full Text Available Short-term passenger flow forecasting is an important component of transportation systems. The forecasting result can be applied to support transportation system operation and management such as operation planning and revenue management. In this paper, a divide-and-conquer method based on neural network and origin-destination (OD matrix estimation is developed to forecast the short-term passenger flow in high-speed railway system. There are three steps in the forecasting method. Firstly, the numbers of passengers who arrive at each station or depart from each station are obtained from historical passenger flow data, which are OD matrices in this paper. Secondly, short-term passenger flow forecasting of the numbers of passengers who arrive at each station or depart from each station based on neural network is realized. At last, the OD matrices in short-term time are obtained with an OD matrix estimation method. The experimental results indicate that the proposed divide-and-conquer method performs well in forecasting the short-term passenger flow on high-speed railway.

  15. Peak load demand forecasting using two-level discrete wavelet decomposition and neural network algorithm

    Science.gov (United States)

    Bunnoon, Pituk; Chalermyanont, Kusumal; Limsakul, Chusak

    2010-02-01

    This paper proposed the discrete transform and neural network algorithms to obtain the monthly peak load demand in mid term load forecasting. The mother wavelet daubechies2 (db2) is employed to decomposed, high pass filter and low pass filter signals from the original signal before using feed forward back propagation neural network to determine the forecasting results. The historical data records in 1997-2007 of Electricity Generating Authority of Thailand (EGAT) is used as reference. In this study, historical information of peak load demand(MW), mean temperature(Tmean), consumer price index (CPI), and industrial index (economic:IDI) are used as feature inputs of the network. The experimental results show that the Mean Absolute Percentage Error (MAPE) is approximately 4.32%. This forecasting results can be used for fuel planning and unit commitment of the power system in the future.

  16. Material procedure quality forecast based on genetic BP neural network

    Science.gov (United States)

    Zheng, Bao-Hua

    2017-07-01

    Material procedure quality forecast plays an important role in quality control. This paper proposes a prediction model based on genetic algorithm (GA) and back propagation (BP) neural network. It can obtain the initial weights and thresholds of optimized BP neural network with the GA global search ability. A material process quality prediction model with the optimized BP neural network is adopted to predict the error of future process to measure the accuracy of process quality. The results show that the proposed method has the advantages of high accuracy and fast convergence rate compared with BP neural network.

  17. Streamflow Forecasting Using Nuero-Fuzzy Inference System

    Science.gov (United States)

    Nanduri, U. V.; Swain, P. C.

    2005-12-01

    The prediction of flow into a reservoir is fundamental in water resources planning and management. The need for timely and accurate streamflow forecasting is widely recognized and emphasized by many in water resources fraternity. Real-time forecasts of natural inflows to reservoirs are of particular interest for operation and scheduling. The physical system of the river basin that takes the rainfall as an input and produces the runoff is highly nonlinear, complicated and very difficult to fully comprehend. The system is influenced by large number of factors and variables. The large spatial extent of the systems forces the uncertainty into the hydrologic information. A variety of methods have been proposed for forecasting reservoir inflows including conceptual (physical) and empirical (statistical) models (WMO 1994), but none of them can be considered as unique superior model (Shamseldin 1997). Owing to difficulties of formulating reasonable non-linear watershed models, recent attempts have resorted to Neural Network (NN) approach for complex hydrologic modeling. In recent years the use of soft computing in the field of hydrological forecasting is gaining ground. The relatively new soft computing technique of Adaptive Neuro-Fuzzy Inference System (ANFIS), developed by Jang (1993) is able to take care of the non-linearity, uncertainty, and vagueness embedded in the system. It is a judicious combination of the Neural Networks and fuzzy systems. It can learn and generalize highly nonlinear and uncertain phenomena due to the embedded neural network (NN). NN is efficient in learning and generalization, and the fuzzy system mimics the cognitive capability of human brain. Hence, ANFIS can learn the complicated processes involved in the basin and correlate the precipitation to the corresponding discharge. In the present study, one step ahead forecasts are made for ten-daily flows, which are mostly required for short term operational planning of multipurpose reservoirs. A

  18. Climate Prediction Center (CPC) NCEP-Global Forecast System (GFS) Precipitation Forecast Product

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Global Forecast System (GFS) forecast precipitation data at 37.5km resolution is created at the NOAA Climate Prediction Center for the purpose of near real-time...

  19. SHORT-TERM SOLAR RADIATION FORECASTING BY USING AN ITERATIVE COMBINATION OF WAVELET ARTIFICIAL NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Julio Cesar Royer

    2016-03-01

    Full Text Available The information provided by accurate forecasts of solar energy time series are considered essential for performing an appropriate prediction of the electrical power that will be available in an electric system, as pointed out in Zhou et al. (2011. However, since the underlying data are highly non-stationary, it follows that to produce their accurate predictions is a very difficult assignment. In order to accomplish it, this paper proposes an iterative Combination of Wavelet Artificial Neural Networks (CWANN which is aimed to produce short-term solar radiation time series forecasting. Basically, the CWANN method can be split into three stages: at first one, a decomposition of level p, defined in terms of a wavelet basis, of a given solar radiation time series is performed, generating r+1 Wavelet Components (WC; at second one, these r+1 WCs are individually modeled by the k different ANNs, where k>5, and the 5 best forecasts of each WC are combined by means of another ANN, producing the combined forecasts of WC; and, at third one, the combined forecasts WC are simply added, generating the forecasts of the underlying solar radiation data. An iterative algorithm is proposed for iteratively searching for the optimal values for the CWANN parameters, as we will see. In order to evaluate it, ten real solar radiation time series of Brazilian system were modeled here. In all statistical results, the CWANN method has achieved remarkable greater forecasting performances when compared with a traditional ANN (described in Section 2.1.

  20. Short-Term Load Forecasting Model Based on Quantum Elman Neural Networks

    Directory of Open Access Journals (Sweden)

    Zhisheng Zhang

    2016-01-01

    Full Text Available Short-term load forecasting model based on quantum Elman neural networks was constructed in this paper. The quantum computation and Elman feedback mechanism were integrated into quantum Elman neural networks. Quantum computation can effectively improve the approximation capability and the information processing ability of the neural networks. Quantum Elman neural networks have not only the feedforward connection but also the feedback connection. The feedback connection between the hidden nodes and the context nodes belongs to the state feedback in the internal system, which has formed specific dynamic memory performance. Phase space reconstruction theory is the theoretical basis of constructing the forecasting model. The training samples are formed by means of K-nearest neighbor approach. Through the example simulation, the testing results show that the model based on quantum Elman neural networks is better than the model based on the quantum feedforward neural network, the model based on the conventional Elman neural network, and the model based on the conventional feedforward neural network. So the proposed model can effectively improve the prediction accuracy. The research in the paper makes a theoretical foundation for the practical engineering application of the short-term load forecasting model based on quantum Elman neural networks.

  1. Skillful seasonal forecasts of Arctic sea ice retreat and advance dates in a dynamical forecast system

    Science.gov (United States)

    Sigmond, M.; Reader, M. C.; Flato, G. M.; Merryfield, W. J.; Tivy, A.

    2016-12-01

    The need for skillful seasonal forecasts of Arctic sea ice is rapidly increasing. Technology to perform such forecasts with coupled atmosphere-ocean-sea ice systems has only recently become available, with previous skill evaluations mainly limited to area-integrated quantities. Here we show, based on a large set of retrospective ensemble model forecasts, that a dynamical forecast system produces skillful seasonal forecasts of local sea ice retreat and advance dates - variables that are of great interest to a wide range of end users. Advance dates can generally be skillfully predicted at longer lead times ( 5 months on average) than retreat dates ( 3 months). The skill of retreat date forecasts mainly stems from persistence of initial sea ice anomalies, whereas advance date forecasts benefit from longer time scale and more predictable variability in ocean temperatures. These results suggest that further investments in the development of dynamical seasonal forecast systems may result in significant socioeconomic benefits.

  2. Initialization of multilayer forecasting artifical neural networks

    OpenAIRE

    Bochkarev, Vladimir V.; Maslennikova, Yulia S.

    2014-01-01

    In this paper, a new method was developed for initialising artificial neural networks predicting dynamics of time series. Initial weighting coefficients were determined for neurons analogously to the case of a linear prediction filter. Moreover, to improve the accuracy of the initialization method for a multilayer neural network, some variants of decomposition of the transformation matrix corresponding to the linear prediction filter were suggested. The efficiency of the proposed neural netwo...

  3. An Artificial Neural Network for Data Forecasting Purposes

    Directory of Open Access Journals (Sweden)

    Catalina Lucia COCIANU

    2015-01-01

    Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.

  4. Short-term load forecasting using neural network for future smart grid application

    Science.gov (United States)

    Zennamo, Joseph Anthony, III

    Short-term load forecasting of power system has been a classic problem for a long time. Not merely it has been researched extensively and intensively, but also a variety of forecasting methods has been raised. This thesis outlines some aspects and functions of smart meter. It also presents different policies and current statuses as well as future projects and objectives of SG development in several countries. Then the thesis compares main aspects about latest products of smart meter from different companies. Lastly, three types of prediction models are established in MATLAB to emulate the functions of smart grid in the short-term load forecasting, and then their results are compared and analyzed in terms of accuracy. For this thesis, more variables such as dew point temperature are used in the Neural Network model to achieve more accuracy for better short-term load forecasting results.

  5. Wavelet Neural Network Model for Yield Spread Forecasting

    Directory of Open Access Journals (Sweden)

    Firdous Ahmad Shah

    2017-11-01

    Full Text Available In this study, a hybrid method based on coupling discrete wavelet transforms (DWTs and artificial neural network (ANN for yield spread forecasting is proposed. The discrete wavelet transform (DWT using five different wavelet families is applied to decompose the five different yield spreads constructed at shorter end, longer end, and policy relevant area of the yield curve to eliminate noise from them. The wavelet coefficients are then used as inputs into Levenberg-Marquardt (LM ANN models to forecast the predictive power of each of these spreads for output growth. We find that the yield spreads constructed at the shorter end and policy relevant areas of the yield curve have a better predictive power to forecast the output growth, whereas the yield spreads, which are constructed at the longer end of the yield curve do not seem to have predictive information for output growth. These results provide the robustness to the earlier results.

  6. Improved Neural Networks with Random Weights for Short-Term Load Forecasting

    Science.gov (United States)

    Lang, Kun; Zhang, Mingyuan; Yuan, Yongbo

    2015-01-01

    An effective forecasting model for short-term load plays a significant role in promoting the management efficiency of an electric power system. This paper proposes a new forecasting model based on the improved neural networks with random weights (INNRW). The key is to introduce a weighting technique to the inputs of the model and use a novel neural network to forecast the daily maximum load. Eight factors are selected as the inputs. A mutual information weighting algorithm is then used to allocate different weights to the inputs. The neural networks with random weights and kernels (KNNRW) is applied to approximate the nonlinear function between the selected inputs and the daily maximum load due to the fast learning speed and good generalization performance. In the application of the daily load in Dalian, the result of the proposed INNRW is compared with several previously developed forecasting models. The simulation experiment shows that the proposed model performs the best overall in short-term load forecasting. PMID:26629825

  7. Improvements in medium range weather forecasting system of India

    Indian Academy of Sciences (India)

    Medium range weather forecasts are being generated in real time using Global Data Assimilation Forecasting System (GDAFS) at NCMRWF since 1994. The system has been continuously upgraded in terms of data usage, assimilation and forecasting system. Recently this system was upgraded to a horizontal resolution of ...

  8. Matlab for Forecasting of Electric Power Load Based on BP Neural Network

    Science.gov (United States)

    Wang, Xi-Ping; Shi, Ming-Xi

    Modeling and predicting electricity consumption play a vital role both in developed and developing countries for policy makers and related organizations. Improve load forecasting technology level is not only beneficial to plan power management and make reasonable construction plan, but also good for saving energy and reducing power cost, and then, it can improve the economic benefits and social benefit for power system. BP neural network is one of the most widely used neural networks and it has many advantages in the power load forecasting. Matlab has become the best technology application software which has been internationally recognized, the software has many characteristics, such as data visualization function and neural network toolbox, for these, it is the essential software when we do some research on neural network.

  9. Stacked Heterogeneous Neural Networks for Time Series Forecasting

    Directory of Open Access Journals (Sweden)

    Florin Leon

    2010-01-01

    Full Text Available A hybrid model for time series forecasting is proposed. It is a stacked neural network, containing one normal multilayer perceptron with bipolar sigmoid activation functions, and the other with an exponential activation function in the output layer. As shown by the case studies, the proposed stacked hybrid neural model performs well on a variety of benchmark time series. The combination of weights of the two stack components that leads to optimal performance is also studied.

  10. Ocean wave forecasting using recurrent neural networks

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.; Prabaharan, N.

    to the biological neurons, works on the input and output passing through a hidden layer. The ANN used here is a data- oriented modeling technique to find relations between input and output patterns by self learning and without any fixed mathematical form assumed... = 1/p ? Ep (2) Where, Ep = ? ? (Tk ?Ok)2 (3) p is the total number of training patterns; Tk is the actual output and Ok is the predicted output at kth output node. In the learning process of backpropagation neural network...

  11. Drought forecasting: Methodological topics from a systems perspective

    Science.gov (United States)

    Krzysztofowicz, R.

    1991-12-01

    A systemic framework is presented for organizing knowledge about drought forecasting. It includes these topics: couplings among a descriptive drought model, monitoring system, and forecasting system; propagation of uncertainties; types of forecasts and attributes of performance such as the lead time and skill; sufficient measures of skill and economic value of forecasts; theoretical and operational limits of predictability; and the interface between forecasts and drought management decisions. Reviews of operational forecasts of the seasonal snowmelt runoff volumes and forecasts of the seasonal cyclone frequencies. temperature, and precipitation in the United States illustrate the methodological topics, outline the present limits of drought predictability, and suggest promising research paths. Among them are modeling of forecast uncertainties and their propagation from states of atmospheric circulation to states of a hydrologic regime, and exploring novel forms of the hydro-meteorologic coupling that would extend the lead time and/or increase the skill of long-range drought forecasts.

  12. Road icing forecasting and detecting system

    Science.gov (United States)

    Xu, Hongke; Zheng, Jinnan; Li, Peiqi; Wang, Qiucai

    2017-05-01

    Regard for the facts that the low accuracy and low real-time of the artificial observation to determine the road icing condition, and it is difficult to forecast icing situation, according to the main factors influencing the road-icing, and the electrical characteristics reflected by the pavement ice layer, this paper presents an innovative system, that is, ice-forecasting of the highway's dangerous section. The system bases on road surface water salinity measurements and pavement temperature measurement to calculate the freezing point of water and temperature change trend, and then predicts the occurrence time of road icing; using capacitance measurements to verdict the road surface is frozen or not; This paper expounds the method of using single chip microcomputer as the core of the control system and described the business process of the system.

  13. Road landslide information management and forecasting system base on GIS.

    Science.gov (United States)

    Wang, Wei Dong; Du, Xiang Gang; Xie, Cui Ming

    2009-09-01

    Take account of the characters of road geological hazard and its supervision, it is very important to develop the Road Landslides Information Management and Forecasting System based on Geographic Information System (GIS). The paper presents the system objective, function, component modules and key techniques in the procedure of system development. The system, based on the spatial information and attribute information of road geological hazard, was developed and applied in Guizhou, a province of China where there are numerous and typical landslides. The manager of communication, using the system, can visually inquire all road landslides information based on regional road network or on the monitoring network of individual landslide. Furthermore, the system, integrated with mathematical prediction models and the GIS's strongpoint on spatial analyzing, can assess and predict landslide developing procedure according to the field monitoring data. Thus, it can efficiently assists the road construction or management units in making decision to control the landslides and to reduce human vulnerability.

  14. Forecast of consumer behaviour based on neural networks models comparison

    Directory of Open Access Journals (Sweden)

    Michael Štencl

    2012-01-01

    Full Text Available The aim of this article is comparison of accuracy level of forecasted values of several artificial neural network models. The comparison is performed on datasets of Czech household consumption values. Several statistical models often resolve this task with more or fewer restrictions. In previous work where models’ input conditions were not so strict and model with missing data was used (the time series didn’t contain many values we have obtained comparably good results with artificial neural networks. Two views – practical and theoretical, motivate the purpose of this study. Forecasting models for medium term prognosis of the main trends of Czech household consumption is part of the faculty research design grant MSM 6215648904/03/02 (Sub-task 5.3 which defines the practical purpose. Testing of nonlinear autoregressive artificial neural network model compared with feed-forward neural network and radial basis function neural network defines the theoretical purpose. The performance metrics of the models were evaluated using a combination of common error metrics, namely Correlation Coefficient and Mean Square Error, together with the number of epochs and/or main prediction error.

  15. Combining neural networks and genetic algorithms for hydrological flow forecasting

    Science.gov (United States)

    Neruda, Roman; Srejber, Jan; Neruda, Martin; Pascenko, Petr

    2010-05-01

    predicting relative runoff show the best behavior so far. Utilizing the genetically evolved input filter improves the performance of yet another 5 per cent. In the future we would like to continue with experiments in on-line prediction using real-time data from Smeda River with 6 hours lead time forecast. Following the operational reality we will focus on classification of the runoffs into flood alert levels, and reformulation of the time series prediction task as a classification problem. The main goal of all this work is to improve flood warning system operated by the Czech Hydrometeorological Institute.

  16. UNCERTAINTY IN THE GLOBAL FORECAST SYSTEM

    Energy Technology Data Exchange (ETDEWEB)

    Werth, D.; Garrett, A.

    2009-04-15

    We validated one year of Global Forecast System (GFS) predictions of surface meteorological variables (wind speed, air temperature, dewpoint temperature, air pressure) over the entire planet for forecasts extending from zero hours into the future (an analysis) to 36 hours. Approximately 12,000 surface stations world-wide were included in this analysis. Root-Mean-Square- Errors (RMSE) increased as the forecast period increased from zero to 36 hours, but the initial RMSE were almost as large as the 36 hour forecast RMSE for all variables. Typical RMSE were 3 C for air temperature, 2-3mb for sea-level pressure, 3.5 C for dewpoint temperature and 2.5 m/s for wind speed. Approximately 20-40% of the GFS errors can be attributed to a lack of resolution of local features. We attribute the large initial RMSE for the zero hour forecasts to the inability of the GFS to resolve local terrain features that often dominate local weather conditions, e.g., mountain- valley circulations and sea and land breezes. Since the horizontal resolution of the GFS (about 1{sup o} of latitude and longitude) prevents it from simulating these locally-driven circulations, its performance will not improve until model resolution increases by a factor of 10 or more (from about 100 km to less than 10 km). Since this will not happen in the near future, an alternative for the near term to improve surface weather analyses and predictions for specific points in space and time would be implementation of a high-resolution, limited-area mesoscale atmospheric prediction model in regions of interest.

  17. North American Mesoscale Forecast System (NAM) [12 km

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The North American Mesoscale Forecast System (NAM) is one of the major regional weather forecast models run by the National Centers for Environmental Prediction...

  18. Global Forecast System (GFS) [0.5 Deg.

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Global Forecast System (GFS) is a weather forecast model produced by the National Centers for Environmental Prediction (NCEP). Dozens of atmospheric and...

  19. Radar Based Flow and Water Level Forecasting in Sewer Systems

    DEFF Research Database (Denmark)

    Thorndahl, Søren; Rasmussen, Michael R.; Grum, M.

    2009-01-01

    This paper describes the first radar based forecast of flow and/or water level in sewer systems in Denmark. The rainfall is successfully forecasted with a lead time of 1-2 hours, and flow/levels are forecasted an additional ½-1½ hours using models describing the behaviour of the sewer system. Both...

  20. Web Information Retrieval System for Technological Forecasting

    OpenAIRE

    Montiel, Raúl; Lezcano Airaldi, Luis; Favret, Fabián; Eckert, Karina

    2017-01-01

    Technological Forecasting and Competitive Intelligence are two different disciplines that, used together, provide the organizations with an invaluable analytic tool for the environment and the competing companies’ behavior. This kind of technology can be used for extracting useful information to make strategic decisions. This paper describes a Web mining system which gathers the users’ information requirements through a series of guided questions, constructs various search keys with the answe...

  1. Forecasting of IBOVESPA returns using feedforward evolutionary artificial neural networks

    Directory of Open Access Journals (Sweden)

    Edgar Leite dos Santos Filho

    2011-12-01

    Full Text Available Facing the challenges of anticipating financial market uncertainties and movements, and the necessity of taking buy or sell decisions supported by rational methods, market traders found in statistics and econometrics methods, the base to support their decisions. In several scientific papers about forecasting financial time series, method selection keeps as central concern. This paper compares the performance of evolutionary feedforward artificial neural network (EANN and an AR+GARCH model, for one step ahead forecasting of IBOVESPA returns. The EANN is trained by self-adapting differential evolution algorithm and AR+GARCH model is adjusted to be used as performance reference. The root mean square error (RMSE and U-Theil inequality coefficient were used as performance metrics. Simulation results showed  EANN feedforward achieved better results, fit better and captured the nonlinear behavior of returns.

  2. Forecasting stochastic neural network based on financial empirical mode decomposition.

    Science.gov (United States)

    Wang, Jie; Wang, Jun

    2017-06-01

    In an attempt to improve the forecasting accuracy of stock price fluctuations, a new one-step-ahead model is developed in this paper which combines empirical mode decomposition (EMD) with stochastic time strength neural network (STNN). The EMD is a processing technique introduced to extract all the oscillatory modes embedded in a series, and the STNN model is established for considering the weight of occurrence time of the historical data. The linear regression performs the predictive availability of the proposed model, and the effectiveness of EMD-STNN is revealed clearly through comparing the predicted results with the traditional models. Moreover, a new evaluated method (q-order multiscale complexity invariant distance) is applied to measure the predicted results of real stock index series, and the empirical results show that the proposed model indeed displays a good performance in forecasting stock market fluctuations. Copyright © 2017 Elsevier Ltd. All rights reserved.

  3. A Comparative Study of Neural Networks and ANFIS for Forecasting Attendance Rate of Soccer Games

    Directory of Open Access Journals (Sweden)

    Mehmet Şahin

    2017-11-01

    Full Text Available The main purpose of this study was to develop and apply a neural network (NN approach and an adaptive neuro-fuzzy inference system (ANFIS model for forecasting the attendance rates at soccer games. The models were designed based on the characteristics of the problem. Past real data was used. Training data was used for training the models, and the testing data was used for evaluating the performance of the forecasting models. The obtained forecasting results were compared to the actual data and to each other. To evaluate the performance of the models, two statistical indicators, Mean Absolute Deviation (MAD and mean absolute percent error (MAPE, were used. Based on the results, the proposed neural network approach and the ANFIS model were shown to be effective in forecasting attendance at soccer games. The neural network approach performed better than the ANFIS model. The main contribution of this study is to introduce two effective techniques for estimating attendance at sports games. This is the first attempt to use an ANFIS model for that purpose.

  4. Hydrological Forecasting in Mexico: Extending the University of Washington West-wide Seasonal Hydrologic Forecast System

    Science.gov (United States)

    Munoz-Arriola, F.; Thomas, G.; Wood, A.; Wagner-Gomez, A.; Lobato-Sanchez, R.; Lettenmaier, D. P.

    2007-12-01

    Hydrologic forecasting in areas constrained by the availability of hydrometeorological records is a notable challenge in water resource management. Techniques from the University of Washington West-wide Seasonal Hydrologic Forecast system www.hydro.washington.edu/forecast/westwide) for generating daily nowcasts in areas with sparse and time-varying station coverage have been extended from the western U.S. into Mexico. The primary forecasting approaches consist of ensembles based on the NWS ensemble streamflow prediction method (ESP; essentially resampling of climatology) and on NCEP Coupled Forecast System (CFS) outputs. These in turn are used to force the Variable Infiltration Capacity (VIC) macroscale hydrology model to produce streamflow ensembles. The initial hydrologic state utilized in the seasonal forecasting is generated by VIC using daily real-time hydrologic nowcasts, produced using forcings derived via an 'index-station percentile' approach from meteorological station data accessed in real time from Servicio Meteorológico Nacional (SMN). One-year lead time streamflow forecasts at monthly time step are produced at a set of major river locations in Mexico. As a case study, the streamflow forecasts, along with forecasts of reservoir evaporation, are used as input to the Simulation-Optimization (SIMOP) model of the Rio Yaqui system, one of the major agricultural production centers of Mexico. This is the first step in an eventual planned water management implementation over all of Mexico.

  5. Appraisal of artificial neural network for forecasting of economic parameters

    Science.gov (United States)

    Kordanuli, Bojana; Barjaktarović, Lidija; Jeremić, Ljiljana; Alizamir, Meysam

    2017-01-01

    The main aim of this research is to develop and apply artificial neural network (ANN) with extreme learning machine (ELM) and back propagation (BP) to forecast gross domestic product (GDP) and Hirschman-Herfindahl Index (HHI). GDP could be developed based on combination of different factors. In this investigation GDP forecasting based on the agriculture and industry added value in gross domestic product (GDP) was analysed separately. Other inputs are final consumption expenditure of general government, gross fixed capital formation (investments) and fertility rate. The relation between product market competition and corporate investment is contentious. On one hand, the relation can be positive, but on the other hand, the relation can be negative. Several methods have been proposed to monitor market power for the purpose of developing procedures to mitigate or eliminate the effects. The most widely used methods are based on indices such as the Hirschman-Herfindahl Index (HHI). The reliability of the ANN models were accessed based on simulation results and using several statistical indicators. Based upon simulation results, it was presented that ELM shows better performances than BP learning algorithm in applications of GDP and HHI forecasting.

  6. Urban Ozone Concentration Forecasting with Artificial Neural Network in Corsica

    Directory of Open Access Journals (Sweden)

    Tamas Wani

    2014-03-01

    Full Text Available Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France, needs to develop a short-term prediction model to lead its mission of information towards the public. Various deterministic models exist for local forecasting, but need important computing resources, a good knowledge of atmospheric processes and can be inaccurate because of local climatical or geographical particularities, as observed in Corsica, a mountainous island located in the Mediterranean Sea. As a result, we focus in this study on statistical models, and particularly Artificial Neural Networks (ANNs that have shown good results in the prediction of ozone concentration one hour ahead with data measured locally. The purpose of this study is to build a predictor realizing predictions of ozone 24 hours ahead in Corsica in order to be able to anticipate pollution peaks formation and to take appropriate preventive measures. Specific meteorological conditions are known to lead to particular pollution event in Corsica (e.g. Saharan dust events. Therefore, an ANN model will be used with pollutant and meteorological data for operational forecasting. Index of agreement of this model was calculated with a one year test dataset and reached 0.88.

  7. Short-term load and wind power forecasting using neural network-based prediction intervals.

    Science.gov (United States)

    Quan, Hao; Srinivasan, Dipti; Khosravi, Abbas

    2014-02-01

    Electrical power systems are evolving from today's centralized bulk systems to more decentralized systems. Penetrations of renewable energies, such as wind and solar power, significantly increase the level of uncertainty in power systems. Accurate load forecasting becomes more complex, yet more important for management of power systems. Traditional methods for generating point forecasts of load demands cannot properly handle uncertainties in system operations. To quantify potential uncertainties associated with forecasts, this paper implements a neural network (NN)-based method for the construction of prediction intervals (PIs). A newly introduced method, called lower upper bound estimation (LUBE), is applied and extended to develop PIs using NN models. A new problem formulation is proposed, which translates the primary multiobjective problem into a constrained single-objective problem. Compared with the cost function, this new formulation is closer to the primary problem and has fewer parameters. Particle swarm optimization (PSO) integrated with the mutation operator is used to solve the problem. Electrical demands from Singapore and New South Wales (Australia), as well as wind power generation from Capital Wind Farm, are used to validate the PSO-based LUBE method. Comparative results show that the proposed method can construct higher quality PIs for load and wind power generation forecasts in a short time.

  8. Research on Marine Photovoltaic Power Forecasting Based on Wavelet Transform and Echo State Network

    Directory of Open Access Journals (Sweden)

    Xinhui Du

    2017-08-01

    Full Text Available With the rapid development of photovoltaic power generation technology, photovoltaic power generation system has gradually become an important component of the integrated energy system of marine. High precision short-term photovoltaic power generation forecasting is becoming one of the key technologies in ship energy saving and ship energy efficiency improving. Aiming at the characteristics of marine photovoltaic power generation system, we designed a highprecision power forecasting model (WT+ESN for marine photovoltaic power generation system with anti-marine environmental interference. In this model, the information mining of the photovoltaic system in marine environment is carried out based on wavelet theory, then the forecasting model basing on echo state network is construct ed. Lastly, three kinds of error metrics are compared with the three traditional models by Matlab, the result shows that the model has high forecasting accuracy and strong robustness to marine environmental factors, which is of great significance to save fuel for ships, improve the energy utilization rate and assist the power dispatching and fuel dispatching of the marine power generation system.

  9. Management earnings forecasts and analyst forecasts: Evidence from mandatory disclosure system

    Directory of Open Access Journals (Sweden)

    Yutao Wang

    2015-06-01

    Full Text Available Distinct from the literature on the effects that management earnings forecasts (MEFs properties, such as point, range and qualitative estimations, have on analyst forecasts, this study explores the effects of selective disclosure of MEFs. Under China’s mandatory disclosure system, this study proposes that managers issue frequent forecasts to take advantage of opportune changes in predicted earnings. The argument herein is that this selective disclosure of MEFs increases information asymmetry and uncertainty, negatively influencing analyst earnings forecasts. Empirical evidence shows that firms that issue more frequent forecasts and make significant changes in MEFs are less likely to attract an analyst following, which can lead to less accurate analyst forecasts. The results imply that the selective disclosure of MEFs damages information transmission and market efficiency, which can enlighten regulators seeking to further enhance disclosure policies.

  10. Using Quantile Regression to Extend an Existing Wind Power Forecasting System with Probabilistic Forecasts

    DEFF Research Database (Denmark)

    Nielsen, Henrik Aalborg; Madsen, Henrik; Nielsen, Torben Skov

    2006-01-01

    For operational planning it is important to provide information about the situation-dependent uncertainty of a wind power forecast. Factors which influence the uncertainty of a wind power forecast include the predictability of the actual meteorological situation, the level of the predicted wind....... An existing wind power forecasting system (Zephyr/WPPT) is considered and it is shown how analysis of the forecast error can be used to build a model of the quantiles of the forecast error. Only explanatory variables or indices which are predictable are considered, whereby the model obtained can be used...... speed (due to the non-linearity of the power curve) and the forecast horizon. With respect to the predictability of the actual meteorological situation a number of explanatory variables are considered, some inspired by the literature. The article contains an overview of related work within the field...

  11. A Bayesian Network-Based Probabilistic Framework for Drought Forecasting and Outlook

    Directory of Open Access Journals (Sweden)

    Ji Yae Shin

    2016-01-01

    Full Text Available Reliable drought forecasting is necessary to develop mitigation plans to cope with severe drought. This study developed a probabilistic scheme for drought forecasting and outlook combined with quantification of the prediction uncertainties. The Bayesian network was mainly employed as a statistical scheme for probabilistic forecasting that can represent the cause-effect relationships between the variables. The structure of the Bayesian network-based drought forecasting (BNDF model was designed using the past, current, and forecasted drought condition. In this study, the drought conditions were represented by the standardized precipitation index (SPI. The accuracy of forecasted SPIs was assessed by comparing the observed SPIs and confidence intervals (CIs, exhibiting the associated uncertainty. Then, this study suggested the drought outlook framework based on probabilistic drought forecasting results. The overall results provided sufficient agreement between the observed and forecasted drought conditions in the outlook framework.

  12. Neural Network-based Load Forecasting and Error Implication for Short-term Horizon

    NARCIS (Netherlands)

    Khuntia, S.R.; Rueda Torres, José L.; van der Meijden, M.A.M.M.

    2016-01-01

    Load forecasting is considered vital along with many other important entities required for assessing the reliability of power system. Thus, the primary concern is not to forecast load with a novel model, rather to forecast load with the highest accuracy. Short-term load forecast accuracy is often

  13. Sensor network based solar forecasting using a local vector autoregressive ridge framework

    Energy Technology Data Exchange (ETDEWEB)

    Xu, J. [Stony Brook Univ., NY (United States); Yoo, S. [Brookhaven National Lab. (BNL), Upton, NY (United States); Heiser, J. [Brookhaven National Lab. (BNL), Upton, NY (United States); Kalb, P. [Brookhaven National Lab. (BNL), Upton, NY (United States)

    2016-04-04

    The significant improvements and falling costs of photovoltaic (PV) technology make solar energy a promising resource, yet the cloud induced variability of surface solar irradiance inhibits its effective use in grid-tied PV generation. Short-term irradiance forecasting, especially on the minute scale, is critically important for grid system stability and auxiliary power source management. Compared to the trending sky imaging devices, irradiance sensors are inexpensive and easy to deploy but related forecasting methods have not been well researched. The prominent challenge of applying classic time series models on a network of irradiance sensors is to address their varying spatio-temporal correlations due to local changes in cloud conditions. We propose a local vector autoregressive framework with ridge regularization to forecast irradiance without explicitly determining the wind field or cloud movement. By using local training data, our learned forecast model is adaptive to local cloud conditions and by using regularization, we overcome the risk of overfitting from the limited training data. Our systematic experimental results showed an average of 19.7% RMSE and 20.2% MAE improvement over the benchmark Persistent Model for 1-5 minute forecasts on a comprehensive 25-day dataset.

  14. [Combined forecasting system of peritonitis outcome].

    Science.gov (United States)

    Lebedev, N V; Klimov, A E; Agrba, S B; Gaidukevich, E K

    To create a reliable system for assessing of severity and prediction of the outcome of peritonitis. Critical analysis of the systems for peritonitis severity assessment is presented. The study included outcomes of 347 patients who admitted at the Department of Faculty Surgery of Peoples' Friendship University of Russia in 2015-2016. The cause of peritonitis were destructive forms of acute appendicitis, cholecystitis, perforated gastroduodenal ulcer, various perforation of small and large intestines (including tumor). Combined forecasting system for peritonitis severity assessment is created. The system includes clinical, laboratory data, assessment of systemic inflammatory response (SIRS) and severity of organ failure (qSOFA). The authors focused on easily identifiable parameters which are available in virtually any surgical hospital. Threshold value (lethal outcome probability over 50%) is 8 scores in this system. Sensitivity, specificity and accuracy were 93.3, 99.7 and 98.9%, respectively according to ROC-curve that exceeds those parameters of MPI and APACHE II.

  15. Development and evaluation of an operational SDS forecasting system for East Asia: CUACE/DUST

    Science.gov (United States)

    Zhou, C. H.; Gong, S. L.; Zhang, X. Y.; Wang, Y. Q.; Niu, T.; Liu, H. L.; Zhao, T. L.; Yang, Y. Q.; Hou, Q.

    2007-06-01

    CUACE/Dust, an operational sand and dust storm (SDS) forecasting system for East Asia, was developed at CMA (China Meteorological Administration) by integrating a meso-scale dust aerosol model with a 3DVar data assimilation system that uses both surface network observation data and dust intensity data retrieved from the Chinese Geostationary Satellite FY-2C. For spring 2006, CUACE/Dust successfully forecasted most of the 31 SDS episodes in East Asia. A detailed comparison of the modeling predictions for the 8-12 March episode with surface network observations and lidar measurements revealed a robust forecasting ability of the system. The time series of the forecasted dust concentrations for a number of representative stations for the whole spring 2006 were also evaluated against surface PM10 monitoring data, showing a very good agreement in terms of the SDS timing and magnitudes near source regions where dust aerosols dominate. For the entire domain forecasts in spring 2006 (1 March-31 May), a TS (thread score) system evaluated the performance of the system against all available observations and rendered an averaged TS value of 0.31 for 24 h forecasts, 0.23 for 48 h and 0.21 for 72 h forecasts.

  16. Online Learning Algorithm for Time Series Forecasting Suitable for Low Cost Wireless Sensor Networks Nodes

    Directory of Open Access Journals (Sweden)

    Juan Pardo

    2015-04-01

    Full Text Available Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.

  17. Online learning algorithm for time series forecasting suitable for low cost wireless sensor networks nodes.

    Science.gov (United States)

    Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

    2015-04-21

    Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.

  18. The Red Sea Modeling and Forecasting System

    KAUST Repository

    Hoteit, Ibrahim

    2015-04-01

    Despite its importance for a variety of socio-economical and political reasons and the presence of extensive coral reef gardens along its shores, the Red Sea remains one of the most under-studied large marine physical and biological systems in the global ocean. This contribution will present our efforts to build advanced modeling and forecasting capabilities for the Red Sea, which is part of the newly established Saudi ARAMCO Marine Environmental Research Center at KAUST (SAMERCK). Our Red Sea modeling system compromises both regional and nested costal MIT general circulation models (MITgcm) with resolutions varying between 8 km and 250 m to simulate the general circulation and mesoscale dynamics at various spatial scales, a 10-km resolution Weather Research Forecasting (WRF) model to simulate the atmospheric conditions, a 4-km resolution European Regional Seas Ecosystem Model (ERSEM) to simulate the Red Sea ecosystem, and a 1-km resolution WAVEWATCH-III model to simulate the wind driven surface waves conditions. We have also implemented an oil spill model, and a probabilistic dispersion and larval connectivity modeling system (CMS) based on a stochastic Lagrangian framework and incorporating biological attributes. We are using the models outputs together with available observational data to study all aspects of the Red Sea circulations. Advanced monitoring capabilities are being deployed in the Red Sea as part of the SAMERCK, comprising multiple gliders equipped with hydrographical and biological sensors, high frequency (HF) surface current/wave mapping, buoys/ moorings, etc, complementing the available satellite ocean and atmospheric observations and Automatic Weather Stations (AWS). The Red Sea models have also been equipped with advanced data assimilation capabilities. Fully parallel ensemble-based Kalman filtering (EnKF) algorithms have been implemented with the MITgcm and ERSEM for assimilating all available multivariate satellite and in-situ data sets. We

  19. Investigating and forecasting coastal Adriatic surface currents by using neural networks (NEURAL)

    Science.gov (United States)

    Vilibic, Ivica; Zagar, Nedjeljka; Cosoli, Simone; Dadic, Vlado; Horvath, Kristian; Ivankovic, Damir; Jesenko, Blaz; Mihanovic, Hrvoje; Sepic, Jadranka; Tudor, Martina

    2014-05-01

    We present major components of the project NEURAL (www.izor.hr/neural) funded by the Unity Through Knowledge Fund (www.ukf.hr). The project aims to investigate and to build an efficient and reliable prototype of the ocean surface current forecasting system, based on high-frequency (HF) radar measurements, numerical weather prediction (NWP) model outputs and neural network algorithms (Self-Organising Maps). The Self-Organising Maps (SOM) method, a kind of neural network algorithms that performs a nonlinear smooth mapping of high-dimensional input data into the elements of a low-dimensional array, has previously been used on historical HF radar measurements and NWP Aladin/HR wind fields, which were operational in the northern Adriatic during 2008. It was found that the SOM surface currents patterns and associated SOM surface currents and winds patterns were highly correlated, indicating the predominance of the wind-driven forcing on the measured ocean currents. Therefore, a forecasting system has been proposed, that will use operational NWP products for the Adriatic region, then search for the closest SOM solutions in wind fields and finally to forecast ocean currents by using associated SOM patterns in HF radar currents. Such a prototype forecasting system will be tested on a long and quality-checked HF radar surface currents dataset available in the northern Adriatic, where the first part of the series will be used for the training of the SOM and the second part for assessing the skill performance of the surface currents hindcast. Two NWP systems will be used on the project: (1) high-resolution non-hydrostatic research WRF-ARW model based at the Faculty of Mathematics and Physics of the University of Ljubljana, and (2) operational Aladin/HR NWP system of the Meteorological and Hydrological Service of Croatia. The prototype forecasting system will be also tested in the middle Adriatic after the collection of substantially long high-quality surface currents dataset

  20. Load forecasting method considering temperature effect for distribution network

    Directory of Open Access Journals (Sweden)

    Meng Xiao Fang

    2016-01-01

    Full Text Available To improve the accuracy of load forecasting, the temperature factor was introduced into the load forecasting in this paper. This paper analyzed the characteristics of power load variation, and researched the rule of the load with the temperature change. Based on the linear regression analysis, the mathematical model of load forecasting was presented with considering the temperature effect, and the steps of load forecasting were given. Used MATLAB, the temperature regression coefficient was calculated. Using the load forecasting model, the full-day load forecasting and time-sharing load forecasting were carried out. By comparing and analyzing the forecast error, the results showed that the error of time-sharing load forecasting method was small in this paper. The forecasting method is an effective method to improve the accuracy of load forecasting.

  1. Incorporating Wind Power Forecast Uncertainties Into Stochastic Unit Commitment Using Neural Network-Based Prediction Intervals.

    Science.gov (United States)

    Quan, Hao; Srinivasan, Dipti; Khosravi, Abbas

    2015-09-01

    Penetration of renewable energy resources, such as wind and solar power, into power systems significantly increases the uncertainties on system operation, stability, and reliability in smart grids. In this paper, the nonparametric neural network-based prediction intervals (PIs) are implemented for forecast uncertainty quantification. Instead of a single level PI, wind power forecast uncertainties are represented in a list of PIs. These PIs are then decomposed into quantiles of wind power. A new scenario generation method is proposed to handle wind power forecast uncertainties. For each hour, an empirical cumulative distribution function (ECDF) is fitted to these quantile points. The Monte Carlo simulation method is used to generate scenarios from the ECDF. Then the wind power scenarios are incorporated into a stochastic security-constrained unit commitment (SCUC) model. The heuristic genetic algorithm is utilized to solve the stochastic SCUC problem. Five deterministic and four stochastic case studies incorporated with interval forecasts of wind power are implemented. The results of these cases are presented and discussed together. Generation costs, and the scheduled and real-time economic dispatch reserves of different unit commitment strategies are compared. The experimental results show that the stochastic model is more robust than deterministic ones and, thus, decreases the risk in system operations of smart grids.

  2. Neural networks forecast in small catchments with transfer of network parameters

    Science.gov (United States)

    Maca, P.; Havlicek, V.; Hermanovsky, M.; Horacek, S.; Pech, P.

    2009-04-01

    This contribution deals with neural network approach for short term forecast on small catchments. The applied methodology is based on theory of multilayer perceptron (MLP), feed forward neural network with back propagation optimization procedure was tested in order to explore the possibilities to transfer parameters between different catchments. Supervised optimization of network parameters and structure was investigated. A software tool was created for these research and operative purposes. The hourly discharges and rainfall data of real flood events served as an input to MLP. Seven catchments with areas, which range from 10 to 250 square kilometres and which are situated in the east part of the Czech Republic, were selected. The input data were normalized by parametric method. Variable configuration of neural network was tested in number of modes represented by different combination of learning and testing data sets. The analysis focuses on ability of the model to forecast the flood event with different peak discharge magnitudes. This should be achieved in both application steps - MLP learning and testing within given catchment and in step of parameter transfer of well learned network to another catchment. The length of prediction ranged from one hour to six hours ahead. The results showed that the model is capable to provide satisfying short term discharge forecast for the most of studied cases, including successful parameter transfer among different catchments. This was accomplished by using optimization of parameters which determine not only the structure and behaviour of applied network but also the transformation of input data.

  3. Forecasting macroeconomic variables using neural network models and three automated model selection techniques

    DEFF Research Database (Denmark)

    Kock, Anders Bredahl; Teräsvirta, Timo

    2016-01-01

    When forecasting with neural network models one faces several problems, all of which influence the accuracy of the forecasts. First, neural networks are often hard to estimate due to their highly nonlinear structure. To alleviate the problem, White (2006) presented a solution (QuickNet...

  4. A production throughput forecasting system in an automated hard disk drive test operation using GRNN

    Energy Technology Data Exchange (ETDEWEB)

    Samattapapong, N.; Afzulpurkar, N.

    2016-07-01

    The goal of this paper is to develop a pragmatic system of a production throughput forecasting system for an automated test operation in a hard drive manufacturing plant. The accurate forecasting result is necessary for the management team to response to any changes in the production processes and the resources allocations. In this study, we design a production throughput forecasting system in an automated test operation in hard drive manufacturing plant. In the proposed system, consists of three main stages. In the first stage, a mutual information method was adopted for selecting the relevant inputs into the forecasting model. In the second stage, a generalized regression neural network (GRNN) was implemented in the forecasting model development phase. Finally, forecasting accuracy was improved by searching the optimal smoothing parameter which selected from comparisons result among three optimization algorithms: particle swarm optimization (PSO), unrestricted search optimization (USO) and interval halving optimization (IHO). The experimental result shows that (1) the developed production throughput forecasting system using GRNN is able to provide forecasted results close to actual values, and to projected the future trends of production throughput in an automated hard disk drive test operation; (2) An IHO algorithm performed as superiority appropriate optimization method than the other two algorithms. (3) Compared with current forecasting system in manufacturing, the results show that the proposed system’s performance is superior to the current system in prediction accuracy and suitable for real-world application. The production throughput volume is a key performance index of hard disk drive manufacturing systems that need to be forecast. Because of the production throughput forecasting result is useful information for management team to respond to any changing in production processes and resources allocation. However, a practically forecasting system for

  5. Multitask Learning-Based Security Event Forecast Methods for Wireless Sensor Networks

    Directory of Open Access Journals (Sweden)

    Hui He

    2016-01-01

    Full Text Available Wireless sensor networks have strong dynamics and uncertainty, including network topological changes, node disappearance or addition, and facing various threats. First, to strengthen the detection adaptability of wireless sensor networks to various security attacks, a region similarity multitask-based security event forecast method for wireless sensor networks is proposed. This method performs topology partitioning on a large-scale sensor network and calculates the similarity degree among regional subnetworks. The trend of unknown network security events can be predicted through multitask learning of the occurrence and transmission characteristics of known network security events. Second, in case of lacking regional data, the quantitative trend of unknown regional network security events can be calculated. This study introduces a sensor network security event forecast method named Prediction Network Security Incomplete Unmarked Data (PNSIUD method to forecast missing attack data in the target region according to the known partial data in similar regions. Experimental results indicate that for an unknown security event forecast the forecast accuracy and effects of the similarity forecast algorithm are better than those of single-task learning method. At the same time, the forecast accuracy of the PNSIUD method is better than that of the traditional support vector machine method.

  6. Evaluation of Air Force and Navy Demand Forecasting Systems

    Science.gov (United States)

    1994-01-01

    FORECASTING SYSTEMS THESIS Presented to the Faculty of the Graduate School of Logistics and Acquisition Management of the Air Force Institute of...compute the forecasting error measurements (MAD, , vAPE & MPE) to evaluate the accuracy and the stability of the Air Force RDB Forecasting system. The RDB...Institute, March 1993. Bond, A. Craig and Marvin E. Ruth. A Conceptual Model of the Air Force Logistics Picline. MS thesis, AFIT/GLM/LSM/89S-2. School

  7. Error analysis for Winters' Additive Seasonal Forecasting System

    OpenAIRE

    McKenzie, Edward

    1984-01-01

    A procedure for deriving the variance of the forecast error for Winters' Additive Seasonal Forecasting system is given. Both point and cumulative T-step ahead forecasts are dealt with. Closed form expressions are given in the cases when the model is (i) trend-free and (ii) non-seasonal. The effects of renormal ization of the seasonal factors is also discussed. The fact that the error variance for this system can be infinite is discussed and the relationship of this property ...

  8. Nivmar: a storm surge forecasting system for Spanish waters

    Directory of Open Access Journals (Sweden)

    Enrique Álvarez Fanjul

    2001-07-01

    Full Text Available In this paper, a storm surge prediction system for the Spanish Waters is presented. The system, named Nivmar, is based on the ocean circulation Hamsom model and on the harmonical prediction of tides computed from data measured by the tide gauge network Redmar, managed by Puertos del Estado. Nivmar is executed twice a day, running Hamsom forced by meteorological fields derived from the INM (Instituto Nacional de Meteorología operational application of Hirlam atmospheric model. Data from Redmar tide gauges is used to to forecast the tidal elevations, to validate the system and to perform data assimilation, correcting systematic errors in the mean sea level due to physicals processes that are not included in the ocean model (i. e. steric height. The forecast horizon is 48 hours. In order to validate the system with measured data from Redmar a very stormy 5 months period was selected. Results from this test (November 95 to March 96 are presented. Data from this experiment shown that Nivmar is able to correctly predict sea level in the region. A simple data assimilation scheme for sea level is described and results from its application are studied. Finally, special focus is made in future plans and potential developments and applications of the system.

  9. Skill of a global seasonal ensemble streamflow forecasting system

    Science.gov (United States)

    Candogan Yossef, Naze; Winsemius, Hessel; Weerts, Albrecht; van Beek, Rens; Bierkens, Marc

    2013-04-01

    Forecasting of water availability and scarcity is a prerequisite for managing the risks and opportunities caused by the inter-annual variability of streamflow. Reliable seasonal streamflow forecasts are necessary to prepare for an appropriate response in disaster relief, management of hydropower reservoirs, water supply, agriculture and navigation. Seasonal hydrological forecasting on a global scale could be valuable especially for developing regions of the world, where effective hydrological forecasting systems are scarce. In this study, we investigate the forecasting skill of the global seasonal streamflow forecasting system FEWS-World, using the global hydrological model PCR-GLOBWB. FEWS-World has been setup within the European Commission 7th Framework Programme project Global Water Scarcity Information Service (GLOWASIS). Skill is assessed in historical simulation mode as well as retroactive forecasting mode. The assessment in historical simulation mode used a meteorological forcing based on observations from the Climate Research Unit of the University of East Anglia and the ERA-40 reanalysis of the European Center for Medium-Range Weather Forecasts (ECMWF). We assessed the skill of the global hydrological model PCR-GLOBWB in reproducing past discharge extremes in 20 large rivers of the world. This preliminary assessment concluded that the prospects for seasonal forecasting with PCR-GLOBWB or comparable models are positive. However this assessment did not include actual meteorological forecasts. Thus the meteorological forcing errors were not assessed. Yet, in a forecasting setup, the predictive skill of a hydrological forecasting system is affected by errors due to uncertainty from numerical weather prediction models. For the assessment in retroactive forecasting mode, the model is forced with actual ensemble forecasts from the seasonal forecast archives of ECMWF. Skill is assessed at 78 stations on large river basins across the globe, for all the months of

  10. The GOCF/AWAP system - forecasting temperature extremes

    Energy Technology Data Exchange (ETDEWEB)

    Fawcett, Robert [National Climate Centre, Australian Bureau of Meteorology, Docklands, Victoria 3008 (Australia); Hume, Timothy, E-mail: r.fawcett@bom.gov.a, E-mail: t.hume@bom.gov.a [Centre for Australian Weather and Climate Research, Australian Bureau of Meteorology, Docklands, Victoria 3008 (Australia)

    2010-08-15

    Gridded hourly temperature forecasts from the Bureau of Meteorology's Gridded Operational Consensus Forecasting (GOCF) system are combined in real time with the Australian Water Availability Project (AWAP) gridded daily temperature analyses to produce gridded daily maximum and minimum temperature forecasts with lead times from one to five days. These forecasts are compared against the historical record of AWAP daily temperature analyses (1911 to present), to identify regions where record or near-record temperatures are predicted to occur. This paper describes the GOCF/AWAP system, showing how the daily maximum and minimum temperature forecasts are prepared from the hourly forecasts, and how they are bias-corrected in real time using the AWAP analyses, against which they are subsequently verified. Using monthly climatologies of long-term daily mean, standard deviation and all-time highest and lowest on record, derived forecast products (for both maximum and minimum temperature) include ordinary and standardised anomalies, 'forecast - highest on record' and 'forecast - lowest on record'. Compensation for the climatological variation across the country is achieved in these last two products, which provide the necessary guidance as to whether or not record-breaking temperatures are expected, by expressing the forecast departure from the previous record in both {sup 0}C and standard deviations.

  11. Multiplexed FBG Monitoring System for Forecasting Coalmine Water Inrush Disaster

    Directory of Open Access Journals (Sweden)

    B. Liu

    2012-01-01

    Full Text Available This paper presents a novel fiber-Bragg-grating- (FBG- based system which can monitor and analyze multiple parameters such as temperature, strain, displacement, and seepage pressure simultaneously for forecasting coalmine water inrush disaster. The sensors have minimum perturbation on the strain field. And the seepage pressure sensors adopt a drawbar structure and employ a corrugated diaphragm to transmit seepage pressure to the axial strain of FBG. The pressure sensitivity is 20.20 pm/KPa, which is 6E3 times higher than that of ordinary bare FBG. The FBG sensors are all preembedded on the roof of mining area in coalmine water inrush model test. Then FBG sensing network is set up applying wavelength-division multiplexing (WDM technology. The experiment is carried out by twelve steps, while the system acquires temperature, strain, displacement, and seepage pressure signals in real time. The results show that strain, displacement, and seepage pressure monitored by the system change significantly before water inrush occurs, and the strain changes firstly. Through signal fusion analyzed it can be concluded that the system provides a novel way to forecast water inrush disaster successfully.

  12. Forecasting Macroeconomic Variables using Neural Network Models and Three Automated Model Selection Techniques

    DEFF Research Database (Denmark)

    Kock, Anders Bredahl; Teräsvirta, Timo

    In this paper we consider the forecasting performance of a well-defined class of flexible models, the so-called single hidden-layer feedforward neural network models. A major aim of our study is to find out whether they, due to their flexibility, are as useful tools in economic forecasting as some...... previous studies have indicated. When forecasting with neural network models one faces several problems, all of which influence the accuracy of the forecasts. First, neural networks are often hard to estimate due to their highly nonlinear structure. In fact, their parameters are not even globally...... on the linearisation idea: the Marginal Bridge Estimator and Autometrics. Second, one must decide whether forecasting should be carried out recursively or directly. Comparisons of these two methodss exist for linear models and here these comparisons are extended to neural networks. Finally, a nonlinear model...

  13. Forecasting the Performance of Agroforestry Systems

    Science.gov (United States)

    Luedeling, E.; Shepherd, K.

    2014-12-01

    Agroforestry has received considerable attention from scientists and development practitioners in recent years. It is recognized as a cornerstone of many traditional agricultural systems, as well as a new option for sustainable land management in currently treeless agricultural landscapes. Agroforestry systems are diverse, but most manifestations supply substantial ecosystem services, including marketable tree products, soil fertility, water cycle regulation, wildlife habitat and carbon sequestration. While these benefits have been well documented for many existing systems, projecting the outcomes of introducing new agroforestry systems, or forecasting system performance under changing environmental or climatic conditions, remains a substantial challenge. Due to the various interactions between system components, the multiple benefits produced by trees and crops, and the host of environmental, socioeconomic and cultural factors that shape agroforestry systems, mechanistic models of such systems quickly become very complex. They then require a lot of data for site-specific calibration, which presents a challenge for their use in new environmental and climatic domains, especially in data-scarce environments. For supporting decisions on the scaling up of agroforestry technologies, new projection methods are needed that can capture system complexity to an adequate degree, while taking full account of the fact that data on many system variables will virtually always be highly uncertain. This paper explores what projection methods are needed for supplying decision-makers with useful information on the performance of agroforestry in new places or new climates. Existing methods are discussed in light of these methodological needs. Finally, a participatory approach to performance projection is proposed that captures system dynamics in a holistic manner and makes probabilistic projections about expected system performance. This approach avoids the temptation to take

  14. DMI's Baltic Sea Coastal operational forecasting system

    Science.gov (United States)

    Murawski, Jens; Berg, Per; Weismann Poulsen, Jacob

    2017-04-01

    Operational forecasting is challenged with bridging the gap between the large scales of the driving weather systems and the local, human scales of the model applications. The limit of what can be represented by local model has been continuously shifted to higher and higher spatial resolution, with the aim to better resolve the local dynamic and to make it possible to describe processes that could only be parameterised in older versions, with the ultimate goal to improve the quality of the forecast. Current hardware trends demand a str onger focus on the development of efficient, highly parallelised software and require a refactoring of the code with a solid focus on portable performance. The gained performance can be used for running high resolution model with a larger coverage. Together with the development of efficient two-way nesting routines, this has made it possible to approach the near-coastal zone with model applications that can run in a time effective way. Denmarks Meteorological Institute uses the HBM(1) ocean circulation model for applications that covers the entire Baltic Sea and North Sea with an integrated model set-up that spans the range of horizontal resolution from 1nm for the entire Baltic Sea to approx. 200m resolution in local fjords (Limfjord). For the next model generation, the high resolution set-ups are going to be extended and new high resolution domains in coastal zones are either implemented or tested for operational use. For the first time it will be possible to cover large stretches of the Baltic coastal zone with sufficiently high resolution to model the local hydrodynamic adequately. (1) HBM stands for HIROMB-BOOS-Model, whereas HIROMB stands for "High Resolution Model for the Baltic Sea" and BOOS stands for "Baltic Operational Oceanography System".

  15. A review of effective flood forecasting, warning and response system ...

    African Journals Online (AJOL)

    drinie

    2002-04-02

    Apr 2, 2002 ... A review of effective flood forecasting, warning and response system for application in ... is to discuss one aspect covered by a holistic integrated catchment management approach, namely a flood forecast, warning and response system, which .... structural measure”. In Europe an FFWRS is implemented to.

  16. Hybrid Predictive Models for Accurate Forecasting in PV Systems

    Directory of Open Access Journals (Sweden)

    Marco Mussetta

    2013-04-01

    Full Text Available The accurate forecasting of energy production from renewable sources represents an important topic also looking at different national authorities that are starting to stimulate a greater responsibility towards plants using non-programmable renewables. In this paper the authors use advanced hybrid evolutionary techniques of computational intelligence applied to photovoltaic systems forecasting, analyzing the predictions obtained by comparing different definitions of the forecasting error.

  17. Value assessment of a global hydrological forecasting system

    Science.gov (United States)

    Candogan Yossef, N.; Winsemius, H.; van Beek, L. P. H.; van Beek, E.; Bierkens, M. F. P.

    2012-04-01

    The inter-annual variability in streamflow presents risks and opportunities in the management of water resources systems. Reliable hydrological forecasts, effective communication and proper response allow several sectors to make more informed management decisions. In many developing regions of the world, there are no efficient hydrological forecasting systems. A global forecasting system which indicates increased probabilities of streamflow excesses or shortages over long lead-times can be of great value for these regions. FEWS-World system is developed for this purpose. It is based on the Delft-FEWS (flood early warning system) developed by Deltares and incorporates the global hydrological model PCR-GLOBWB. This study investigates the skill and value of FEWS-World. Skill is defined as the ability of the system to forecast discharge extremes; and value as its usefulness for possible users and ultimately for affected populations. Skill is assessed in historical simulation mode as well as retroactive forecasting mode. For the assessment in historical simulation mode a meteorological forcing based on observations from the Climate Research Unit of the University of East Anglia and the ERA-40 reanalysis of the European Center for Medium-Range Weather Forecasts (ECMWF) was used. For the assessment in retroactive forecasting mode the model was forced with ensemble forecasts from the seasonal forecast archives of ECMWF. The eventual goal is to transfer FEWS-World to operational forecasting mode, where the system will use operational seasonal forecasts from ECMWF. The results will be disseminated on the internet, and hopefully provide information that is valuable for users in data and model-poor regions of the world. The results of the preliminary assessment show that although forecasting skill decreases with increasing lead time, the value of forecasts does not necessarily decrease. The forecast requirements and response options of several water related sectors was

  18. Impact of a high density GPS network on the operational forecast

    Directory of Open Access Journals (Sweden)

    C. Faccani

    2005-01-01

    Full Text Available Global Positioning System Zenith Total Delay (GPS ZTD can provide information about the water vapour in atmosphere. Its assimilation into the analysis used to initialize a model can then improve the weather forecast, giving the right amount of moisture and reducing the model spinup. In the last year, an high density GPS network has been created on the Basilicata region (south of Italy by the Italian Space Agency in the framework of a national project named MAGIC2. MAGIC2 is the Italian follow on of the EC project MAGIC has. Daily operational data assimilation experiments are performed since December 2003. The results show that the assimilation of GPS ZTD improves the forecast especially during the transition from winter to spring even if a no very high model resolution (9km is used.

  19. Hybrid Power Forecasting Model for Photovoltaic Plants Based on Neural Network with Air Quality Index

    Directory of Open Access Journals (Sweden)

    Idris Khan

    2017-01-01

    Full Text Available High concentration of greenhouse gases in the atmosphere has increased dependency on photovoltaic (PV power, but its random nature poses a challenge for system operators to precisely predict and forecast PV power. The conventional forecasting methods were accurate for clean weather. But when the PV plants worked under heavy haze, the radiation is negatively impacted and thus reducing PV power; therefore, to deal with haze weather, Air Quality Index (AQI is introduced as a parameter to predict PV power. AQI, which is an indication of how polluted the air is, has been known to have a strong correlation with power generated by the PV panels. In this paper, a hybrid method based on the model of conventional back propagation (BP neural network for clear weather and BP AQI model for haze weather is used to forecast PV power with conventional parameters like temperature, wind speed, humidity, solar radiation, and an extra parameter of AQI as input. The results show that the proposed method has less error under haze condition as compared to conventional model of neural network.

  20. Assessment of an ensemble seasonal streamflow forecasting system for Australia

    Science.gov (United States)

    Bennett, James C.; Wang, Quan J.; Robertson, David E.; Schepen, Andrew; Li, Ming; Michael, Kelvin

    2017-11-01

    Despite an increasing availability of skilful long-range streamflow forecasts, many water agencies still rely on simple resampled historical inflow sequences (stochastic scenarios) to plan operations over the coming year. We assess a recently developed forecasting system called forecast guided stochastic scenarios (FoGSS) as a skilful alternative to standard stochastic scenarios for the Australian continent. FoGSS uses climate forecasts from a coupled ocean-land-atmosphere prediction system, post-processed with the method of calibration, bridging and merging. Ensemble rainfall forecasts force a monthly rainfall-runoff model, while a staged hydrological error model quantifies and propagates hydrological forecast uncertainty through forecast lead times. FoGSS is able to generate ensemble streamflow forecasts in the form of monthly time series to a 12-month forecast horizon. FoGSS is tested on 63 Australian catchments that cover a wide range of climates, including 21 ephemeral rivers. In all perennial and many ephemeral catchments, FoGSS provides an effective alternative to resampled historical inflow sequences. FoGSS generally produces skilful forecasts at shorter lead times ( < 4 months), and transits to climatology-like forecasts at longer lead times. Forecasts are generally reliable and unbiased. However, FoGSS does not perform well in very dry catchments (catchments that experience zero flows more than half the time in some months), sometimes producing strongly negative forecast skill and poor reliability. We attempt to improve forecasts through the use of (i) ESP rainfall forcings, (ii) different rainfall-runoff models, and (iii) a Bayesian prior to encourage the error model to return climatology forecasts in months when the rainfall-runoff model performs poorly. Of these, the use of the prior offers the clearest benefit in very dry catchments, where it moderates strongly negative forecast skill and reduces bias in some instances. However, the prior does not

  1. Forecasting financial asset processes: stochastic dynamics via learning neural networks.

    Science.gov (United States)

    Giebel, S; Rainer, M

    2010-01-01

    Models for financial asset dynamics usually take into account their inherent unpredictable nature by including a suitable stochastic component into their process. Unknown (forward) values of financial assets (at a given time in the future) are usually estimated as expectations of the stochastic asset under a suitable risk-neutral measure. This estimation requires the stochastic model to be calibrated to some history of sufficient length in the past. Apart from inherent limitations, due to the stochastic nature of the process, the predictive power is also limited by the simplifying assumptions of the common calibration methods, such as maximum likelihood estimation and regression methods, performed often without weights on the historic time series, or with static weights only. Here we propose a novel method of "intelligent" calibration, using learning neural networks in order to dynamically adapt the parameters of the stochastic model. Hence we have a stochastic process with time dependent parameters, the dynamics of the parameters being themselves learned continuously by a neural network. The back propagation in training the previous weights is limited to a certain memory length (in the examples we consider 10 previous business days), which is similar to the maximal time lag of autoregressive processes. We demonstrate the learning efficiency of the new algorithm by tracking the next-day forecasts for the EURTRY and EUR-HUF exchange rates each.

  2. Assimilation scheme of the Mediterranean Forecasting System: operational implementation

    Directory of Open Access Journals (Sweden)

    E. Demirov

    2003-01-01

    Full Text Available This paper describes the operational implementation of the data assimilation scheme for the Mediterranean Forecasting System Pilot Project (MFSPP. The assimilation scheme, System for Ocean Forecast and Analysis (SOFA, is a reduced order Optimal Interpolation (OI scheme. The order reduction is achieved by projection of the state vector into vertical Empirical Orthogonal Functions (EOF. The data assimilated are Sea Level Anomaly (SLA and temperature profiles from Expandable Bathy Termographs (XBT. The data collection, quality control, assimilation and forecast procedures are all done in Near Real Time (NRT. The OI is used intermittently with an assimilation cycle of one week so that an analysis is produced once a week. The forecast is then done for ten days following the analysis day. The root mean square (RMS between the model forecast and the analysis (the forecast RMS is below 0.7°C in the surface layers and below 0.2°C in the layers deeper than 200 m for all the ten forecast days. The RMS between forecast and initial condition (persistence RMS is higher than forecast RMS after the first day. This means that the model improves forecast with respect to persistence. The calculation of the misfit between the forecast and the satellite data suggests that the model solution represents well the main space and time variability of the SLA except for a relatively short period of three – four weeks during the summer when the data show a fast transition between the cyclonic winter and anti-cyclonic summer regimes. This occurs in the surface layers that are not corrected by our assimilation scheme hypothesis. On the basis of the forecast skill scores analysis, conclusions are drawn about future improvements. Key words. Oceanography; general (marginal and semi-enclosed seas; numerical modeling; ocean prediction

  3. Assimilation scheme of the Mediterranean Forecasting System: operational implementation

    Directory of Open Access Journals (Sweden)

    E. Demirov

    Full Text Available This paper describes the operational implementation of the data assimilation scheme for the Mediterranean Forecasting System Pilot Project (MFSPP. The assimilation scheme, System for Ocean Forecast and Analysis (SOFA, is a reduced order Optimal Interpolation (OI scheme. The order reduction is achieved by projection of the state vector into vertical Empirical Orthogonal Functions (EOF. The data assimilated are Sea Level Anomaly (SLA and temperature profiles from Expandable Bathy Termographs (XBT. The data collection, quality control, assimilation and forecast procedures are all done in Near Real Time (NRT. The OI is used intermittently with an assimilation cycle of one week so that an analysis is produced once a week. The forecast is then done for ten days following the analysis day. The root mean square (RMS between the model forecast and the analysis (the forecast RMS is below 0.7°C in the surface layers and below 0.2°C in the layers deeper than 200 m for all the ten forecast days. The RMS between forecast and initial condition (persistence RMS is higher than forecast RMS after the first day. This means that the model improves forecast with respect to persistence. The calculation of the misfit between the forecast and the satellite data suggests that the model solution represents well the main space and time variability of the SLA except for a relatively short period of three – four weeks during the summer when the data show a fast transition between the cyclonic winter and anti-cyclonic summer regimes. This occurs in the surface layers that are not corrected by our assimilation scheme hypothesis. On the basis of the forecast skill scores analysis, conclusions are drawn about future improvements.

    Key words. Oceanography; general (marginal and semi-enclosed seas; numerical modeling; ocean prediction

  4. Verification of a probabilistic flood forecasting system for an Alpine Region of northern Italy

    Science.gov (United States)

    Laiolo, P.; Gabellani, S.; Rebora, N.; Rudari, R.; Ferraris, L.; Ratto, S.; Stevenin, H.

    2012-04-01

    Probabilistic hydrometeorological forecasting chains are increasingly becoming an operational tool used by civil protection centres for issuing flood alerts. One of the most important requests of decision makers is to have reliable systems, for this reason an accurate verification of their predictive performances become essential. The aim of this work is to validate a probabilistic flood forecasting system: Flood-PROOFS. The system works in real time, since 2008, in an alpine Region of northern Italy, Valle d'Aosta. It is used by the Civil Protection regional service to issue warnings and by the local water company to protect its facilities. Flood-PROOFS uses as input Quantitative Precipitation Forecast (QPF) derived from the Italian limited area model meteorological forecast (COSMO-I7) and forecasts issued by regional expert meteorologists. Furthermore the system manages and uses both real time meteorological and satellite data and real time data on the maneuvers performed by the water company on dams and river devices. The main outputs produced by the computational chain are deterministic and probabilistic discharge forecasts in different cross sections of the considered river network. The validation of the flood prediction system has been conducted on a 25 months period considering different statistical methods such as Brier score, Rank histograms and verification scores. The results highlight good performances of the system as support system for emitting warnings but there is a lack of statistics especially for huge discharge events.

  5. Forecasting of Market Clearing Price by Using GA Based Neural Network

    Science.gov (United States)

    Yang, Bo; Chen, Yun-Ping; Zhao, Zun-Lian; Han, Qi-Ye

    Forecasting of Market Clearing Price (MCP) is important to economic benefits of electricity market participants. To accurately forecast MCP, a novel two-stage GA-based neural network model (GA-NN) is proposed. In the first stage, GA chromosome is designed into two parts: boolean coding part for neural network topology and real coding part for connection weights. By hybrid genetic operation of selection, crossover and mutation under the criterion of error minimization between the actual output and the desired output, optimal architecture of neural network is obtained. In the second stage, gradient learning algorithm with momentum rate is imposed on neural network with optimal architecture. After learning process, optimal connection weights are obtained. The proposed model is tested on MCP forecasting in California electricity market. The test results show that GA-NN has self-adaptive ability in its topology and connection weights and can obtain more accurate MCP forecasting values than BP neural network.

  6. Artificial Neural Network Models for Long Lead Streamflow Forecasts using Climate Information

    Science.gov (United States)

    Kumar, J.; Devineni, N.

    2007-12-01

    Information on season ahead stream flow forecasts is very beneficial for the operation and management of water supply systems. Daily streamflow conditions at any particular reservoir primarily depend on atmospheric and land surface conditions including the soil moisture and snow pack. On the other hand recent studies suggest that developing long lead streamflow forecasts (3 months ahead) typically depends on exogenous climatic conditions particularly Sea Surface Temperature conditions (SST) in the tropical oceans. Examples of some oceanic variables are El Nino Southern Oscillation (ENSO) and Pacific Decadal Oscillation (PDO). Identification of such conditions that influence the moisture transport into a given basin poses many challenges given the nonlinear dependency between the predictors (SST) and predictand (stream flows). In this study, we apply both linear and nonlinear dependency measures to identify the predictors that influence the winter flows into the Neuse basin. The predictor identification approach here adopted uses simple correlation coefficients to spearman rank correlation measures for detecting nonlinear dependency. All these dependency measures are employed with a lag 3 time series of the high flow season (January - February - March) using 75 years (1928-2002) of stream flows recorded in to the Falls Lake, Neuse River Basin. Developing streamflow forecasts contingent on these exogenous predictors will play an important role towards improved water supply planning and management. Recently, the soft computing techniques, such as artificial neural networks (ANNs) have provided an alternative method to solve complex problems efficiently. ANNs are data driven models which trains on the examples given to it. The ANNs functions as universal approximators and are non linear in nature. This paper presents a study aiming towards using climatic predictors for 3 month lead time streamflow forecast. ANN models representing the physical process of the system are

  7. Climate Forecast System Reforecast (CFSR), for 1981 to 2011

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The NCEP Climate Forecast System Reanalysis (CFSR) was designed and executed as a global, high resolution, coupled atmosphere-ocean-land surface-sea ice system to...

  8. Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.

    Science.gov (United States)

    Waheeb, Waddah; Ghazali, Rozaida; Herawan, Tutut

    2016-01-01

    Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

  9. Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.

    Directory of Open Access Journals (Sweden)

    Waddah Waheeb

    Full Text Available Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN and the Dynamic Ridge Polynomial Neural Network (DRPNN. Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

  10. Unmanned Aircraft Systems Demand Forecast Study

    Science.gov (United States)

    Hackenberg, Davis L.

    2017-01-01

    UAS demand slides discuss the purpose, scope, and assumptions of the UAS Demand Forecast Study. It discusses some operational environments and market research study, this information is broad knowledge in the UAS community.

  11. Operational air quality forecasting system for Spain: CALIOPE

    Science.gov (United States)

    Baldasano, J. M.; Piot, M.; Jorba, O.; Goncalves, M.; Pay, M.; Pirez, C.; Lopez, E.; Gasso, S.; Martin, F.; García-Vivanco, M.; Palomino, I.; Querol, X.; Pandolfi, M.; Dieguez, J. J.; Padilla, L.

    2009-12-01

    The European Commission (EC) and the United States Environmental Protection Agency (US-EPA) have shown great concerns to understand the transport and dynamics of pollutants in the atmosphere. According to the European directives (1996/62/EC, 2002/3/EC, 2008/50/EC), air quality modeling, if accurately applied, is a useful tool to understand the dynamics of air pollutants, to analyze and forecast the air quality, and to develop programs reducing emissions and alert the population when health-related issues occur. The CALIOPE project, funded by the Spanish Ministry of the Environment, has the main objective to establish an air quality forecasting system for Spain. A partnership of four research institutions composes the CALIOPE project: the Barcelona Supercomputing Center (BSC), the center of investigation CIEMAT, the Earth Sciences Institute ‘Jaume Almera’ (IJA-CSIC) and the CEAM Foundation. CALIOPE will become the official Spanish air quality operational system. This contribution focuses on the recent developments and implementation of the integrated modelling system for the Iberian Peninsula (IP) and Canary Islands (CI) with a high spatial and temporal resolution (4x4 sq. km for IP and 2x2 sq. km for CI, 1 hour), namely WRF-ARW/HERMES04/CMAQ/BSC-DREAM. The HERMES04 emission model has been specifically developed as a high-resolution (1x1 sq. km, 1 hour) emission model for Spain. It includes biogenic and anthropogenic emissions such as on-road and paved-road resuspension production, power plant generation, ship and plane traffic, airports and ports activities, industrial and agricultural sectors as well as domestic and commercial emissions. The qualitative and quantitative evaluation of the model was performed for a reference year (2004) using data from ground-based measurement networks. The products of the CALIOPE system will provide 24h and 48h forecasts for O3, NO2, SO2, CO, PM10 and PM2.5 at surface level. An operational evaluation system has been developed

  12. Artificial Neural Network versus Linear Models Forecasting Doha Stock Market

    Science.gov (United States)

    Yousif, Adil; Elfaki, Faiz

    2017-12-01

    The purpose of this study is to determine the instability of Doha stock market and develop forecasting models. Linear time series models are used and compared with a nonlinear Artificial Neural Network (ANN) namely Multilayer Perceptron (MLP) Technique. It aims to establish the best useful model based on daily and monthly data which are collected from Qatar exchange for the period starting from January 2007 to January 2015. Proposed models are for the general index of Qatar stock exchange and also for the usages in other several sectors. With the help of these models, Doha stock market index and other various sectors were predicted. The study was conducted by using various time series techniques to study and analyze data trend in producing appropriate results. After applying several models, such as: Quadratic trend model, double exponential smoothing model, and ARIMA, it was concluded that ARIMA (2,2) was the most suitable linear model for the daily general index. However, ANN model was found to be more accurate than time series models.

  13. CUACE/Dust - an integrated system of observation and modeling systems for operational dust forecasting in Asia

    Science.gov (United States)

    Gong, S. L.; Zhang, X. Y.

    2008-05-01

    An integrated sand and dust storm (SDS) forecasting system - CUACE/Dust (Chinese Unified Atmospheric Chemistry Environment for Dust) has been developed, which consists of a comprehensive dust aerosol module with emission, dry/wet depositions and other atmospheric dynamic processes, and a data assimilation system (DAS) using observational data from the CMA (China Meteorological Administration) ground dust monitoring network and retrieved dust information from a Chinese geostationary satellite - FY-2C. This is the first time that a combination of surface network observations and satellite retrievals of the dust aerosol has been successfully used in the real time operational forecasts in East Asia through a DAS. During its application for the operational SDS forecasts in East Asia for spring 2006, this system captured the major 31 SDS episodes observed by both surface and satellite observations. Analysis shows that the seasonal mean threat score (TS) for 0-24 h forecast over the East Asia in spring 2006 increased from 0.22 to 0.31 by using the DAS, a 41% enhancement. The time series of the forecasted dust concentrations for a number of representative stations for the whole spring 2006 were also evaluated against the surface PM10 monitoring data, showing a very good agreement in terms of the SDS timing and magnitudes near source regions where dust aerosols dominate. This is a summary paper for a special issue of ACP featuring the development and results of the forecasting system.

  14. An artificial neural network model for rainfall forecasting in Bangkok, Thailand

    Directory of Open Access Journals (Sweden)

    N. Q. Hung

    2009-08-01

    Full Text Available This paper presents a new approach using an Artificial Neural Network technique to improve rainfall forecast performance. A real world case study was set up in Bangkok; 4 years of hourly data from 75 rain gauge stations in the area were used to develop the ANN model. The developed ANN model is being applied for real time rainfall forecasting and flood management in Bangkok, Thailand. Aimed at providing forecasts in a near real time schedule, different network types were tested with different kinds of input information. Preliminary tests showed that a generalized feedforward ANN model using hyperbolic tangent transfer function achieved the best generalization of rainfall. Especially, the use of a combination of meteorological parameters (relative humidity, air pressure, wet bulb temperature and cloudiness, the rainfall at the point of forecasting and rainfall at the surrounding stations, as an input data, advanced ANN model to apply with continuous data containing rainy and non-rainy period, allowed model to issue forecast at any moment. Additionally, forecasts by ANN model were compared to the convenient approach namely simple persistent method. Results show that ANN forecasts have superiority over the ones obtained by the persistent model. Rainfall forecasts for Bangkok from 1 to 3 h ahead were highly satisfactory. Sensitivity analysis indicated that the most important input parameter besides rainfall itself is the wet bulb temperature in forecasting rainfall.

  15. Electricity market price forecasting by grid computing optimizing artificial neural networks

    OpenAIRE

    Niimura, T.; Ozawa, K.; Sakamoto, N.

    2007-01-01

    This paper presents a grid computing approach to parallel-process a neural network time-series model for forecasting electricity market prices. A grid computing environment introduced in a university computing laboratory provides access to otherwise underused computing resources. The grid computing of the neural network model not only processes several times faster than a single iterative process, but also provides chances of improving forecasting accuracy. Results of numerical tests using re...

  16. The Method of Oilfield Development Risk Forecasting and Early Warning Using Revised Bayesian Network

    Directory of Open Access Journals (Sweden)

    Yihua Zhong

    2016-01-01

    Full Text Available Oilfield development aiming at crude oil production is an extremely complex process, which involves many uncertain risk factors affecting oil output. Thus, risk prediction and early warning about oilfield development may insure operating and managing oilfields efficiently to meet the oil production plan of the country and sustainable development of oilfields. However, scholars and practitioners in the all world are seldom concerned with the risk problem of oilfield block development. The early warning index system of blocks development which includes the monitoring index and planning index was refined and formulated on the basis of researching and analyzing the theory of risk forecasting and early warning as well as the oilfield development. Based on the indexes of warning situation predicted by neural network, the method dividing the interval of warning degrees was presented by “3σ” rule; and a new method about forecasting and early warning of risk was proposed by introducing neural network to Bayesian networks. Case study shows that the results obtained in this paper are right and helpful to the management of oilfield development risk.

  17. Forecasting Natural Gas Prices Using Wavelets, Time Series, and Artificial Neural Networks.

    Science.gov (United States)

    Jin, Junghwan; Kim, Jinsoo

    2015-01-01

    Following the unconventional gas revolution, the forecasting of natural gas prices has become increasingly important because the association of these prices with those of crude oil has weakened. With this as motivation, we propose some modified hybrid models in which various combinations of the wavelet approximation, detail components, autoregressive integrated moving average, generalized autoregressive conditional heteroskedasticity, and artificial neural network models are employed to predict natural gas prices. We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not. The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results. The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance. Therefore, forecasting with only an approximation component would be acceptable, in consideration of forecasting efficiency.

  18. Operational flood forecasting system of Umbria Region "Functional Centre

    Science.gov (United States)

    Berni, N.; Pandolfo, C.; Stelluti, M.; Ponziani, F.; Viterbo, A.

    2009-04-01

    The hydrometeorological alert office (called "Decentrate Functional Centre" - CFD) of Umbria Region, in central Italy, is the office that provides technical tools able to support decisions when significant flood/landslide events occur, furnishing 24h support for the whole duration of the emergency period, according to the national directive DPCM 27 February 2004 concerning the "Operating concepts for functional management of national and regional alert system during flooding and landslide events for civil protection activities purposes" that designs, within the Italian Civil Defence Emergency Management System, a network of 21 regional Functional Centres coordinated by a central office at the National Civil Protection Department in Rome. Due to its "linking" role between Civil Protection "real time" activities and environmental/planning "deferred time" ones, the Centre is in charge to acquire and collect both real time and quasi-static data: quantitative data from monitoring networks (hydrometeorological stations, meteo radar, ...), meteorological forecasting models output, Earth Observation data, hydraulic and hydrological simulation models, cartographic and thematic GIS data (vectorial and raster type), planning studies related to flooding areas mapping, dam managing plans during flood events, non instrumental information from direct control of "territorial presidium". A detailed procedure for the management of critical events was planned, also in order to define the different role of various authorities and institutions involved. Tiber River catchment, of which Umbria region represents the main upper-medium portion, includes also regional trans-boundary issues very important to cope with, especially for what concerns large dam behavior and management during heavy rainfall. The alert system is referred to 6 different warning areas in which the territory has been divided into and based on a threshold system of three different increasing critical levels according

  19. A Hybrid Neural Network and H-P Filter Model for Short-Term Vegetable Price Forecasting

    Directory of Open Access Journals (Sweden)

    Youzhu Li

    2014-01-01

    Full Text Available This paper is concerned with time series data for vegetable prices, which have a great impact on human’s life. An accurate forecasting method for prices and an early-warning system in the vegetable market are an urgent need in people’s daily lives. The time series price data contain both linear and nonlinear patterns. Therefore, neither a current linear forecasting nor a neural network can be adequate for modeling and predicting the time series data. The linear forecasting model cannot deal with nonlinear relationships, while the neural network model alone is not able to handle both linear and nonlinear patterns at the same time. The linear Hodrick-Prescott (H-P filter can extract the trend and cyclical components from time series data. We predict the linear and nonlinear patterns and then combine the two parts linearly to produce a forecast from the original data. This study proposes a structure of a hybrid neural network based on an H-P filter that learns the trend and seasonal patterns separately. The experiment uses vegetable prices data to evaluate the model. Comparisons with the autoregressive integrated moving average method and back propagation artificial neural network methods show that our method has higher accuracy than the others.

  20. A New Training Method for Analyzable Structured Neural Network and Application of Daily Peak Load Forecasting

    Science.gov (United States)

    Iizaka, Tatsuya; Matsui, Tetsuro; Fukuyama, Yoshikazu

    This paper presents a daily peak load forecasting method using an analyzable structured neural network (ASNN) in order to explain forecasting reasons. In this paper, we propose a new training method for ASNN in order to explain forecasting reason more properly than the conventional training method. ASNN consists of two types of hidden units. One type of hidden units has connecting weights between the hidden units and only one group of related input units. Another one has connecting weights between the hidden units and all input units. The former type of hidden units allows to explain forecasting reasons. The latter type of hidden units ensures the forecasting performance. The proposed training method make the former type of hidden units train only independent relations between the input factors and output, and make the latter type of hidden units train only complicated interactions between input factors. The effectiveness of the proposed neural network is shown using actual daily peak load. ASNN trained by the proposed method can explain forecasting reasons more properly than ASNN trained by the conventional method. Moreover, the proposed neural network can forecast daily peak load more accurately than conventional neural network trained by the back propagation algorithm.

  1. Elements of a coastal ocean forecasting system for India

    Digital Repository Service at National Institute of Oceanography (India)

    Shetye, S.R.; Radhakrishnan, K.

    After about four decades of investment in infrastructure for ocean research, an appropriate initiative for India now would be to build a coastal ocean forecasting system to support the country's myriad activities in its Exclusive Economic Zone...

  2. NOAA/NCEP Global Forecast System (GFS) Atmospheric Model

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — U.S. National Oceanic and Atmospheric Administration (NOAA) National Centers for Environmental Prediction (NCEP) Global Forecast System (GFS) numerical weather...

  3. Climate Forecast System Reanalysis (CFSR), for 1979 to 2011

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The NCEP Climate Forecast System Reanalysis (CFSR) was initially completed for the 31-year period from 1979 to 2009, in January 2010. The CFSR was designed and...

  4. Climate Forecast System Version 2 (CFSv2) Operational Analysis

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Climate Forecast System Version 2 (CFSv2) produced by the NOAA National Centers for Environmental Prediction (NCEP) is a fully coupled model representing the...

  5. An experimental system for flood risk forecasting at global scale

    Science.gov (United States)

    Alfieri, L.; Dottori, F.; Kalas, M.; Lorini, V.; Bianchi, A.; Hirpa, F. A.; Feyen, L.; Salamon, P.

    2016-12-01

    Global flood forecasting and monitoring systems are nowadays a reality and are being applied by an increasing range of users and practitioners in disaster risk management. Furthermore, there is an increasing demand from users to integrate flood early warning systems with risk based forecasts, combining streamflow estimations with expected inundated areas and flood impacts. To this end, we have developed an experimental procedure for near-real time flood mapping and impact assessment based on the daily forecasts issued by the Global Flood Awareness System (GloFAS). The methodology translates GloFAS streamflow forecasts into event-based flood hazard maps based on the predicted flow magnitude and the forecast lead time and a database of flood hazard maps with global coverage. Flood hazard maps are then combined with exposure and vulnerability information to derive flood risk. Impacts of the forecasted flood events are evaluated in terms of flood prone areas, potential economic damage, and affected population, infrastructures and cities. To further increase the reliability of the proposed methodology we integrated model-based estimations with an innovative methodology for social media monitoring, which allows for real-time verification of impact forecasts. The preliminary tests provided good results and showed the potential of the developed real-time operational procedure in helping emergency response and management. In particular, the link with social media is crucial for improving the accuracy of impact predictions.

  6. Forecast and restoration of geomagnetic activity indices by using the software-computational neural network complex

    Science.gov (United States)

    Barkhatov, Nikolay; Revunov, Sergey

    2010-05-01

    specially designed pre-list are created which perceived by software-computational neural network complex where each line the detailed description of each experiment is contained. In this case, it is possible to perform statistical studies of work ANN results. The modular architecture of application with the purpose to solve various problems to modify it is allows. The developed software complex with sets of databases in the form of arrays, plug and downloaded separately is worked. For a complex functioning at present time the number of simultaneously processable streams of events in the input data has been determined. Blocks of databases contain the numerical minute data for 30 geomagnetic storms during the period from 2000 to 2003: Solar wind parameter, an interplanetary magnetic field (from space craft "ACE") and geomagnetic indices (Dst, SYM, ASY, AU, AL). These data are received from http://cdaweb.gsfc.nasa.gov. Is it necessary, modified discrete data using the spline is provided. This complex for wide range of tasks for the general trend studies of nonlinear connection between the different parameters determining the causal relationships in the system «interplanetary space-magnetosphere-ionosphere» is used. With this the following studies are carried out: the search of nonlinear connection of auroral and mid-current systems with the parameters of the solar wind and interplanetary magnetic field, the restoration of geomagnetic activity indices, the forecast and restoration of F2 ionosphere layer critical frequencies, the forecast maximum observed frequencies on the traces of oblique HF ionospheric sounding with perturbation heliogeophysical parameters and others. Work is executed at partial support under grants of the RFBR 08-05-12051-OBR and 09-05-00495, and also program Ministry of Education and Science «Development of higher school scientific potential (2009-2010, project N 1623)».

  7. Multistep Wind Speed Forecasting Using a Novel Model Hybridizing Singular Spectrum Analysis, Modified Intelligent Optimization, and Rolling Elman Neural Network

    Directory of Open Access Journals (Sweden)

    Zhongshan Yang

    2016-01-01

    Full Text Available Wind speed high-accuracy forecasting, an important part of the electrical system monitoring and control, is of the essence to protect the safety of wind power utilization. However, the wind speed signals are always intermittent and intrinsic complexity; therefore, it is difficult to forecast them accurately. Many traditional wind speed forecasting studies have focused on single models, which leads to poor prediction accuracy. In this paper, a new hybrid model is proposed to overcome the shortcoming of single models by combining singular spectrum analysis, modified intelligent optimization, and the rolling Elman neural network. In this model, except for the multiple seasonal patterns used to reduce interferences from the original data, the rolling model is utilized to forecast the multistep wind speed. To verify the forecasting ability of the proposed hybrid model, 10 min and 60 min wind speed data from the province of Shandong, China, were proposed in this paper as the case study. Compared to the other models, the proposed hybrid model forecasts the wind speed with higher accuracy.

  8. A Hybrid Wind Speed Forecasting System Based on a ‘Decomposition and Ensemble’ Strategy and Fuzzy Time Series

    Directory of Open Access Journals (Sweden)

    Hufang Yang

    2017-09-01

    Full Text Available Accurate and stable wind speed forecasting is of critical importance in the wind power industry and has measurable influence on power-system management and the stability of market economics. However, most traditional wind speed forecasting models require a large amount of historical data and face restrictions due to assumptions, such as normality postulates. Additionally, any data volatility leads to increased forecasting instability. Therefore, in this paper, a hybrid forecasting system, which combines the ‘decomposition and ensemble’ strategy and fuzzy time series forecasting algorithm, is proposed that comprises two modules—data pre-processing and forecasting. Moreover, the statistical model, artificial neural network, and Support Vector Regression model are employed to compare with the proposed hybrid system, which is proven to be very effective in forecasting wind speed data affected by noise and instability. The results of these comparisons demonstrate that the hybrid forecasting system can improve the forecasting accuracy and stability significantly, and supervised discretization methods outperform the unsupervised methods for fuzzy time series in most cases.

  9. Forecasting of Groundwater Level using Artificial Neural Network by incorporating river recharge and river bank infiltration

    Directory of Open Access Journals (Sweden)

    Nizar Shamsuddin Mohd Khairul

    2017-01-01

    Full Text Available Groundwater tables forecasting during implemented river bank infiltration (RBI method is important to identify adequate storage of groundwater aquifer for water supply purposes. This study illustrates the development and application of artificial neural networks (ANNs to predict groundwater tables in two vertical wells located in confined aquifer adjacent to the Langat River. ANN model was used in this study is based on the long period forecasting of daily groundwater tables. ANN models were carried out to predict groundwater tables for 1 day ahead at two different geological materials. The input to the ANN models consider of daily rainfall, river stage, water level, stream flow rate, temperature and groundwater level. Two different type of ANNs structure were used to predict the fluctuation of groundwater tables and compared the best forecasting values. The performance of different models structure of the ANN is used to identify the fluctuation of the groundwater table and provide acceptable predictions. Dynamics prediction and time series of the system can be implemented in two possible ways of modelling. The coefficient correlation (R, Mean Square Error (MSE, Root Mean Square Error (RMSE and coefficient determination (R2 were chosen as the selection criteria of the best model. The statistical values for DW1 are 0.8649, 0.0356, 0.01, and 0.748 respectively. While for DW2 the statistical values are 0.7392, 0.0781, 0.0139, and 0.546 respectively. Based on these results, it clearly shows that accurate predictions can be achieved with time series 1-day ahead of forecasting groundwater table and the interaction between river and aquifer can be examine. The findings of the study can be used to assist policy marker to manage groundwater resources by using RBI method.

  10. Electric power systems advanced forecasting techniques and optimal generation scheduling

    CERN Document Server

    Catalão, João P S

    2012-01-01

    Overview of Electric Power Generation SystemsCláudio MonteiroUncertainty and Risk in Generation SchedulingRabih A. JabrShort-Term Load ForecastingAlexandre P. Alves da Silva and Vitor H. FerreiraShort-Term Electricity Price ForecastingNima AmjadyShort-Term Wind Power ForecastingGregor Giebel and Michael DenhardPrice-Based Scheduling for GencosGovinda B. Shrestha and Songbo QiaoOptimal Self-Schedule of a Hydro Producer under UncertaintyF. Javier Díaz and Javie

  11. Neural network based load and price forecasting and confidence interval estimation in deregulated power markets

    Science.gov (United States)

    Zhang, Li

    With the deregulation of the electric power market in New England, an independent system operator (ISO) has been separated from the New England Power Pool (NEPOOL). The ISO provides a regional spot market, with bids on various electricity-related products and services submitted by utilities and independent power producers. A utility can bid on the spot market and buy or sell electricity via bilateral transactions. Good estimation of market clearing prices (MCP) will help utilities and independent power producers determine bidding and transaction strategies with low risks, and this is crucial for utilities to compete in the deregulated environment. MCP prediction, however, is difficult since bidding strategies used by participants are complicated and MCP is a non-stationary process. The main objective of this research is to provide efficient short-term load and MCP forecasting and corresponding confidence interval estimation methodologies. In this research, the complexity of load and MCP with other factors is investigated, and neural networks are used to model the complex relationship between input and output. With improved learning algorithm and on-line update features for load forecasting, a neural network based load forecaster was developed, and has been in daily industry use since summer 1998 with good performance. MCP is volatile because of the complexity of market behaviors. In practice, neural network based MCP predictors usually have a cascaded structure, as several key input factors need to be estimated first. In this research, the uncertainties involved in a cascaded neural network structure for MCP prediction are analyzed, and prediction distribution under the Bayesian framework is developed. A fast algorithm to evaluate the confidence intervals by using the memoryless Quasi-Newton method is also developed. The traditional back-propagation algorithm for neural network learning needs to be improved since MCP is a non-stationary process. The extended Kalman

  12. A Dynamic Fuzzy Controller to Meet Thermal Comfort by Using Neural Network Forecasted Parameters as the Input

    Directory of Open Access Journals (Sweden)

    Mario Collotta

    2014-07-01

    Full Text Available Heating, ventilating and air-conditioning (HVAC systems are typical non-linear time-variable multivariate systems with disturbances and uncertainties. In this paper, an approach based on a combined neuro-fuzzy model for dynamic and automatic regulation of indoor temperature is proposed. The proposed artificial neural network performs indoor temperatures forecasts that are used to feed a fuzzy logic control unit in order to manage the on/off switching of the HVAC system and the regulation of the inlet air speed. Moreover, the used neural network is optimized by the analytical calculation of the embedding parameters, and the goodness of this approach is tested through MATLAB. The fuzzy controller is driven by the indoor temperature forecasted by the neural network module and is able to adjust the membership functions dynamically, since thermal comfort is a very subjective factor and may vary even in the same subject. The paper shows some experimental results, through a real implementation in an embedded prototyping board, of the proposed approach in terms of the evolution of the inlet air speed injected by the fan coils, the indoor air temperature forecasted by the neural network model and the adjusting of the membership functions after receiving user feedback.

  13. Microsensors to the Model Forecasts: Multiscale Embedded Networked Sensing of Nutrients in the Watershed

    Science.gov (United States)

    Harmon, T. C.

    2005-12-01

    Hydrologic and water quality observatories are being planned with a vision of enhancing our ability to better understand, forecast and adaptively manage both water quantity and quality. To adequately cover these spatially and temporally variable systems, distributed, embedded sensor networks must be designed with the proper mix (multimodality) of sensors to quantify key system properties, including temperature and chemical distributions, as well as mass and energy fluxes, and to do so across multiple scales. Given resource limitations, process models need to be coupled to the sensor network to interpolate between sensor data. This work focuses on the spatially distributed flux of nutrients, specifically nitrate, in surface-subsurface environments. It begins at the sensor level, describing the development and testing of nitrate microsensors that are scaleable to large, dense sensor networks required to cover heterogeneous watersheds, including associated soil and sediment systems. First and second generation miniature and inexpensive nitrate sensors (ion selective electrodes) fabricated by depositing conducting polymers on carbon substrates are presented in the context of laboratory and field tests. While these sensors are limited to relatively short deployments (4-8 weeks), there are potential strategies for overcoming this problem. Scale-up to one- and three-dimensional soil/sediment sensor arrays is discussed in the context of two deployments: (1) a groundwater quality protection network, where recycled wastewater that is potentially high in nitrate is being used for agricultural irrigation, and (2) nonpoint source nitrate pollution in rivers and groundwater in agricultural watersheds. Recent hardware (wireless transceivers) and software advancements (e.g., network topology design and debugging, energy management) intended for networks spanning 100s of m in space are outlined in these examples. The discussion extends to sensor form factor, in situ calibration

  14. Demonstrating the value of larger ensembles in forecasting physical systems

    Directory of Open Access Journals (Sweden)

    Reason L. Machete

    2016-12-01

    Full Text Available Ensemble simulation propagates a collection of initial states forward in time in a Monte Carlo fashion. Depending on the fidelity of the model and the properties of the initial ensemble, the goal of ensemble simulation can range from merely quantifying variations in the sensitivity of the model all the way to providing actionable probability forecasts of the future. Whatever the goal is, success depends on the properties of the ensemble, and there is a longstanding discussion in meteorology as to the size of initial condition ensemble most appropriate for Numerical Weather Prediction. In terms of resource allocation: how is one to divide finite computing resources between model complexity, ensemble size, data assimilation and other components of the forecast system. One wishes to avoid undersampling information available from the model's dynamics, yet one also wishes to use the highest fidelity model available. Arguably, a higher fidelity model can better exploit a larger ensemble; nevertheless it is often suggested that a relatively small ensemble, say ~16 members, is sufficient and that larger ensembles are not an effective investment of resources. This claim is shown to be dubious when the goal is probabilistic forecasting, even in settings where the forecast model is informative but imperfect. Probability forecasts for a ‘simple’ physical system are evaluated at different lead times; ensembles of up to 256 members are considered. The pure density estimation context (where ensemble members are drawn from the same underlying distribution as the target differs from the forecasting context, where one is given a high fidelity (but imperfect model. In the forecasting context, the information provided by additional members depends also on the fidelity of the model, the ensemble formation scheme (data assimilation, the ensemble interpretation and the nature of the observational noise. The effect of increasing the ensemble size is quantified by

  15. Rough Precipitation Forecasts based on Analogue Method: an Operational System

    Science.gov (United States)

    Raffa, Mario; Mercogliano, Paola; Lacressonnière, Gwendoline; Guillaume, Bruno; Deandreis, Céline; Castanier, Pierre

    2017-04-01

    In the framework of the Climate KIC partnership, has been funded the project Wat-Ener-Cast (WEC), coordinated by ARIA Technologies, having the goal to adapt, through tailored weather-related forecast, the water and energy operations to the increased weather fluctuation and to climate change. The WEC products allow providing high quality forecast suited in risk and opportunities assessment dashboard for water and energy operational decisions and addressing the needs of sewage/water distribution operators, energy transport & distribution system operators, energy manager and wind energy producers. A common "energy water" web platform, able to interface with newest smart water-energy IT network have been developed. The main benefit by sharing resources through the "WEC platform" is the possibility to optimize the cost and the procedures of safety and maintenance team, in case of alerts and, finally to reduce overflows. Among the different services implemented on the WEC platform, ARIA have developed a product having the goal to support sewage/water distribution operators, based on a gradual forecast information system ( at 48hrs/24hrs/12hrs horizons) of heavy precipitation. For each fixed deadline different type of operation are implemented: 1) 48hour horizon, organisation of "on call team", 2) 24 hour horizon, update and confirm the "on call team", 3) 12 hour horizon, secure human resources and equipment (emptying storage basins, pipes manipulations …). More specifically CMCC have provided a statistical downscaling method in order to provide a "rough" daily local precipitation at 24 hours, especially when high precipitation values are expected. This statistical technique consists of an adaptation of analogue method based on ECMWF data (analysis and forecast at 24 hours). One of the most advantages of this technique concerns a lower computational burden and budget compared to running a Numerical Weather Prediction (NWP) model, also if, of course it provides only this

  16. Forecasting daily source air quality using multivariate statistical analysis and radial basis function networks.

    Science.gov (United States)

    Sun, Gang; Hoff, Steven J; Zelle, Brian C; Nelson, Minda A

    2008-12-01

    It is vital to forecast gas and particle matter concentrations and emission rates (GPCER) from livestock production facilities to assess the impact of airborne pollutants on human health, ecological environment, and global warming. Modeling source air quality is a complex process because of abundant nonlinear interactions between GPCER and other factors. The objective of this study was to introduce statistical methods and radial basis function (RBF) neural network to predict daily source air quality in Iowa swine deep-pit finishing buildings. The results show that four variables (outdoor and indoor temperature, animal units, and ventilation rates) were identified as relative important model inputs using statistical methods. It can be further demonstrated that only two factors, the environment factor and the animal factor, were capable of explaining more than 94% of the total variability after performing principal component analysis. The introduction of fewer uncorrelated variables to the neural network would result in the reduction of the model structure complexity, minimize computation cost, and eliminate model overfitting problems. The obtained results of RBF network prediction were in good agreement with the actual measurements, with values of the correlation coefficient between 0.741 and 0.995 and very low values of systemic performance indexes for all the models. The good results indicated the RBF network could be trained to model these highly nonlinear relationships. Thus, the RBF neural network technology combined with multivariate statistical methods is a promising tool for air pollutant emissions modeling.

  17. Short-Term Load Forecasting for Microgrids Based on Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Antonio J. Sanchez-Esguevillas

    2013-03-01

    Full Text Available Electricity is indispensable and of strategic importance to national economies. Consequently, electric utilities make an effort to balance power generation and demand in order to offer a good service at a competitive price. For this purpose, these utilities need electric load forecasts to be as accurate as possible. However, electric load depends on many factors (day of the week, month of the year, etc., which makes load forecasting quite a complex process requiring something other than statistical methods. This study presents an electric load forecast architectural model based on an Artificial Neural Network (ANN that performs Short-Term Load Forecasting (STLF. In this study, we present the excellent results obtained, and highlight the simplicity of the proposed model. Load forecasting was performed in a geographic location of the size of a potential microgrid, as microgrids appear to be the future of electric power supply.

  18. A seasonal agricultural drought forecast system for food-insecure regions of East Africa

    Science.gov (United States)

    Shukla, Shraddhanand; McNally, Amy; Husak, Gregory; Funk, Christopher C.

    2014-01-01

     The increasing food and water demands of East Africa's growing population are stressing the region's inconsistent water resources and rain-fed agriculture. More accurate seasonal agricultural drought forecasts for this region can inform better water and agricultural management decisions, support optimal allocation of the region's water resources, and mitigate socio-economic losses incurred by droughts and floods. Here we describe the development and implementation of a seasonal agricultural drought forecast system for East Africa (EA) that provides decision support for the Famine Early Warning Systems Network's science team. We evaluate this forecast system for a region of equatorial EA (2° S to 8° N, and 36° to 46° E) for the March-April-May growing season. This domain encompasses one of the most food insecure, climatically variable and socio-economically vulnerable regions in EA, and potentially the world: this region has experienced famine as recently as 2011. To assess the agricultural outlook for the upcoming season our forecast system simulates soil moisture (SM) scenarios using the Variable Infiltration Capacity (VIC) hydrologic model forced with climate scenarios for the upcoming season. First, to show that the VIC model is appropriate for this application we forced the model with high quality atmospheric observations and found that the resulting SM values were consistent with the Food and Agriculture Organization's (FAO's) Water Requirement Satisfaction Index (WRSI), an index used by FEWS NET to estimate crop yields. Next we tested our forecasting system with hindcast runs (1993–2012). We found that initializing SM forecasts with start-of-season (5 March) SM conditions resulted in useful SM forecast skill (> 0.5 correlation) at 1-month, and in some cases at 3 month lead times. Similarly, when the forecast was initialized with mid-season (i.e. 5 April) SM conditions the skill until the end-of-season improved. This shows that early-season rainfall

  19. Short-Term Wind Speed Forecasting for Power System Operations

    KAUST Repository

    Zhu, Xinxin

    2012-04-01

    The emphasis on renewable energy and concerns about the environment have led to large-scale wind energy penetration worldwide. However, there are also significant challenges associated with the use of wind energy due to the intermittent and unstable nature of wind. High-quality short-term wind speed forecasting is critical to reliable and secure power system operations. This article begins with an overview of the current status of worldwide wind power developments and future trends. It then reviews some statistical short-term wind speed forecasting models, including traditional time series approaches and more advanced space-time statistical models. It also discusses the evaluation of forecast accuracy, in particular, the need for realistic loss functions. New challenges in wind speed forecasting regarding ramp events and offshore wind farms are also presented. © 2012 The Authors. International Statistical Review © 2012 International Statistical Institute.

  20. Short-Termed Integrated Forecasting System: 1993 Model documentation report

    Energy Technology Data Exchange (ETDEWEB)

    1993-05-01

    The purpose of this report is to define the Short-Term Integrated Forecasting System (STIFS) and describe its basic properties. The Energy Information Administration (EIA) of the US Energy Department (DOE) developed the STIFS model to generate short-term (up to 8 quarters), monthly forecasts of US supplies, demands, imports exports, stocks, and prices of various forms of energy. The models that constitute STIFS generate forecasts for a wide range of possible scenarios, including the following ones done routinely on a quarterly basis: A base (mid) world oil price and medium economic growth. A low world oil price and high economic growth. A high world oil price and low economic growth. This report is written for persons who want to know how short-term energy markets forecasts are produced by EIA. The report is intended as a reference document for model analysts, users, and the public.

  1. An operational real-time flood forecasting system in Southern Italy

    Science.gov (United States)

    Ortiz, Enrique; Coccia, Gabriele; Todini, Ezio

    2015-04-01

    A real-time flood forecasting system has been operating since year 2012 as a non-structural measure for mitigating the flood risk in Campania Region (Southern Italy), within the Sele river basin (3.240 km2). The Sele Flood Forecasting System (SFFS) has been built within the FEWS (Flood Early Warning System) platform developed by Deltares and it assimilates the numerical weather predictions of the COSMO LAM family: the deterministic COSMO-LAMI I2, the deterministic COSMO-LAMI I7 and the ensemble numerical weather predictions COSMO-LEPS (16 members). Sele FFS is composed by a cascade of three main models. The first model is a fully continuous physically based distributed hydrological model, named TOPKAPI-eXtended (Idrologia&Ambiente s.r.l., Naples, Italy), simulating the dominant processes controlling the soil water dynamics, runoff generation and discharge with a spatial resolution of 250 m. The second module is a set of Neural-Networks (ANN) built for forecasting the river stages at a set of monitored cross-sections. The third component is a Model Conditional Processor (MCP), which provides the predictive uncertainty (i.e., the probability of occurrence of a future flood event) within the framework of a multi-temporal forecast, according to the most recent advancements on this topic (Coccia and Todini, HESS, 2011). The MCP provides information about the probability of exceedance of a maximum river stage within the forecast lead time, by means of a discrete time function representing the variation of cumulative probability of exceeding a river stage during the forecast lead time and the distribution of the time occurrence of the flood peak, starting from one or more model forecasts. This work shows the Sele FFS performance after two years of operation, evidencing the added-values that can provide to a flood early warning and emergency management system.

  2. Neuro-fuzzy system for chaotic time series forecasting

    Science.gov (United States)

    Masulli, Francesco; Studer, Leonard

    1997-10-01

    We report on an on-going study to assess potential benefits using soft computing methods in forecasting problems. Our goal is to forecast natural phenomena represented by time series that show chaotic features. We use a neuro-fuzzy system for its ability to adapt to numerical data and for the possibility to input and extract expert knowledge expressed in words. We present results of experiments designed to study how to shape a neuro-fuzzy systems to forecast chaotic time series. Our main conclusions are: (1) The neuro-fuzzy system is able to forecast a synthetic chaotic time series with high accuracy if the number of inputs and the time delay between them are chosen adequately. (2) The Takens-Mane theorem from chaos theory gives a useful lower bound on the minimal number of inputs. (3) The time delay between the inputs can not be set a priori. It has to be tuned for every different times series. (4) The number of fuzzy rules seems related to the size of the learning set and not to the structure of the chaotic dynamical system. We tentatively try to interpret the rules that the neuro-fuzzy system has learned. Finally we discuss the adequacy of the whole set of fuzzy rules to forecast locally the dynamical system.

  3. Sea Level Forecasts Aggregated from Established Operational Systems

    Directory of Open Access Journals (Sweden)

    Andy Taylor

    2017-08-01

    Full Text Available A system for providing routine seven-day forecasts of sea level observable at tide gauge locations is described and evaluated. Forecast time series are aggregated from well-established operational systems of the Australian Bureau of Meteorology; although following some adjustments these systems are only quasi-complimentary. Target applications are routine coastal decision processes under non-extreme conditions. The configuration aims to be relatively robust to operational realities such as version upgrades, data gaps and metadata ambiguities. Forecast skill is evaluated against hourly tide gauge observations. Characteristics of the bias correction term are demonstrated to be primarily static in time, with time varying signals showing regional coherence. This simple approach to exploiting existing complex systems can offer valuable levels of skill at a range of Australian locations. The prospect of interpolation between observation sites and exploitation of lagged-ensemble uncertainty estimates could be meaningfully pursued. Skill characteristics define a benchmark against which new operational sea level forecasting systems can be measured. More generally, an aggregation approach may prove to be optimal for routine sea level forecast services given the physically inhomogeneous processes involved and ability to incorporate ongoing improvements and extensions of source systems.

  4. Short-term localized weather forecasting by using different artificial neural network algorithm in tropical climate

    OpenAIRE

    Mohd-Safar, Noor Zuraidin; Ndzi, David Lorater; Kagalidis, Ioannis; Yang, Yanyan; Zakaria, Ammar

    2016-01-01

    This paper evaluates the performance of localized weather forecasting model using Artificial Neural Network (ANN) with different ANN algorithms in a tropical climate. Three ANN algorithms namely, Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient are used in the short-term weather forecasting model. The study focuses on the data from North-West Malaysia (Chuping). Meteorological data such as atmospheric pressure, temperature, dew point, humidity and wind speed are used...

  5. Modelling and Forecasting Cruise Tourism Demand to İzmir by Different Artificial Neural Network Architectures

    Directory of Open Access Journals (Sweden)

    Murat Cuhadar

    2014-03-01

    Full Text Available Abstract Cruise ports emerged as an important sector for the economy of Turkey bordered on three sides by water. Forecasting cruise tourism demand ensures better planning, efficient preparation at the destination and it is the basis for elaboration of future plans. In the recent years, new techniques such as; artificial neural networks were employed for developing of the predictive models to estimate tourism demand. In this study, it is aimed to determine the forecasting method that provides the best performance when compared the forecast accuracy of Multi-layer Perceptron (MLP, Radial Basis Function (RBF and Generalized Regression neural network (GRNN to estimate the monthly inbound cruise tourism demand to İzmir via the method giving best results. We used the total number of foreign cruise tourist arrivals as a measure of inbound cruise tourism demand and monthly cruise tourist arrivals to İzmir Cruise Port in the period of January 2005 ‐December 2013 were utilized to appropriate model. Experimental results showed that radial basis function (RBF neural network outperforms multi-layer perceptron (MLP and the generalised regression neural networks (GRNN in terms of forecasting accuracy. By the means of the obtained RBF neural network model, it has been forecasted the monthly inbound cruise tourism demand to İzmir for the year 2014.

  6. A Passenger Flow Risk Forecasting Algorithm for High-Speed Railway Transport Hub Based on Surveillance Sensor Networks

    Directory of Open Access Journals (Sweden)

    Zhengyu Xie

    2016-01-01

    Full Text Available Passenger flow risk forecasting is a vital task for safety management in high-speed railway transport hub. In this paper, we considered the passenger flow risk forecasting problem in high-speed railway transport hub. Based on the surveillance sensor networks, a passenger flow risk forecasting algorithm was developed based on spatial correlation. Computational results showed that the proposed forecasting approach was effective and significant for the high-speed railway transport hub.

  7. Conditional time series forecasting with convolutional neural networks

    NARCIS (Netherlands)

    A. Borovykh (Anastasia); S.M. Bohte (Sander); C.W. Oosterlee (Cornelis)

    2017-01-01

    textabstractForecasting financial time series using past observations has been a significant topic of interest. While temporal relationships in the data exist, they are difficult to analyze and predict accurately due to the non-linear trends and noise present in the series. We propose to learn these

  8. The Next Mercator Ocean Forecasting System: Scientific and Technical Designs

    Science.gov (United States)

    Tranchant, B.; Testut, C.; Bourdallebadie, R.; Derval, C.; Drillet, Y.; Le Galloudec, O.

    2008-12-01

    An integrated ocean forecasting and data assimilation system has been and is continuing to be developed by Mercator Ocean. It consists of a global ocean and sea ice high resolution model with a horizontal resolution of 1/12 ° and 50 vertical levels based on the NEMO OGCM which is coupled to the data assimilation scheme named SAM2v1 (based on the SEEK filter). Assimilation of both in situ and remotely sensed data (SLA, SST) provides the initial conditions required for numerical ocean prediction. This new global ocean forecasting system offers a new perspective on ocean monitoring but it needs high performance computing resources. Scientific and technical designs of this new global ocean forecasting system will be shown. In addition, results of an interannual simulation forced by ECMWF atmospheric forcing and results of first hindcast experiments will be detailed.

  9. Computer network defense system

    Science.gov (United States)

    Urias, Vincent; Stout, William M. S.; Loverro, Caleb

    2017-08-22

    A method and apparatus for protecting virtual machines. A computer system creates a copy of a group of the virtual machines in an operating network in a deception network to form a group of cloned virtual machines in the deception network when the group of the virtual machines is accessed by an adversary. The computer system creates an emulation of components from the operating network in the deception network. The components are accessible by the group of the cloned virtual machines as if the group of the cloned virtual machines was in the operating network. The computer system moves network connections for the group of the virtual machines in the operating network used by the adversary from the group of the virtual machines in the operating network to the group of the cloned virtual machines, enabling protecting the group of the virtual machines from actions performed by the adversary.

  10. Water level forecasting through fuzzy logic and artificial neural network approaches

    Directory of Open Access Journals (Sweden)

    S. Alvisi

    2006-01-01

    Full Text Available In this study three data-driven water level forecasting models are presented and discussed. One is based on the artificial neural networks approach, while the other two are based on the Mamdani and the Takagi-Sugeno fuzzy logic approaches, respectively. All of them are parameterised with reference to flood events alone, where water levels are higher than a selected threshold. The analysis of the three models is performed by using the same input and output variables. However, in order to evaluate their capability to deal with different levels of information, two different input sets are considered. The former is characterized by significant spatial and time aggregated rainfall information, while the latter considers rainfall information more distributed in space and time. The analysis is made with great attention to the reliability and accuracy of each model, with reference to the Reno river at Casalecchio di Reno (Bologna, Italy. It is shown that the two models based on the fuzzy logic approaches perform better when the physical phenomena considered are synthesised by both a limited number of variables and IF-THEN logic statements, while the ANN approach increases its performance when more detailed information is used. As regards the reliability aspect, it is shown that the models based on the fuzzy logic approaches may fail unexpectedly to forecast the water levels, in the sense that in the testing phase, some input combinations are not recognised by the rule system and thus no forecasting is performed. This problem does not occur in the ANN approach.

  11. Mediterranean monitoring and forecasting operational system for Copernicus Marine Service

    Science.gov (United States)

    Coppini, Giovanni; Drudi, Massimiliano; Korres, Gerasimos; Fratianni, Claudia; Salon, Stefano; Cossarini, Gianpiero; Clementi, Emanuela; Zacharioudaki, Anna; Grandi, Alessandro; Delrosso, Damiano; Pistoia, Jenny; Solidoro, Cosimo; Pinardi, Nadia; Lecci, Rita; Agostini, Paola; Cretì, Sergio; Turrisi, Giuseppe; Palermo, Francesco; Konstantinidou, Anna; Storto, Andrea; Simoncelli, Simona; Di Pietro, Pier Luigi; Masina, Simona; Ciliberti, Stefania Angela; Ravdas, Michalis; Mancini, Marco; Aloisio, Giovanni; Fiore, Sandro; Buonocore, Mauro

    2016-04-01

    The MEDiterranean Monitoring and Forecasting Center (Med-MFC) is part of the Copernicus Marine Environment Monitoring Service (CMEMS, http://marine.copernicus.eu/), provided on an operational mode by Mercator Ocean in agreement with the European Commission. Specifically, Med MFC system provides regular and systematic information about the physical state of the ocean and marine ecosystems for the Mediterranean Sea. The Med-MFC service started in May 2015 from the pre-operational system developed during the MyOcean projects, consolidating the understanding of regional Mediterranean Sea dynamics, from currents to biogeochemistry to waves, interfacing with local data collection networks and guaranteeing an efficient link with other Centers in Copernicus network. The Med-MFC products include analyses, 10 days forecasts and reanalysis, describing currents, temperature, salinity, sea level and pelagic biogeochemistry. Waves products will be available in MED-MFC version in 2017. The consortium, composed of INGV (Italy), HCMR (Greece) and OGS (Italy) and coordinated by the Euro-Mediterranean Centre on Climate Change (CMCC, Italy), performs advanced R&D activities and manages the service delivery. The Med-MFC infrastructure consists of 3 Production Units (PU), for Physics, Biogechemistry and Waves, a unique Dissemination Unit (DU) and Archiving Unit (AU) and Backup Units (BU) for all principal components, guaranteeing a resilient configuration of the service and providing and efficient and robust solution for the maintenance of the service and delivery. The Med-MFC includes also an evolution plan, both in terms of research and operational activities, oriented to increase the spatial resolution of products, to start wave products dissemination, to increase temporal extent of the reanalysis products and improving ocean physical modeling for delivering new products. The scientific activities carried out in 2015 concerned some improvements in the physical, biogeochemical and

  12. Wind Power Forecasting Using Multi-Objective Evolutionary Algorithms for Wavelet Neural Network-Optimized Prediction Intervals

    Directory of Open Access Journals (Sweden)

    Yanxia Shen

    2018-01-01

    Full Text Available The intermittency of renewable energy will increase the uncertainty of the power system, so it is necessary to predict the short-term wind power, after which the electrical power system can operate reliably and safely. Unlike the traditional point forecasting, the purpose of this study is to quantify the potential uncertainties of wind power and to construct prediction intervals (PIs and prediction models using wavelet neural network (WNN. Lower upper bound estimation (LUBE of the PIs is achieved by minimizing a multi-objective function covering both interval width and coverage probabilities. Considering the influence of the points out of the PIs to shorten the width of PIs without compromising coverage probability, a new, improved, multi-objective artificial bee colony (MOABC algorithm combining multi-objective evolutionary knowledge, called EKMOABC, is proposed for the optimization of the forecasting model. In this paper, some comparative simulations are carried out and the results show that the proposed model and algorithm can achieve higher quality PIs for wind power forecasting. Taking into account the intermittency of renewable energy, such a type of wind power forecast can actually provide a more reliable reference for dispatching of the power system.

  13. The role of model and initial condition error in numerical weather forecasting investigated with an observing system simulation experiment

    Directory of Open Access Journals (Sweden)

    Nikki C. Privé

    2013-11-01

    Full Text Available A series of experiments that explore the roles of model and initial condition error in numerical weather prediction are performed using an observing system simulation experiment (OSSE framework developed at the National Aeronautics and Space Administration Global Modeling and Assimilation Office (NASA/GMAO. The use of an OSSE allows the analysis and forecast errors to be explicitly calculated, and different hypothetical observing networks can be tested with ease. In these experiments, both a full global OSSE framework and an ‘identical twin’ OSSE setup are used to compare the behaviour of the data assimilation system (DAS and evolution of forecast skill with and without model error. The initial condition error is manipulated by varying the distribution and quality of the observing network and the magnitude of observation errors. The results show that model error has a strong impact on both the quality of the analysis field and the evolution of forecast skill, including both systematic and unsystematic model error components. With a realistic observing network, the analysis state retains a significant quantity of error due to systematic model error. If errors of the analysis state are minimised, model error acts to rapidly degrade forecast skill during the first 24–48 hours of forward integration. In the presence of model error, the impact of observation errors on forecast skill is small, but in the absence of model error, observation errors cause a substantial degradation of the skill of medium-range forecasts.

  14. Daily Crude Oil Price Forecasting Using Hybridizing Wavelet and Artificial Neural Network Model

    Directory of Open Access Journals (Sweden)

    Ani Shabri

    2014-01-01

    Full Text Available A new method based on integrating discrete wavelet transform and artificial neural networks (WANN model for daily crude oil price forecasting is proposed. The discrete Mallat wavelet transform is used to decompose the crude price series into one approximation series and some details series (DS. The new series obtained by adding the effective one approximation series and DS component is then used as input into the ANN model to forecast crude oil price. The relative performance of WANN model was compared to regular ANN model for crude oil forecasting at lead times of 1 day for two main crude oil price series, West Texas Intermediate (WTI and Brent crude oil spot prices. In both cases, WANN model was found to provide more accurate crude oil prices forecasts than individual ANN model.

  15. Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization

    Science.gov (United States)

    Abbot, John; Marohasy, Jennifer

    2017-11-01

    General circulation models, which forecast by first modelling actual conditions in the atmosphere and ocean, are used extensively for monthly rainfall forecasting. We show how more skilful monthly and seasonal rainfall forecasts can be achieved through the mining of historical climate data using artificial neural networks (ANNs). This technique is demonstrated for two agricultural regions of Australia: the wheat belt of Western Australia and the sugar growing region of coastal Queensland. The most skilful monthly rainfall forecasts measured in terms of Ideal Point Error (IPE), and a score relative to climatology, are consistently achieved through the use of ANNs optimized for each month individually, and also by choosing to input longer historical series of climate indices. Using the longer series restricts the number of climate indices that can be used.

  16. Flood forecasting and alert system for Arda River basin

    Science.gov (United States)

    Artinyan, Eram; Vincendon, Beatrice; Kroumova, Kamelia; Nedkov, Nikolai; Tsarev, Petko; Balabanova, Snezhanka; Koshinchanov, Georgy

    2016-10-01

    The paper presents the set-up and functioning of a flood alert system based on SURFEX-TOPODYN platform for the cross-border Arda River basin. The system was built within a Bulgarian-Greek project funded by the European Territorial Cooperation (ETC) Programme and is in operational use since April 2014. The basin is strongly influenced by Mediterranean cyclones during the autumn-winter period and experiences dangerous rapid floods, mainly after intensive rain, often combined with snow melt events. The steep mountainous terrain leads to floods with short concentration time and high river speed causing damage to settlements and infrastructure. The main challenge was to correctly simulate the riverflow in near-real time and to timely forecast peak floods for small drainage basins below 100 km2 but also for larger ones of about 1900 km2 using the same technology. To better account for that variability, a modification of the original hydrological model parameterisation is proposed. Here we present the first results of a new model variant which uses dynamically adjusted TOPODYN river velocity as function of the computed partial streamflow discharge. Based on historical flooding data, river sections along endangered settlements were included in the river flow forecasting. A continuous hydrological forecast for 5 days ahead was developed for 18 settlements in Bulgaria and for the border with Greece, thus giving enough reaction time in case of high floods. The paper discusses the practical implementation of models for the Arda basin, the method used to calibrate the models' parameters, the results of the calibration-validation procedure and the way the information system is organised. A real case of forecasted rapid floods that occurred after the system's finalisation is analysed. One of the important achievements of the project is the on-line presentation of the forecasts that takes into account their temporal variability and uncertainty. The web presentation includes a

  17. Operational Forecasting and Warning systems for Coastal hazards in Korea

    Science.gov (United States)

    Park, Kwang-Soon; Kwon, Jae-Il; Kim, Jin-Ah; Heo, Ki-Young; Jun, Kicheon

    2017-04-01

    Coastal hazards caused by both Mother Nature and humans cost tremendous social, economic and environmental damages. To mitigate these damages many countries have been running the operational forecasting or warning systems. Since 2009 Korea Operational Oceanographic System (KOOS) has been developed by the leading of Korea Institute of Ocean Science and Technology (KIOST) in Korea and KOOS has been operated in 2012. KOOS is consists of several operational modules of numerical models and real-time observations and produces the basic forecasting variables such as winds, tides, waves, currents, temperature and salinity and so on. In practical application systems include storm surges, oil spills, and search and rescue prediction models. In particular, abnormal high waves (swell-like high-height waves) have occurred in the East coast of Korea peninsula during winter season owing to the local meteorological condition over the East Sea, causing property damages and the loss of human lives. In order to improve wave forecast accuracy even very local wave characteristics, numerical wave modeling system using SWAN is established with data assimilation module using 4D-EnKF and sensitivity test has been conducted. During the typhoon period for the prediction of sever waves and the decision making support system for evacuation of the ships, a high-resolution wave forecasting system has been established and calibrated.

  18. Enhancing Community Based Early Warning Systems in Nepal with Flood Forecasting Using Local and Global Models

    Science.gov (United States)

    Dugar, Sumit; Smith, Paul; Parajuli, Binod; Khanal, Sonu; Brown, Sarah; Gautam, Dilip; Bhandari, Dinanath; Gurung, Gehendra; Shakya, Puja; Kharbuja, RamGopal; Uprety, Madhab

    2017-04-01

    Operationalising effective Flood Early Warning Systems (EWS) in developing countries like Nepal poses numerous challenges, with complex topography and geology, sparse network of river and rainfall gauging stations and diverse socio-economic conditions. Despite these challenges, simple real-time monitoring based EWSs have been in place for the past decade. A key constraint of these simple systems is the very limited lead time for response - as little as 2-3 hours, especially for rivers originating from steep mountainous catchments. Efforts to increase lead time for early warning are focusing on imbedding forecasts into the existing early warning systems. In 2016, the Nepal Department of Hydrology and Meteorology (DHM) piloted an operational Probabilistic Flood Forecasting Model in major river basins across Nepal. This comprised a low data approach to forecast water levels, developed jointly through a research/practitioner partnership with Lancaster University and WaterNumbers (UK) and the International NGO Practical Action. Using Data-Based Mechanistic Modelling (DBM) techniques, the model assimilated rainfall and water levels to generate localised hourly flood predictions, which are presented as probabilistic forecasts, increasing lead times from 2-3 hours to 7-8 hours. The Nepal DHM has simultaneously started utilizing forecasts from the Global Flood Awareness System (GLoFAS) that provides streamflow predictions at the global scale based upon distributed hydrological simulations using numerical ensemble weather forecasts from the ECMWF (European Centre for Medium-Range Weather Forecasts). The aforementioned global and local models have already affected the approach to early warning in Nepal, being operational during the 2016 monsoon in the West Rapti basin in Western Nepal. On 24 July 2016, GLoFAS hydrological forecasts for the West Rapti indicated a sharp rise in river discharge above 1500 m3/sec (equivalent to the river warning level at 5 meters) with 53

  19. Climate Prediction Center (CPC) NCEP-Global Forecast System (GFS) 0-10cm Soil-Moisture Forecast Product

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The Global Forecast System (GFS) forecast 0-10cm soil-moisture data at 37.5km resolution is created at the NOAA Climate Prediction Center for the purpose of near...

  20. Application of BP Neural Network Algorithm in Traditional Hydrological Model for Flood Forecasting

    Directory of Open Access Journals (Sweden)

    Jianjin Wang

    2017-01-01

    Full Text Available Flooding contributes to tremendous hazards every year; more accurate forecasting may significantly mitigate the damages and loss caused by flood disasters. Current hydrological models are either purely knowledge-based or data-driven. A combination of data-driven method (artificial neural networks in this paper and knowledge-based method (traditional hydrological model may booster simulation accuracy. In this study, we proposed a new back-propagation (BP neural network algorithm and applied it in the semi-distributed Xinanjiang (XAJ model. The improved hydrological model is capable of updating the flow forecasting error without losing the leading time. The proposed method was tested in a real case study for both single period corrections and real-time corrections. The results reveal that the proposed method could significantly increase the accuracy of flood forecasting and indicate that the global correction effect is superior to the second-order autoregressive correction method in real-time correction.

  1. Modeling and computing of stock index forecasting based on neural network and Markov chain.

    Science.gov (United States)

    Dai, Yonghui; Han, Dongmei; Dai, Weihui

    2014-01-01

    The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP) neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market.

  2. Network operating system

    Science.gov (United States)

    1985-01-01

    Long-term and short-term objectives for the development of a network operating system for the Space Station are stated. The short-term objective is to develop a prototype network operating system for a 100 megabit/second fiber optic data bus. The long-term objective is to establish guidelines for writing a detailed specification for a Space Station network operating system. Major milestones are noted. Information is given in outline form.

  3. Power Grid Maintenance Scheduling Intelligence Arrangement Supporting System Based on Power Flow Forecasting

    Science.gov (United States)

    Xie, Chang; Wen, Jing; Liu, Wenying; Wang, Jiaming

    With the development of intelligent dispatching, the intelligence level of network control center full-service urgent need to raise. As an important daily work of network control center, the application of maintenance scheduling intelligent arrangement to achieve high-quality and safety operation of power grid is very important. By analyzing the shortages of the traditional maintenance scheduling software, this paper designs a power grid maintenance scheduling intelligence arrangement supporting system based on power flow forecasting, which uses the advanced technologies in maintenance scheduling, such as artificial intelligence, online security checking, intelligent visualization techniques. It implements the online security checking of maintenance scheduling based on power flow forecasting and power flow adjusting based on visualization, in order to make the maintenance scheduling arrangement moreintelligent and visual.

  4. Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze, China

    Directory of Open Access Journals (Sweden)

    C. W. Dawson

    2002-01-01

    Full Text Available While engineers have been quantifying rainfall-runoff processes since the mid-19th century, it is only in the last decade that artificial neural network models have been applied to the same task. This paper evaluates two neural networks in this context: the popular multilayer perceptron (MLP, and the radial basis function network (RBF. Using six-hourly rainfall-runoff data for the River Yangtze at Yichang (upstream of the Three Gorges Dam for the period 1991 to 1993, it is shown that both neural network types can simulate river flows beyond the range of the training set. In addition, an evaluation of alternative RBF transfer functions demonstrates that the popular Gaussian function, often used in RBF networks, is not necessarily the ‘best’ function to use for river flow forecasting. Comparisons are also made between these neural networks and conventional statistical techniques; stepwise multiple linear regression, auto regressive moving average models and a zero order forecasting approach. Keywords: Artificial neural network, multilayer perception, radial basis function, flood forecasting

  5. Towards a medium-range coastal station fog forecasting system

    CSIR Research Space (South Africa)

    Landman, S

    2013-09-01

    Full Text Available -1 29th Annual conference of South African Society for Atmospheric Sciences (SASAS) 2013 http://sasas.ukzn.ac.za/homepage.aspx Towards a Medium-Range Coastal Station Fog Forecasting System Stephanie Landman*1, Estelle Marx1, Willem A. Landman2...

  6. Adaptive predictions of the euro/złoty currency exchange rate using state space wavelet networks and forecast combinations

    Directory of Open Access Journals (Sweden)

    Brdyś Mietek A.

    2016-03-01

    Full Text Available The paper considers the forecasting of the euro/Polish złoty (EUR/PLN spot exchange rate by applying state space wavelet network and econometric forecast combination models. Both prediction methods are applied to produce one-trading-day-ahead forecasts of the EUR/PLN exchange rate. The paper presents the general state space wavelet network and forecast combination models as well as their underlying principles. The state space wavelet network model is, in contrast to econometric forecast combinations, a non-parametric prediction technique which does not make any distributional assumptions regarding the underlying input variables. Both methods can be used as forecasting tools in portfolio investment management, asset valuation, IT security and integrated business risk intelligence in volatile market conditions.

  7. Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks

    Directory of Open Access Journals (Sweden)

    Petr Maca

    2016-01-01

    Full Text Available The presented paper compares forecast of drought indices based on two different models of artificial neural networks. The first model is based on feedforward multilayer perceptron, sANN, and the second one is the integrated neural network model, hANN. The analyzed drought indices are the standardized precipitation index (SPI and the standardized precipitation evaporation index (SPEI and were derived for the period of 1948–2002 on two US catchments. The meteorological and hydrological data were obtained from MOPEX experiment. The training of both neural network models was made by the adaptive version of differential evolution, JADE. The comparison of models was based on six model performance measures. The results of drought indices forecast, explained by the values of four model performance indices, show that the integrated neural network model was superior to the feedforward multilayer perceptron with one hidden layer of neurons.

  8. Artificial neural networks to forecast biomass of Pacific sardine and its environment

    DEFF Research Database (Denmark)

    Cisneros Mata, M.A.; Brey, T.; Jarre, Astrid

    1996-01-01

    We tested the forecasting performance of artificial neural networks (ANNs) using several time series of environmental and biotic data pertaining to the California Current (CC) neritic ecosystem. ANNs performed well predicting CC monthly 10-m depth temperature up to nine years in advance, using te...

  9. Improving Global Forecast System of extreme precipitation events with regional statistical model: Application of quantile-based probabilistic forecasts

    Science.gov (United States)

    Shastri, Hiteshri; Ghosh, Subimal; Karmakar, Subhankar

    2017-02-01

    Forecasting of extreme precipitation events at a regional scale is of high importance due to their severe impacts on society. The impacts are stronger in urban regions due to high flood potential as well high population density leading to high vulnerability. Although significant scientific improvements took place in the global models for weather forecasting, they are still not adequate at a regional scale (e.g., for an urban region) with high false alarms and low detection. There has been a need to improve the weather forecast skill at a local scale with probabilistic outcome. Here we develop a methodology with quantile regression, where the reliably simulated variables from Global Forecast System are used as predictors and different quantiles of rainfall are generated corresponding to that set of predictors. We apply this method to a flood-prone coastal city of India, Mumbai, which has experienced severe floods in recent years. We find significant improvements in the forecast with high detection and skill scores. We apply the methodology to 10 ensemble members of Global Ensemble Forecast System and find a reduction in ensemble uncertainty of precipitation across realizations with respect to that of original precipitation forecasts. We validate our model for the monsoon season of 2006 and 2007, which are independent of the training/calibration data set used in the study. We find promising results and emphasize to implement such data-driven methods for a better probabilistic forecast at an urban scale primarily for an early flood warning.

  10. Forecasting abrupt changes in foreign exchange markets: method using dynamical network marker

    Science.gov (United States)

    Oya, Shunsuke; Aihara, Kazuyuki; Hirata, Yoshito

    2014-11-01

    We apply the idea of dynamical network markers (Chen et al 2012 Sci. Rep. 2 342) to foreign exchange markets so that early warning signals can be provided for any abrupt changes. The dynamical network marker constructed achieves a high odds ratio for forecasting these sudden changes. In addition, we also extend the notion of the dynamical network marker by using recurrence plots so that the notion can be applied to delay coordinates and point processes. Thus, the dynamical network marker is useful in a variety of contexts in science, technology, and society.

  11. Wavelet Network Model Based on Multiple Criteria Decision Making for Forecasting Temperature Time Series

    OpenAIRE

    Zhang, Jian; Yang, Xiao-hua; Chen, Xiao-juan

    2015-01-01

    Due to nonlinear and multiscale characteristics of temperature time series, a new model called wavelet network model based on multiple criteria decision making (WNMCDM) has been proposed, which combines the advantage of wavelet analysis, multiple criteria decision making, and artificial neural network. One case for forecasting extreme monthly maximum temperature of Miyun Reservoir has been conducted to examine the performance of WNMCDM model. Compared with nearest neighbor bootstrapping regr...

  12. Artificial Neural Network Based Model for Forecasting of Inflation in India

    Directory of Open Access Journals (Sweden)

    Gour Sundar Mitra Thakur

    2016-03-01

    Full Text Available Inflation can be attributed to both microeconomic and macroeconomic factors which influence the stability of the economy of any nation. With the raising of recession at the end of the year 2008, world communities started paying much contemplation on inflation and put enormous hard work to predict it accurately. Prediction of inflation is not a simple task. Moreover, the behavior of inflation is so complex and uncertain that both economists and statisticians have been striving to model and forecast inflation in an accurate way. As a result, many researchers have proposed inflation forecasting models based on different methods; however the accuracy is always being a major constraint. In this paper, we have analyzed the historical monthly economic data of India between January 2000 and December 2012 and constructed an inflation forecasting model based on feed forward back propagation neural network. Initially some critical factors that can considerably influence the inflation of India have been identified, then an efficient artificial neural network (ANN model has been proposed to forecast the inflation. Accuracy of the model is proved to be satisfactory when compared with the forecasting of some well-known agencies.

  13. Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network

    Directory of Open Access Journals (Sweden)

    Lukas Falat

    2016-01-01

    Full Text Available This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.

  14. Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network.

    Science.gov (United States)

    Falat, Lukas; Marcek, Dusan; Durisova, Maria

    2016-01-01

    This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.

  15. Short term forecasting for HFSWR sea surface current mapping using artificial neural network

    Science.gov (United States)

    Lai, J. W.; Lu, Y. C.; Hsieh, C. M.; Liau, J. M.; Yang, W. C.

    2016-02-01

    Taiwan Ocean Research Institute (TORI) established the Taiwan Ocean Radar Observing System (TOROS) based on the CODAR high frequency surface wave radar (HFSWR). The TOROS is the first network having complete, contiguous HFSWR coverage of nation's coastline in the world. This network consisting of 17 SeaSonde radars offers coverage across approximately 190,000 square kilometers an area, over five times the size of Taiwan's entire land mass. In the southernmost and narrowest part of Taiwan, two 13 MHz and one 24 MHz radars were established along the NanWan Bay since June, 2014. NanWan Bay, the southern tip of Taiwan, is a southward semi-enclosed basin bounded by two capes and is open to the Luzon Strait. The distance between the two caps is around 12 km, and the distance from the northernmost point of the bay to the caps are 5 and 11 km, respectively. Strong tidal currents dominate the ocean circulation in the NanWan Bay and induce obvious upwelling of cold water that intrudes on to the shallow regions of NanWan Bay around spring tides. From late fall to early spring, the seaward wind dominated by the northeast monsoon often destratifies the water column and decreases the sea surface temperature inside the Bay (Lee et al, 1997). Furthermore, the Nanwan Bay is famous with well-developed fringing reefs distributed along the shoreline. In this area, 230 species of scleractinian corals, nine species of non-scleractinian reef-building corals, and 40 species of alcyonacean corals have been recorded (Dai, 1991). NanWan, in the shape of a beautiful arch, attracts large crowds of people to take all kinds of beach or water activities every summer. In order to improve the applicability of HFSWR ocean surface current data on search and rescue issue and evaluation of coral spawn dispersal, a short term forecasting model using artificial neural network (ANN) was developed in this study. That ocean surface current vectors obtained from tidal theory are added as inputs in artificial

  16. Integration of Behind-the-Meter PV Fleet Forecasts into Utility Grid System Operations

    Energy Technology Data Exchange (ETDEWEB)

    Hoff, Thomas Hoff [Clean Power Research, L.L.C., Napa, CA (United States); Kankiewicz, Adam [Clean Power Research, L.L.C., Napa, CA (United States)

    2016-02-26

    Four major research objectives were completed over the course of this study. Three of the objectives were to evaluate three, new, state-of-the-art solar irradiance forecasting models. The fourth objective was to improve the California Independent System Operator’s (ISO) load forecasts by integrating behind-the-meter (BTM) PV forecasts. The three, new, state-of-the-art solar irradiance forecasting models included: the infrared (IR) satellite-based cloud motion vector (CMV) model; the WRF-SolarCA model and variants; and the Optimized Deep Machine Learning (ODML)-training model. The first two forecasting models targeted known weaknesses in current operational solar forecasts. They were benchmarked against existing operational numerical weather prediction (NWP) forecasts, visible satellite CMV forecasts, and measured PV plant power production. IR CMV, WRF-SolarCA, and ODML-training forecasting models all improved the forecast to a significant degree. Improvements varied depending on time of day, cloudiness index, and geographic location. The fourth objective was to demonstrate that the California ISO’s load forecasts could be improved by integrating BTM PV forecasts. This objective represented the project’s most exciting and applicable gains. Operational BTM forecasts consisting of 200,000+ individual rooftop PV forecasts were delivered into the California ISO’s real-time automated load forecasting (ALFS) environment. They were then evaluated side-by-side with operational load forecasts with no BTM-treatment. Overall, ALFS-BTM day-ahead (DA) forecasts performed better than baseline ALFS forecasts when compared to actual load data. Specifically, ALFS-BTM DA forecasts were observed to have the largest reduction of error during the afternoon on cloudy days. Shorter term 30 minute-ahead ALFS-BTM forecasts were shown to have less error under all sky conditions, especially during the morning time periods when traditional load forecasts often experience their largest

  17. Real-time drought forecasting system for irrigation managment

    Science.gov (United States)

    Ceppi, Alessandro; Ravazzani, Giovanni; Corbari, Chiara; Masseroni, Daniele; Meucci, Stefania; Pala, Francesca; Salerno, Raffaele; Meazza, Giuseppe; Chiesa, Marco; Mancini, Marco

    2013-04-01

    In recent years frequent periods of water scarcity have enhanced the need to use water more carefully, even in in European areas traditionally rich of water such as the Po Valley. In dry periods, the problem of water shortage can be enhanced by conflictual use of water such as irrigation, industrial and power production (hydroelectric and thermoelectric). Further, over the last decade the social perspective on this issue is increasing due to climate change and global warming scenarios which come out from the last IPCC Report. The increased frequency of dry periods has stimulated the improvement of irrigation and water management. In this study we show the development and implementation of the real-time drought forecasting system Pre.G.I., an Italian acronym that stands for "Hydro-Meteorological forecast for irrigation management". The system is based on ensemble prediction at long range (30 days) with hydrological simulation of water balance to forecast the soil water content in every parcel over the Consorzio Muzza basin. The studied area covers 74,000 ha in the middle of the Po Valley, near the city of Lodi. The hydrological ensemble forecasts are based on 20 meteorological members of the non-hydrostatic WRF model with 30 days as lead-time, provided by Epson Meteo Centre, while the hydrological model used to generate the soil moisture and water table simulations is the rainfall-runoff distributed FEST-WB model, developed at Politecnico di Milano. The hydrological model was validated against measurements of latent heat flux and soil moisture acquired by an eddy-covariance station. Reliability of the forecasting system and its benefits was assessed on some cases-study occurred in the recent years.

  18. Solar Storm GIC Forecasting: Solar Shield Extension Development of the End-User Forecasting System Requirements

    Science.gov (United States)

    Pulkkinen, A.; Mahmood, S.; Ngwira, C.; Balch, C.; Lordan, R.; Fugate, D.; Jacobs, W.; Honkonen, I.

    2015-01-01

    A NASA Goddard Space Flight Center Heliophysics Science Division-led team that includes NOAA Space Weather Prediction Center, the Catholic University of America, Electric Power Research Institute (EPRI), and Electric Research and Management, Inc., recently partnered with the Department of Homeland Security (DHS) Science and Technology Directorate (S&T) to better understand the impact of Geomagnetically Induced Currents (GIC) on the electric power industry. This effort builds on a previous NASA-sponsored Applied Sciences Program for predicting GIC, known as Solar Shield. The focus of the new DHS S&T funded effort is to revise and extend the existing Solar Shield system to enhance its forecasting capability and provide tailored, timely, actionable information for electric utility decision makers. To enhance the forecasting capabilities of the new Solar Shield, a key undertaking is to extend the prediction system coverage across Contiguous United States (CONUS), as the previous version was only applicable to high latitudes. The team also leverages the latest enhancements in space weather modeling capacity residing at Community Coordinated Modeling Center to increase the Technological Readiness Level, or Applications Readiness Level of the system http://www.nasa.gov/sites/default/files/files/ExpandedARLDefinitions4813.pdf.

  19. Fast training of neural networks for load forecasting

    Energy Technology Data Exchange (ETDEWEB)

    Agosta, J.M.; Nielsen, N.R.; Andeen, G. [SRI International, Menlo Park, CA (United States)

    1996-10-01

    Predicting load demand (e.g., demand for electric power) in a data-rich environment is basically a regression problem. To be successful, however, any regression technique must take into account the nonlinear nature of the problem. Numerous nonlinear regression methods have become practical, with the availability of more powerful computers. Perhaps the best known of these methods are techniques that have been popularized under the name of neural networks, and the most common of these is the back-propagation neural network (BPNN). This paper explains the advantage of a different nonlinear regression method known as the probabilistic neural network (PNN).

  20. Forecasting of Congestion in Traffic Neural Network Modelling Using Duffing Holmes Oscillator

    Science.gov (United States)

    Mrgole, Anamarija L.; Čelan, Marko; Mesarec, Beno

    2017-10-01

    Forecasting of congestion in traffic with Neural Network is an innovative and new process of identification and detection of chaotic features in time series analysis. With the use of Duffing Holmes Oscillator, we estimate the emergence of traffic flow congestion when the traffic load on a specific section of the road and in a specific time period is close to exceeding the capacity of the road infrastructure. The orientated model is validated in six locations with a specific requirement. The paper points out the issue of importance of traffic flow forecasting and simulations for preventing or rerouting possible short term traffic flow congestions.

  1. Ensemble Nonlinear Autoregressive Exogenous Artificial Neural Networks for Short-Term Wind Speed and Power Forecasting.

    Science.gov (United States)

    Men, Zhongxian; Yee, Eugene; Lien, Fue-Sang; Yang, Zhiling; Liu, Yongqian

    2014-01-01

    Short-term wind speed and wind power forecasts (for a 72 h period) are obtained using a nonlinear autoregressive exogenous artificial neural network (ANN) methodology which incorporates either numerical weather prediction or high-resolution computational fluid dynamics wind field information as an exogenous input. An ensemble approach is used to combine the predictions from many candidate ANNs in order to provide improved forecasts for wind speed and power, along with the associated uncertainties in these forecasts. More specifically, the ensemble ANN is used to quantify the uncertainties arising from the network weight initialization and from the unknown structure of the ANN. All members forming the ensemble of neural networks were trained using an efficient particle swarm optimization algorithm. The results of the proposed methodology are validated using wind speed and wind power data obtained from an operational wind farm located in Northern China. The assessment demonstrates that this methodology for wind speed and power forecasting generally provides an improvement in predictive skills when compared to the practice of using an "optimal" weight vector from a single ANN while providing additional information in the form of prediction uncertainty bounds.

  2. Ensemble Nonlinear Autoregressive Exogenous Artificial Neural Networks for Short-Term Wind Speed and Power Forecasting

    Science.gov (United States)

    Lien, Fue-Sang; Yang, Zhiling; Liu, Yongqian

    2014-01-01

    Short-term wind speed and wind power forecasts (for a 72 h period) are obtained using a nonlinear autoregressive exogenous artificial neural network (ANN) methodology which incorporates either numerical weather prediction or high-resolution computational fluid dynamics wind field information as an exogenous input. An ensemble approach is used to combine the predictions from many candidate ANNs in order to provide improved forecasts for wind speed and power, along with the associated uncertainties in these forecasts. More specifically, the ensemble ANN is used to quantify the uncertainties arising from the network weight initialization and from the unknown structure of the ANN. All members forming the ensemble of neural networks were trained using an efficient particle swarm optimization algorithm. The results of the proposed methodology are validated using wind speed and wind power data obtained from an operational wind farm located in Northern China. The assessment demonstrates that this methodology for wind speed and power forecasting generally provides an improvement in predictive skills when compared to the practice of using an “optimal” weight vector from a single ANN while providing additional information in the form of prediction uncertainty bounds. PMID:27382627

  3. Analysis of recurrent neural networks for short-term energy load forecasting

    Science.gov (United States)

    Di Persio, Luca; Honchar, Oleksandr

    2017-11-01

    Short-term forecasts have recently gained an increasing attention because of the rise of competitive electricity markets. In fact, short-terms forecast of possible future loads turn out to be fundamental to build efficient energy management strategies as well as to avoid energy wastage. Such type of challenges are difficult to tackle both from a theoretical and applied point of view. Latter tasks require sophisticated methods to manage multidimensional time series related to stochastic phenomena which are often highly interconnected. In the present work we first review novel approaches to energy load forecasting based on recurrent neural network, focusing our attention on long/short term memory architectures (LSTMs). Such type of artificial neural networks have been widely applied to problems dealing with sequential data such it happens, e.g., in socio-economics settings, for text recognition purposes, concerning video signals, etc., always showing their effectiveness to model complex temporal data. Moreover, we consider different novel variations of basic LSTMs, such as sequence-to-sequence approach and bidirectional LSTMs, aiming at providing effective models for energy load data. Last but not least, we test all the described algorithms on real energy load data showing not only that deep recurrent networks can be successfully applied to energy load forecasting, but also that this approach can be extended to other problems based on time series prediction.

  4. Modeling Markov switching ARMA-GARCH neural networks models and an application to forecasting stock returns.

    Science.gov (United States)

    Bildirici, Melike; Ersin, Özgür

    2014-01-01

    The study has two aims. The first aim is to propose a family of nonlinear GARCH models that incorporate fractional integration and asymmetric power properties to MS-GARCH processes. The second purpose of the study is to augment the MS-GARCH type models with artificial neural networks to benefit from the universal approximation properties to achieve improved forecasting accuracy. Therefore, the proposed Markov-switching MS-ARMA-FIGARCH, APGARCH, and FIAPGARCH processes are further augmented with MLP, Recurrent NN, and Hybrid NN type neural networks. The MS-ARMA-GARCH family and MS-ARMA-GARCH-NN family are utilized for modeling the daily stock returns in an emerging market, the Istanbul Stock Index (ISE100). Forecast accuracy is evaluated in terms of MAE, MSE, and RMSE error criteria and Diebold-Mariano equal forecast accuracy tests. The results suggest that the fractionally integrated and asymmetric power counterparts of Gray's MS-GARCH model provided promising results, while the best results are obtained for their neural network based counterparts. Further, among the models analyzed, the models based on the Hybrid-MLP and Recurrent-NN, the MS-ARMA-FIAPGARCH-HybridMLP, and MS-ARMA-FIAPGARCH-RNN provided the best forecast performances over the baseline single regime GARCH models and further, over the Gray's MS-GARCH model. Therefore, the models are promising for various economic applications.

  5. Modeling Markov Switching ARMA-GARCH Neural Networks Models and an Application to Forecasting Stock Returns

    Directory of Open Access Journals (Sweden)

    Melike Bildirici

    2014-01-01

    Full Text Available The study has two aims. The first aim is to propose a family of nonlinear GARCH models that incorporate fractional integration and asymmetric power properties to MS-GARCH processes. The second purpose of the study is to augment the MS-GARCH type models with artificial neural networks to benefit from the universal approximation properties to achieve improved forecasting accuracy. Therefore, the proposed Markov-switching MS-ARMA-FIGARCH, APGARCH, and FIAPGARCH processes are further augmented with MLP, Recurrent NN, and Hybrid NN type neural networks. The MS-ARMA-GARCH family and MS-ARMA-GARCH-NN family are utilized for modeling the daily stock returns in an emerging market, the Istanbul Stock Index (ISE100. Forecast accuracy is evaluated in terms of MAE, MSE, and RMSE error criteria and Diebold-Mariano equal forecast accuracy tests. The results suggest that the fractionally integrated and asymmetric power counterparts of Gray’s MS-GARCH model provided promising results, while the best results are obtained for their neural network based counterparts. Further, among the models analyzed, the models based on the Hybrid-MLP and Recurrent-NN, the MS-ARMA-FIAPGARCH-HybridMLP, and MS-ARMA-FIAPGARCH-RNN provided the best forecast performances over the baseline single regime GARCH models and further, over the Gray’s MS-GARCH model. Therefore, the models are promising for various economic applications.

  6. DO DYNAMIC NEURAL NETWORKS STAND A BETTER CHANCE IN FRACTIONALLY INTEGRATED PROCESS FORECASTING?

    Directory of Open Access Journals (Sweden)

    Majid Delavari

    2013-04-01

    Full Text Available The main purpose of the present study was to investigate the capabilities of two generations of models such as those based on dynamic neural network (e.g., Nonlinear Neural network Auto Regressive or NNAR model and a regressive (Auto Regressive Fractionally Integrated Moving Average model which is based on Fractional Integration Approach in forecasting daily data related to the return index of Tehran Stock Exchange (TSE. In order to compare these models under similar conditions, Mean Square Error (MSE and also Root Mean Square Error (RMSE were selected as criteria for the models’ simulated out-of-sample forecasting performance. Besides, fractal markets hypothesis was examined and according to the findings, fractal structure was confirmed to exist in the time series under investigation. Another finding of the study was that dynamic artificial neural network model had the best performance in out-of-sample forecasting based on the criteria introduced for calculating forecasting error in comparison with the ARFIMA model.

  7. Development of KASI Geomagnetic Storm Forecast System using Coronagraph Data

    Science.gov (United States)

    Baek, Ji-Hye; Choi, SeongHwan; Park, Jongyeob; Kim, Roksoon; Kim, Sujin; Kim, Jihun

    2017-08-01

    We present Korea Astronomy and Space Science Institute (KASI) Geomagnetic Storm Forecast System. The aim of the system is to calculate the CME arrival time and predict the geoeffectiveness of the CME. To implement the system, we use the Large Angle and Spectrometric Coronagraph (LASCO) C2 and C3 data, the HMI magnetogram data of Solar Dynamics Observatory(SDO), and CACTUS CME list. The system consists of servers, which are to download, process, and publish data, data handling programs and web service. We apply an image differencing technique on LASCO data to determine speed and earthward direction parameters of CMEs. KASI Geomagnetic Storm Forecast Model has installed and being tested at Community Coordinated Modeling Center (CCMC) of NASA/GSFC. We expect that users can predict CME arrival time and geoeffectiveness of the CME easily and fast using the system. In order to improve the forecast performance of the system, we plan to incorporate advanced coronagraph data which will be developed and installed on ISS by KASI and NASA in collaboration.

  8. Comparisons of forecasting for hepatitis in Guangxi Province, China by using three neural networks models

    Directory of Open Access Journals (Sweden)

    Ruijing Gan

    2016-11-01

    Full Text Available This study compares and evaluates the prediction of hepatitis in Guangxi Province, China by using back propagation neural networks based genetic algorithm (BPNN-GA, generalized regression neural networks (GRNN, and wavelet neural networks (WNN. In order to compare the results of forecasting, the data obtained from 2004 to 2013 and 2014 were used as modeling and forecasting samples, respectively. The results show that when the small data set of hepatitis has seasonal fluctuation, the prediction result by BPNN-GA will be better than the two other methods. The WNN method is suitable for predicting the large data set of hepatitis that has seasonal fluctuation and the same for the GRNN method when the data increases steadily.

  9. Electric load forecasting for northern Vietnam, using an artificial neural network

    Energy Technology Data Exchange (ETDEWEB)

    Bhattacharyya, S.C. [Asian Institute of Technology, Pathum Thani (Thailand); Thanh, L.T. [Power Company No. 1 (Viet Nam)

    2003-06-01

    This paper employs a feed-forward neural network with a back-propagation algorithm for the short-term electric load forecasting of daily peak (valley) loads and hourly loads in the northern areas of Vietnam. A large set of data on peak loads, valley loads, hourly loads and temperatures was used to train and calibrate the artificial neural network (ANN). The calibrated network was used for load forecasting. The mean percentage errors for the peak load, valley load, one-hour-ahead hourly load and 24-hour-ahead hourly load were -1.47%, -3.29%, -2.64% and -4.39%, respectively. These results compare well with similar studies. (author)

  10. Short-Term Distribution System State Forecast Based on Optimal Synchrophasor Sensor Placement and Extreme Learning Machine

    Energy Technology Data Exchange (ETDEWEB)

    Jiang, Huaiguang; Zhang, Yingchen

    2016-11-14

    This paper proposes an approach for distribution system state forecasting, which aims to provide an accurate and high speed state forecasting with an optimal synchrophasor sensor placement (OSSP) based state estimator and an extreme learning machine (ELM) based forecaster. Specifically, considering the sensor installation cost and measurement error, an OSSP algorithm is proposed to reduce the number of synchrophasor sensor and keep the whole distribution system numerically and topologically observable. Then, the weighted least square (WLS) based system state estimator is used to produce the training data for the proposed forecaster. Traditionally, the artificial neural network (ANN) and support vector regression (SVR) are widely used in forecasting due to their nonlinear modeling capabilities. However, the ANN contains heavy computation load and the best parameters for SVR are difficult to obtain. In this paper, the ELM, which overcomes these drawbacks, is used to forecast the future system states with the historical system states. The proposed approach is effective and accurate based on the testing results.

  11. Near-Earth Radiation Environment: Operation Control and Forecast System at SINP MSU

    Science.gov (United States)

    Myagkova, Irina; Bobrovnikov, Sergey; Kalegaev, Vladimir; Barinova, Vera; Dolenko, Sergey; Shiroky, Vladimir

    Operational control and forecast of the Earth’s radiation environment is very topical both for solving fundamental scientific problems of solar-terrestrial physics, and for providing safety of space missions and polar aviation. Therefore, data of experiments onboard LEO (low-altitudes polar) spacecraft are very important. Now, a lot of data of experiments are available, including measurements of LEO spacecraft like "Meteor-M No. 1" and POES NOAA series. In the nearest future, new Russian satellites RELEC and "Lomonosov" will be launched to LEO orbit. However, data transmitted from LEO spacecraft has specific character connected with the features of LEO orbit: a spacecraft consistently passes different areas of near-Earth space - polar caps, area of outer Earth’s radiations Belts (ERB), middle latitudes, inner ERB. No public systems intended for analysis of radiation conditions at low altitudes, which could allow quick comparison of data obtained in L1 point with those from LEO and GEO, were created until now. The other important problem is forecasting of the near-Earth radiation environment state which is of key importance for space weather. The described problems are solved by the operational system of monitoring and forecasting of the radiation state of near-Earth environment, created at SINP MSU. The system of short-term (one hour ahead) forecasting of solar energetic particles (SEP) and relativistic electron fluxes at GEO operates on the base of artificial neural networks. The system also predicts the extreme location of SEP penetration boundary in the Earth’s magnetosphere at low altitudes and the high latitude boundary of outer ERB. Both predicted locations depend on Dst and Kp values, which, in turn, are predicted one hour ahead by artificial neural networks. The system operates in the framework of Space monitoring data center of the Moscow State University - http://swx.sinp.msu.ru/radiastatus/currentStatus.php.

  12. Final Report on California Regional Wind Energy Forecasting Project:Application of NARAC Wind Prediction System

    Energy Technology Data Exchange (ETDEWEB)

    Chin, H S

    2005-07-26

    Wind power is the fastest growing renewable energy technology and electric power source (AWEA, 2004a). This renewable energy has demonstrated its readiness to become a more significant contributor to the electricity supply in the western U.S. and help ease the power shortage (AWEA, 2000). The practical exercise of this alternative energy supply also showed its function in stabilizing electricity prices and reducing the emissions of pollution and greenhouse gases from other natural gas-fired power plants. According to the U.S. Department of Energy (DOE), the world's winds could theoretically supply the equivalent of 5800 quadrillion BTUs of energy each year, which is 15 times current world energy demand (AWEA, 2004b). Archer and Jacobson (2005) also reported an estimation of the global wind energy potential with the magnitude near half of DOE's quote. Wind energy has been widely used in Europe; it currently supplies 20% and 6% of Denmark's and Germany's electric power, respectively, while less than 1% of U.S. electricity is generated from wind (AWEA, 2004a). The production of wind energy in California ({approx}1.2% of total power) is slightly higher than the national average (CEC & EPRI, 2003). With the recently enacted Renewable Portfolio Standards calling for 20% of renewables in California's power generation mix by 2010, the growth of wind energy would become an important resource on the electricity network. Based on recent wind energy research (Roulston et al., 2003), accurate weather forecasting has been recognized as an important factor to further improve the wind energy forecast for effective power management. To this end, UC-Davis (UCD) and LLNL proposed a joint effort through the use of UCD's wind tunnel facility and LLNL's real-time weather forecasting capability to develop an improved regional wind energy forecasting system. The current effort of UC-Davis is aimed at developing a database of wind turbine power curves as

  13. Short-term solar forecasting based on sky images to enable higher PV generation in remote electricity networks

    Directory of Open Access Journals (Sweden)

    Schmidt Thomas

    2017-01-01

    Full Text Available The integration of a high share of photovoltaic (PV power generation in remote electricity networks is often limited by the networks’ capabilities to accommodate PV power fluctuations caused by passing clouds. Increasing the share of PV penetration in such networks is accompanied by an increased effort to achieve integration. In the absence of solar forecasting, sufficient spinning reserve must always be provided to cover unforeseen reductions. The expected ramp rates are magnified in small and centralised PV systems and can be in the order of a few seconds. In this study, we investigate the use of a low-cost sky camera for very short-term solar forecasting. Almost 2 months of sky camera data have been recorded in Perth, Western Australia and processed for to provide high-resolution irradiance forecasts based on visible sky images. For performance validation, the capability to provide reliable forecasts under constant clear sky conditions is investigated. During these times, PV generation is expected to be high and reliable, which provides an opportunity to reduce the online spinning reserve often enabling power station operation with one less operating diesel generation. For networks with disconnected diesel generators, we assume that clouds that could reduce the PV generation output have to be predicted at least 2 min before their arrival to have enough time for a diesel generator to start and synchronize with the grid. Therefore, we define an irradiance threshold discriminating between the persistent state of constant clear sky (stays clear and the non-persistent state (cloud shading event based on a 2–5 min time horizon. In a binary evaluation, we achieve an overall accuracy of 97% correct forecasts and low 3% false alarms of cloud events indicating a high potential for fuel savings. Focusing on the rare (2% of the time but more critical non-persistent conditions, we found 8 out of 84 cloud events have not been predicted in advance

  14. A framework for improving a seasonal hydrological forecasting system using sensitivity analysis

    Science.gov (United States)

    Arnal, Louise; Pappenberger, Florian; Smith, Paul; Cloke, Hannah

    2017-04-01

    Seasonal streamflow forecasts are of great value for the socio-economic sector, for applications such as navigation, flood and drought mitigation and reservoir management for hydropower generation and water allocation to agriculture and drinking water. However, as we speak, the performance of dynamical seasonal hydrological forecasting systems (systems based on running seasonal meteorological forecasts through a hydrological model to produce seasonal hydrological forecasts) is still limited in space and time. In this context, the ESP (Ensemble Streamflow Prediction) remains an attractive forecasting method for seasonal streamflow forecasting as it relies on forcing a hydrological model (starting from the latest observed or simulated initial hydrological conditions) with historical meteorological observations. This makes it cheaper to run than a standard dynamical seasonal hydrological forecasting system, for which the seasonal meteorological forecasts will first have to be produced, while still producing skilful forecasts. There is thus the need to focus resources and time towards improvements in dynamical seasonal hydrological forecasting systems which will eventually lead to significant improvements in the skill of the streamflow forecasts generated. Sensitivity analyses are a powerful tool that can be used to disentangle the relative contributions of the two main sources of errors in seasonal streamflow forecasts, namely the initial hydrological conditions (IHC; e.g., soil moisture, snow cover, initial streamflow, among others) and the meteorological forcing (MF; i.e., seasonal meteorological forecasts of precipitation and temperature, input to the hydrological model). Sensitivity analyses are however most useful if they inform and change current operational practices. To this end, we propose a method to improve the design of a seasonal hydrological forecasting system. This method is based on sensitivity analyses, informing the forecasters as to which element of

  15. Towards an integrated forecasting system for pelagic fisheries

    DEFF Research Database (Denmark)

    Christensen, Asbjørn; Butenschön, Momme; Gürkan, Zeren

    trophic level, in this case the sandeel population, demonstrated here on the basis of hindcast data. The coupled forecasting system has been tested for some typical scientific questions appearing in spatial fish stock management and marine spatial planning, including determination of local‐and basin......First results of a coupled modelling and forecasting system for pelagic fisheries are presented. The system consists of three mathematically fundamentally different model subsystems: POLCOMSERSEM provides the physical–biogeochemical environment in the northwest European shelf, the Sandeel...... Population Analysis Model describes sandeel stocks in the North Sea, and the Sandeel Larval Analysis Model connects POLCOMS‐ERSEM and SPAM by computing the physical–biological interaction. Our main findings by coupling model subsystems is that well‐defined and generic model interfaces are very important...

  16. Towards an integrated forecasting system for pelagic fisheries

    DEFF Research Database (Denmark)

    Christensen, Asbjørn; Butenschön, Momme; Gürkan, Zeren

    2012-01-01

    trophic level, in this case the sandeel population, demonstrated here on the basis of hindcast data. The coupled forecasting system has been tested for some typical scientific questions appearing in spatial fish stock management and marine spatial planning, including determination of local‐and basin......First results of a coupled modelling and forecasting system for pelagic fisheries are presented. The system consists of three mathematically fundamentally different model subsystems: POLCOMSERSEM provides the physical–biogeochemical environment in the northwest European shelf, the Sandeel...... Population Analysis Model describes sandeel stocks in the North Sea, and the Sandeel Larval Analysis Model connects POLCOMS‐ERSEM and SPAM by computing the physical–biological interaction. Our main findings by coupling model subsystems is that well‐defined and generic model interfaces are very important...

  17. A Two-Dimensional Gridded Solar Forecasting System using Situation-Dependent Blending of Multiple Weather Models

    Science.gov (United States)

    Lu, S.; Hwang, Y.; Shao, X.; Hamann, H.

    2015-12-01

    Previously, we reported the application of a "weather situation" dependent multi-model blending approach to improve the forecast accuracy of solar irradiance and other atmospheric parameters. The approach uses machine-learning techniques to classify "weather situations" by a set of atmospheric parameters. The "weather situation" classification is location-dependent and each "weather situation" has characteristic forecast errors from a set of individual input numerical weather prediction (NWP) models. The input models are thus corrected or combined differently for different "weather situations" to minimize the overall forecast error. While the original implementation of the model-blending is applicable to only point-like locations having historical data of both measurements and forecasts, here we extend the approach to provide two-dimensional (2D) gridded forecasts. An experimental 2D forecasting system has been set up to provide gridded forecasts of solar irradiance (global horizontal irradiance), temperature, wind speed, and humidity for the contiguous United States (CONUS). Validation results show around 30% enhancement of 0 to 48 hour ahead solar irradiance forecast accuracy compared to the best input NWP model. The forecasting system may be leveraged by other site- or region-specific solar energy forecast products. To enable the 2D forecasting system, historical solar irradiance measurements from around 1,600 selected sites of the remote automated weather stations (RAWS) network have been employed. The CONUS was divided into smaller sub-regions, each containing a group of 10 to 20 RAWS sites. A group of sites, as classified by statistical analysis, have similar "weather patterns", i.e. the NWPs have similar "weather situation" dependent forecast errors for all sites in a group. The model-blending trained by the historical data from a group of sites is then applied for all locations in the corresponding sub-region. We discuss some key techniques developed for

  18. A System for Continuous Hydrological Ensemble Forecasting (SCHEF) to lead times of 9 days

    Science.gov (United States)

    Bennett, James C.; Robertson, David E.; Shrestha, Durga Lal; Wang, Q. J.; Enever, David; Hapuarachchi, Prasantha; Tuteja, Narendra K.

    2014-11-01

    This study describes a System for Continuous Hydrological Ensemble Forecasting (SCHEF) designed to forecast streamflows to lead times of 9 days. SCHEF is intended to support optimal management of water resources for consumptive and environmental purposes and ultimately to support the management of impending floods. Deterministic rainfall forecasts from the ACCESS-G numerical weather prediction (NWP) model are post-processed using a Bayesian joint probability model to correct biases and quantify uncertainty. Realistic temporal and spatial characteristics are instilled in the rainfall forecast ensemble with the Schaake shuffle. The ensemble rainfall forecasts are then used as inputs to the GR4H hydrological model to produce streamflow forecasts. A hydrological error correction is applied to ensure forecasts transit smoothly from recent streamflow observations. SCHEF forecasts streamflows skilfully for a range of hydrological and climate conditions. Skill is particularly evident in forecasts of streamflows at lead times of 1-6 days. Forecasts perform best in temperate perennially flowing rivers, while forecasts are poorest in intermittently flowing rivers. The poor streamflow forecasts in intermittent rivers are primarily the result of poor rainfall forecasts, rather than an inadequate representation of hydrological processes. Forecast uncertainty becomes more reliably quantified at longer lead times; however there is considerable scope for improving the reliability of streamflow forecasts at all lead times. Additionally, we show that the choice of forecast time-step can influence forecast accuracy: forecasts generated at a 1-h time-step tend to be more accurate than at longer time-steps (e.g. 1-day). This is largely because at shorter time-steps the hydrological error correction is able to correct streamflow forecasts with more recent information, rather than the ability of GR4H to simulate hydrological processes better at shorter time-steps. SCHEF will form the

  19. Forecasting Hurricane Tracks Using a Complex Adaptive System

    National Research Council Canada - National Science Library

    Lear, Matthew R

    2005-01-01

    Forecast hurricane tracks using a multi-model ensemble that consists of linearly combining the individual model forecasts have greatly reduced the average forecast errors when compared to individual...

  20. A Complex Adaptive System Approach to Forecasting Hurricane Tracks

    National Research Council Canada - National Science Library

    Lear, Matthew R

    2005-01-01

    Forecast hurricane tracks using a multi-model ensemble that consists of linearly combining the individual model forecasts have greatly reduced the average forecast errors when compared to individual...

  1. Forecasting of Chinese Primary Energy Consumption in 2021 with GRU Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Bingchun Liu

    2017-09-01

    Full Text Available The forecasting of energy consumption in China is a key requirement for achieving national energy security and energy planning. In this study, multi-variable linear regression (MLR and support vector regression (SVR were utilized with a gated recurrent unit (GRU artificial neural network of Chinese energy to establish a forecasting model. The derived model was validated through four economic variables; the gross domestic product (GDP, population, imports, and exports. The performance of various forecasting models was assessed via MAPE and RMSE, and three scenarios were configured based on different sources of variable data. In predicting Chinese energy consumption from 2015 to 2021, results from the established GRU model of the highest predictive accuracy showed that Chinese energy consumption would be likely to fluctuate from 2954.04 Mtoe to 5618.67 Mtoe in 2021.

  2. Forecasting Construction Cost Index based on visibility graph: A network approach

    Science.gov (United States)

    Zhang, Rong; Ashuri, Baabak; Shyr, Yu; Deng, Yong

    2018-03-01

    Engineering News-Record (ENR), a professional magazine in the field of global construction engineering, publishes Construction Cost Index (CCI) every month. Cost estimators and contractors assess projects, arrange budgets and prepare bids by forecasting CCI. However, fluctuations and uncertainties of CCI cause irrational estimations now and then. This paper aims at achieving more accurate predictions of CCI based on a network approach in which time series is firstly converted into a visibility graph and future values are forecasted relied on link prediction. According to the experimental results, the proposed method shows satisfactory performance since the error measures are acceptable. Compared with other methods, the proposed method is easier to implement and is able to forecast CCI with less errors. It is convinced that the proposed method is efficient to provide considerably accurate CCI predictions, which will make contributions to the construction engineering by assisting individuals and organizations in reducing costs and making project schedules.

  3. Application of data-based mechanistic modelling for flood forecasting at multiple locations in the Eden catchment in the National Flood Forecasting System (England and Wales)

    NARCIS (Netherlands)

    Leedal, D.; Weerts, A.H.; Smith, P.J.; Beven, K.J.

    2013-01-01

    The Delft Flood Early Warning System provides a versatile framework for real-time flood forecasting. The UK Environment Agency has adopted the Delft framework to deliver its National Flood Forecasting System. The Delft system incorporates new flood forecasting models very easily using an "open

  4. Management of the ESA Tracking Network- Load Forecasts and Mission Interfaces

    Science.gov (United States)

    Dreihahn, H.; di Giulio, M.

    2012-08-01

    The European Space Agency is operating a network of tracking ground stations distributed all over the world called ESTRACK. These tracking stations provide the space to ground communications for ESA and external space missions and is operated from ESOC in Darmstadt. In the recent years ESOC has successfully developed and deployed the ESTRACK Management System (EMS). The EMS, or more specifically it’s planning and scheduling components are in charge of planning the times, when a certain tracking station is allocated to a space mission. Initially the EMS has been designed as an automated planning system with minimum user interaction. However, looking back number of lessons have been learned:• While automated planning is very valuable, the need for interaction and negotiation of planning results with users, i.e. space missions, has been underestimated.• Interoperability with external space mission and external network providers is already required at the stage of resource allocation planning. This has been addressed by [1].• The originally envisaged planning horizon of 2-3 weeks into the future was too short. Now, depending on the mission characteristic, ground station allocation planning is done routinely for a planning horizon of 1+ year.This paper will focus on the first and the last point of the lessons learned. We will present and discuss an approach for an interface of the ESTRACK Management System with space missions, which extends the currently implement machine to machine interface with a (web based) man to machine interface. The second aspect addressed in this paper is the so called ESTRACK Load Analysis. The capability of the EMS to automatically plan station allocation for long periods into the future enables ESTRACK load forecasts and conflict analysis at an early stage. These forecasts are essential to plan the evolution of ESTRACK and to facilitate the support of future missions. Furthermore it helps to identify resource bottlenecks which

  5. Seasonal rainfall prediction skill over South Africa: one- versus two-tiered forecasting systems

    CSIR Research Space (South Africa)

    Landman, WA

    2012-04-01

    Full Text Available Forecast performance by coupled ocean–atmosphere or one-tiered models predicting seasonal rainfall totals over South Africa is compared with forecasts produced by computationally less demanding two-tiered systems where prescribed sea surface...

  6. Optimal Power Flow for Distribution Systems under Uncertain Forecasts: Preprint

    Energy Technology Data Exchange (ETDEWEB)

    Dall' Anese, Emiliano; Baker, Kyri; Summers, Tyler

    2016-12-01

    The paper focuses on distribution systems featuring renewable energy sources and energy storage devices, and develops an optimal power flow (OPF) approach to optimize the system operation in spite of forecasting errors. The proposed method builds on a chance-constrained multi-period AC OPF formulation, where probabilistic constraints are utilized to enforce voltage regulation with a prescribed probability. To enable a computationally affordable solution approach, a convex reformulation of the OPF task is obtained by resorting to i) pertinent linear approximations of the power flow equations, and ii) convex approximations of the chance constraints. Particularly, the approximate chance constraints provide conservative bounds that hold for arbitrary distributions of the forecasting errors. An adaptive optimization strategy is then obtained by embedding the proposed OPF task into a model predictive control framework.

  7. Optimal Power Flow for Distribution Systems under Uncertain Forecasts

    Energy Technology Data Exchange (ETDEWEB)

    Dall' Anese, Emiliano; Baker, Kyri; Summers, Tyler

    2016-12-29

    The paper focuses on distribution systems featuring renewable energy sources and energy storage devices, and develops an optimal power flow (OPF) approach to optimize the system operation in spite of forecasting errors. The proposed method builds on a chance-constrained multi-period AC OPF formulation, where probabilistic constraints are utilized to enforce voltage regulation with a prescribed probability. To enable a computationally affordable solution approach, a convex reformulation of the OPF task is obtained by resorting to i) pertinent linear approximations of the power flow equations, and ii) convex approximations of the chance constraints. Particularly, the approximate chance constraints provide conservative bounds that hold for arbitrary distributions of the forecasting errors. An adaptive optimization strategy is then obtained by embedding the proposed OPF task into a model predictive control framework.

  8. Triangulation positioning system network

    Directory of Open Access Journals (Sweden)

    Sfendourakis Marios

    2017-01-01

    Full Text Available This paper presents ongoing work on localization and positioning through triangulation procedure for a Fixed Sensors Network - FSN.The FSN has to work as a system.As the triangulation problem becomes high complicated in a case with large numbers of sensors and transmitters, an adequate grid topology is needed in order to tackle the detection complexity.For that reason a Network grid topology is presented and areas that are problematic and need further analysis are analyzed.The Network System in order to deal with problems of saturation and False Triangulations - FTRNs will have to find adequate methods in every sub-area of the Area Of Interest - AOI.Also, concepts like Sensor blindness and overall Network blindness, are presented. All these concepts affect the Network detection rate and its performance and ought to be considered in a way that the network overall performance won’t be degraded.Network performance should be monitored contentiously, with right algorithms and methods.It is also shown that as the number of TRNs and FTRNs is increased Detection Complexity - DC is increased.It is hoped that with further research all the characteristics of a triangulation system network for positioning will be gained and the system will be able to perform autonomously with a high detection rate.

  9. Multiplexed FBG Monitoring System for Forecasting Coalmine Water Inrush Disaster

    OpenAIRE

    Liu, B.; Li, S.C.; J. Wang; Q. M. Sui; Nie, L. C.; Z. F. Wang

    2012-01-01

    This paper presents a novel fiber-Bragg-grating- (FBG-) based system which can monitor and analyze multiple parameters such as temperature, strain, displacement, and seepage pressure simultaneously for forecasting coalmine water inrush disaster. The sensors have minimum perturbation on the strain field. And the seepage pressure sensors adopt a drawbar structure and employ a corrugated diaphragm to transmit seepage pressure to the axial strain of FBG. The pressure sensitivity is 20.20 pm/KPa, ...

  10. Time Series Forecasting Energy-efficient Organization of Wireless Sensor Networks

    Directory of Open Access Journals (Sweden)

    Dao-Wei Bi

    2007-09-01

    Full Text Available Due to their wide potential applications, wireless sensor networks have recentlyreceived tremendous attention. The strict energy constraints of sensor nodes result in thegreat challenges for energy efficiency. This paper investigates the energy efficiency problemand proposes an energy-efficient organization method with time series forecasting. Theorganization of wireless sensor networks is formulated for target tracking. Target model,multi-sensor model and energy model are defined accordingly. For the target trackingapplication, target localization is achieved by collaborative sensing with multi-sensor fusion.The historical localization results are utilized for adaptive target trajectory forecasting.Empirical mode decomposition is implemented to extract the inherent variation modes in thetime series of a target trajectory. Future target position is derived from autoregressivemoving average (ARMA models, which forecast the decomposition components,respectively. Moreover, the energy-efficient organization method is presented to enhance theenergy efficiency of wireless sensor networks. The sensor nodes implement sensing tasksaccording to the probability awakening in a distributed manner. When the sensor nodestransfer their observations to achieve data fusion, the routing scheme is obtained by antcolony optimization. Thus, both the operation and communication energy consumption canbe minimized. Experimental results verify that the combination of the ARMA model andempirical mode decomposition can estimate the target position efficiently and energy savingis achieved by the proposed organization method in wireless sensor networks.

  11. Explicitly integrating parameter, input, and structure uncertainties into Bayesian Neural Networks for probabilistic hydrologic forecasting

    KAUST Repository

    Zhang, Xuesong

    2011-11-01

    Estimating uncertainty of hydrologic forecasting is valuable to water resources and other relevant decision making processes. Recently, Bayesian Neural Networks (BNNs) have been proved powerful tools for quantifying uncertainty of streamflow forecasting. In this study, we propose a Markov Chain Monte Carlo (MCMC) framework (BNN-PIS) to incorporate the uncertainties associated with parameters, inputs, and structures into BNNs. This framework allows the structure of the neural networks to change by removing or adding connections between neurons and enables scaling of input data by using rainfall multipliers. The results show that the new BNNs outperform BNNs that only consider uncertainties associated with parameters and model structures. Critical evaluation of posterior distribution of neural network weights, number of effective connections, rainfall multipliers, and hyper-parameters shows that the assumptions held in our BNNs are not well supported. Further understanding of characteristics of and interactions among different uncertainty sources is expected to enhance the application of neural networks for uncertainty analysis of hydrologic forecasting. © 2011 Elsevier B.V.

  12. Forecasting the portuguese stock market time series by using artificial neural networks

    Science.gov (United States)

    Isfan, Monica; Menezes, Rui; Mendes, Diana A.

    2010-04-01

    In this paper, we show that neural networks can be used to uncover the non-linearity that exists in the financial data. First, we follow a traditional approach by analysing the deterministic/stochastic characteristics of the Portuguese stock market data and some typical features are studied, like the Hurst exponents, among others. We also simulate a BDS test to investigate nonlinearities and the results are as expected: the financial time series do not exhibit linear dependence. Secondly, we trained four types of neural networks for the stock markets and used the models to make forecasts. The artificial neural networks were obtained using a three-layer feed-forward topology and the back-propagation learning algorithm. The quite large number of parameters that must be selected to develop a neural network forecasting model involves some trial and as a consequence the error is not small enough. In order to improve this we use a nonlinear optimization algorithm to minimize the error. Finally, the output of the 4 models is quite similar, leading to a qualitative forecast that we compare with the results of the application of k-nearest-neighbor for the same time series.

  13. A study on the forecasting of daily stream flow using the multilayer neural networks model

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Sung-Won [Colorado State University, Fort Collins, CO(United States)

    2000-10-31

    In this study, Neural Networks models were used to forecast daily stream flow at Jindong station of the Nakdong River basin. Neural Networks models consist of CASE 1(5-5-1) and CASE 2(5-5-5-1). The criteria which separates two models is the number of hidden layers. Each model has Fletcher-Reeves Conjugate Gradient BackPropagation(FR-CGBP) and Scaled Conjugate Gradient BackPropagation(SCGBP) algorithms, which are better than original BackPropagation(BP) in convergence of global error and training tolerance. The data which are available for model training and validation were composed of wet, average, dry, wet+average, wet+dry, average+dry and wet+average+dry year respectively. During model training, the optimal connection weights and biases were determined using each data set and the daily stream flow was calculated at the same time. Except for wet+dry year, the results of training were good conditions by statistical analysis of forecast errors. And, model validation was carried out using the connection weights and biases which were calculated from model training. The results of validation were satisfactory like those of training. Daily stream flow forecasting using Neural Networks models were compared with those forecasted by Multiple Regression Analysis Model(MRAM). Neural Networks models were displayed slightly better results than MRAM in this study. Thus, Neural Networks models have much advantage to provide a more systematic approach, reduce model parameters, and shorten the time spent in the model development. (author). 22 refs., 9 tabs., 7 figs.

  14. Global crop production forecasting data system analysis

    Science.gov (United States)

    Castruccio, P. A. (Principal Investigator); Loats, H. L.; Lloyd, D. G.

    1978-01-01

    The author has identified the following significant results. Findings led to the development of a theory of radiometric discrimination employing the mathematical framework of the theory of discrimination between scintillating radar targets. The theory indicated that the functions which drive accuracy of discrimination are the contrast ratio between targets, and the number of samples, or pixels, observed. Theoretical results led to three primary consequences, as regards the data system: (1) agricultural targets must be imaged at correctly chosen times, when the relative evolution of the crop's development is such as to maximize their contrast; (2) under these favorable conditions, the number of observed pixels can be significantly reduced with respect to wall-to-wall measurements; and (3) remotely sensed radiometric data must be suitably mixed with other auxiliary data, derived from external sources.

  15. Maintaining a Local Data Integration System in Support of Weather Forecast Operations

    Science.gov (United States)

    Watson, Leela R.; Blottman, Peter F.; Sharp, David W.; Hoeth, Brian

    2010-01-01

    /Meteorological Assimilation Data Ingest System (MADIS), as well as the Kennedy Space Center ICape Canaveral Air Force Station wind tower network. The scripts provide NWS MLB and SMG with several options for setting a desirable runtime configuration of the LDIS to account for adjustments in grid spacing, domain location, choice of observational data sources, and selection of background model fields, among others. The utility of an improved LDIS will be demonstrated through postanalysis warm and cool season case studies that compare high-resolution model output with and without the ADAS analyses. Operationally, these upgrades will result in more accurate depictions of the current local environment to help with short-range weather forecasting applications, while also offering an improved initialization for local versions of the Weather Research and Forecasting model.

  16. Comparing the Selected Transfer Functions and Local Optimization Methods for Neural Network Flood Runoff Forecast

    Directory of Open Access Journals (Sweden)

    Petr Maca

    2014-01-01

    Full Text Available The presented paper aims to analyze the influence of the selection of transfer function and training algorithms on neural network flood runoff forecast. Nine of the most significant flood events, caused by the extreme rainfall, were selected from 10 years of measurement on small headwater catchment in the Czech Republic, and flood runoff forecast was investigated using the extensive set of multilayer perceptrons with one hidden layer of neurons. The analyzed artificial neural network models with 11 different activation functions in hidden layer were trained using 7 local optimization algorithms. The results show that the Levenberg-Marquardt algorithm was superior compared to the remaining tested local optimization methods. When comparing the 11 nonlinear transfer functions, used in hidden layer neurons, the RootSig function was superior compared to the rest of analyzed activation functions.

  17. Neural networks and forecasting stock price movements-accounting approach: Empirical evidence from Iran

    Directory of Open Access Journals (Sweden)

    Hossein Naderi

    2012-08-01

    Full Text Available Stock market prediction is one of the most important interesting areas of research in business. Stock markets prediction is normally assumed as tedious task since there are many factors influencing the market. The primary objective of this paper is to forecast trend closing price movement of Tehran Stock Exchange (TSE using financial accounting ratios from year 2003 to year 2008. The proposed study of this paper uses two approaches namely Artificial Neural Networks and multi-layer perceptron. Independent variables are accounting ratios and dependent variable of stock price , so the latter was gathered for the industry of Motor Vehicles and Auto Parts. The results of this study show that neural networks models are useful tools in forecasting stock price movements in emerging markets but multi-layer perception provides better results in term of lowering error terms.

  18. Meteor Shower Forecast Improvements from a Survey of All-Sky Network Observations

    Science.gov (United States)

    Moorhead, Althea V.; Sugar, Glenn; Brown, Peter G.; Cooke, William J.

    2015-01-01

    Meteoroid impacts are capable of damaging spacecraft and potentially ending missions. In order to help spacecraft programs mitigate these risks, NASA's Meteoroid Environment Office (MEO) monitors and predicts meteoroid activity. Temporal variations in near-Earth space are described by the MEO's annual meteor shower forecast, which is based on both past shower activity and model predictions. The MEO and the University of Western Ontario operate sister networks of all-sky meteor cameras. These networks have been in operation for more than 7 years and have computed more than 20,000 meteor orbits. Using these data, we conduct a survey of meteor shower activity in the "fireball" size regime using DBSCAN. For each shower detected in our survey, we compute the date of peak activity and characterize the growth and decay of the shower's activity before and after the peak. These parameters are then incorporated into the annual forecast for an improved treatment of annual activity.

  19. Volatility Degree Forecasting of Stock Market by Stochastic Time Strength Neural Network

    Directory of Open Access Journals (Sweden)

    Haiyan Mo

    2013-01-01

    Full Text Available In view of the applications of artificial neural networks in economic and financial forecasting, a stochastic time strength function is introduced in the backpropagation neural network model to predict the fluctuations of stock price changes. In this model, stochastic time strength function gives a weight for each historical datum and makes the model have the effect of random movement, and then we investigate and forecast the behavior of volatility degrees of returns for the Chinese stock market indexes and some global market indexes. The empirical research is performed in testing the prediction effect of SSE, SZSE, HSI, DJIA, IXIC, and S&P 500 with different selected volatility degrees in the established model.

  20. Anvil Forecast Tool in the Advanced Weather Interactive Processing System

    Science.gov (United States)

    Barrett, Joe H., III; Hood, Doris

    2009-01-01

    Meteorologists from the 45th Weather Squadron (45 WS) and National Weather Service Spaceflight Meteorology Group (SMG) have identified anvil forecasting as one of their most challenging tasks when predicting the probability of violations of the Lightning Launch Commit Criteria and Space Shuttle Flight Rules. As a result, the Applied Meteorology Unit (AMU) was tasked to create a graphical overlay tool for the Meteorological Interactive Data Display System (MIDDS) that indicates the threat of thunderstorm anvil clouds, using either observed or model forecast winds as input. The tool creates a graphic depicting the potential location of thunderstorm anvils one, two, and three hours into the future. The locations are based on the average of the upper level observed or forecasted winds. The graphic includes 10 and 20 n mi standoff circles centered at the location of interest, as well as one-, two-, and three-hour arcs in the upwind direction. The arcs extend outward across a 30 sector width based on a previous AMU study that determined thunderstorm anvils move in a direction plus or minus 15 of the upper-level wind direction. The AMU was then tasked to transition the tool to the Advanced Weather Interactive Processing System (AWIPS). SMG later requested the tool be updated to provide more flexibility and quicker access to model data. This presentation describes the work performed by the AMU to transition the tool into AWIPS, as well as the subsequent improvements made to the tool.

  1. Artificial neural networks in forecasting tourists’ flow, an intelligent technique to help the economic development of tourism in Albania.

    Directory of Open Access Journals (Sweden)

    Dezdemona Gjylapi

    2014-07-01

    The aim of this paper is to present the neural network usage in the tourists’ number forecasting and to determine the trends of the future tourist inflow, thus helping tourism management agencies in making scientific based financial decisions.

  2. Forecasting the mixed-layer depth in the Northeast Atlantic: an ensemble approach, with uncertainties based on data from operational ocean forecasting systems

    OpenAIRE

    Drillet, Y.; J. M. Lellouche; B. Levier; Drévillon, M.; Galloudec, O.; Reffray, G.; Regnier, C.; Greiner, E.; Clavier, M.

    2014-01-01

    Operational systems operated by Mercator Ocean provide daily ocean forecasts, and combining these forecasts we can produce ensemble forecast and uncertainty estimates. This study focuses on the mixed-layer depth in the Northeast Atlantic near the Porcupine Abyssal Plain for May 2013. This period is of interest for several reasons: (1) four Mercator Ocean operational systems provide daily forecasts at a horizontal resolution of 1/4, 1/12 and 1/36° with different physics; (2) ...

  3. UD-WCMA: An Energy Estimation and Forecast Scheme for Solar Powered Wireless Sensor Networks

    KAUST Repository

    Dehwah, Ahmad H.

    2017-04-11

    Energy estimation and forecast represents an important role for energy management in solar-powered wireless sensor networks (WSNs). In general, the energy in such networks is managed over a finite time horizon in the future based on input solar power forecasts to enable continuous operation of the WSNs and achieve the sensing objectives while ensuring that no node runs out of energy. In this article, we propose a dynamic version of the weather conditioned moving average technique (UD-WCMA) to estimate and predict the variations of the solar power in a wireless sensor network. The presented approach combines the information from the real-time measurement data and a set of stored profiles representing the energy patterns in the WSNs location to update the prediction model. The UD-WCMA scheme is based on adaptive weighting parameters depending on the weather changes which makes it flexible compared to the existing estimation schemes without any precalibration. A performance analysis has been performed considering real irradiance profiles to assess the UD-WCMA prediction accuracy. Comparative numerical tests to standard forecasting schemes (EWMA, WCMA, and Pro-Energy) shows the outperformance of the new algorithm. The experimental validation has proven the interesting features of the UD-WCMA in real time low power sensor nodes.

  4. Application of Statistical, Fuzzy and Perceptron Neural Networks in Drought Forecasting (Case Study: Gonbad-e Kavous Station

    Directory of Open Access Journals (Sweden)

    S.M. Hosseini-Moghari

    2016-10-01

    Full Text Available Introduction: Due to economic, social, and environmental perplexities associated with drought, it is considered as one of the most complex natural hazards. To investigate the beginning along with analyzing the direct impacts of drought; the significance of drought monitoring must be highlighted. Regarding drought management and its consequences alleviation, drought forecasting must be taken into account (11. The current research employed multi-layer perceptron (MLP, adaptive neuro-fuzzy inference system (ANFIS, radial basis function (RBF and general regression neural network (GRNN. It is interesting to note that, there has not been any record of applying GRNN in drought forecasting. Materials and Methods: Throughout this paper, Standard Precipitation Index (SPI was the basis of drought forecasting. To do so, the precipitation data of Gonbad Kavous station during the period of 1972-73 to 2006-07 were used. To provide short-term, mid-term, and long-term drought analysis; SPI for 1, 3, 6, 9, 12, and 24 months was evaluated. SPI evaluation benefited from four statistical distributions, namely, Gamma, Normal, Log-normal, and Weibull along with Kolmogrov-Smirnov (K-S test. Later, to compare the capabilities of four utilized neural networks for drought forecasting; MLP, ANFIS, RBF, and GRNN were applied. MLP as a multi-layer network, which has a sigmoid activation function in hidden layer plus linear function in output layer, can be considered as a powerful regressive tool. ANFIS besides adaptive neuro networks, employed fuzzy logic. RBF, the foundation of radial basis networks, is a three-layer network with Gaussian function in its hidden layer, and a linear function in the output layer. GRNN is another type of RBF which is used for radial basis regressive problems. The performance criteria of the research were as follows: Correlation (R2, Root Mean Square Error (RMSE, Mean Absolute Error (MAE. Results Discussion: According to statistical distribution

  5. A multidisciplinary system for monitoring and forecasting Etna volcanic plumes

    Science.gov (United States)

    Coltelli, Mauro; Prestifilippo, Michele; Spata, Gaetano; Scollo, Simona; Andronico, Daniele

    2010-05-01

    One of the most active volcanoes in the world is Mt. Etna, in Italy, characterized by frequent explosive activity from the central craters and from fractures opened along the volcano flanks which, during the last years, caused several damages to aviation and forced the closure of the Catania International Airport. To give precise warning to the aviation authorities and air traffic controller and to assist the work of VAACs, a novel system for monitoring and forecasting Etna volcanic plumes, was developed at the Istituto Nazionale di Geofisica e Vulcanologia, sezione di Catania, the managing institution for the surveillance of Etna volcano. Monitoring is carried out using multispectral infrared measurements from the Spin Enhanced Visible and Infrared Imager (SEVIRI) on board the Meteosat Second Generation geosynchronous satellite able to track the volcanic plume with a high time resolution, visual and thermal cameras used to monitor the explosive activity, three continuous wave X-band disdrometers which detect ash dispersal and fallout, sounding balloons used to evaluate the atmospheric fields, and finally field data collected after the end of the eruptive event needed to extrapolate important features of explosive activity. Forecasting is carried out daily using automatic procedures which download weather forecast data obtained by meteorological mesoscale models from the Italian Air Force national Meteorological Office and from the hydrometeorological service of ARPA-SIM; run four different tephra dispersal models using input parameters obtained by the analysis of the deposits collected after few hours since the eruptive event similar to 22 July 1998, 21-24 July 2001 and 2002-03 Etna eruptions; plot hazard maps on ground and in air and finally publish them on a web-site dedicated to the Italian Civil Protection. The system has been already tested successfully during several explosive events occurring at Etna in 2006, 2007 and 2008. These events produced eruption

  6. Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs

    Directory of Open Access Journals (Sweden)

    Jaime Buitrago

    2017-01-01

    Full Text Available Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN with exogenous multi-variable input (NARX. The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. The New England electrical load data are used to train and validate the forecast prediction.

  7. Forecasting of UV-Vis absorbance time series using artificial neural networks combined with principal component analysis.

    Science.gov (United States)

    Plazas-Nossa, Leonardo; Hofer, Thomas; Gruber, Günter; Torres, Andres

    2017-02-01

    This work proposes a methodology for the forecasting of online water quality data provided by UV-Vis spectrometry. Therefore, a combination of principal component analysis (PCA) to reduce the dimensionality of a data set and artificial neural networks (ANNs) for forecasting purposes was used. The results obtained were compared with those obtained by using discrete Fourier transform (DFT). The proposed methodology was applied to four absorbance time series data sets composed by a total number of 5705 UV-Vis spectra. Absolute percentage errors obtained by applying the proposed PCA/ANN methodology vary between 10% and 13% for all four study sites. In general terms, the results obtained were hardly generalizable, as they appeared to be highly dependent on specific dynamics of the water system; however, some trends can be outlined. PCA/ANN methodology gives better results than PCA/DFT forecasting procedure by using a specific spectra range for the following conditions: (i) for Salitre wastewater treatment plant (WWTP) (first hour) and Graz West R05 (first 18 min), from the last part of UV range to all visible range; (ii) for Gibraltar pumping station (first 6 min) for all UV-Vis absorbance spectra; and (iii) for San Fernando WWTP (first 24 min) for all of UV range to middle part of visible range.

  8. INDIA’S ELECTRICITY DEMAND FORECAST USING REGRESSION ANALYSIS AND ARTIFICIAL NEURAL NETWORKS BASED ON PRINCIPAL COMPONENTS

    Directory of Open Access Journals (Sweden)

    S. Saravanan

    2012-07-01

    Full Text Available Power System planning starts with Electric load (demand forecasting. Accurate electricity load forecasting is one of the most important challenges in managing supply and demand of the electricity, since the electricity demand is volatile in nature; it cannot be stored and has to be consumed instantly. The aim of this study deals with electricity consumption in India, to forecast future projection of demand for a period of 19 years from 2012 to 2030. The eleven input variables used are Amount of CO2 emission, Population, Per capita GDP, Per capita gross national income, Gross Domestic savings, Industry, Consumer price index, Wholesale price index, Imports, Exports and Per capita power consumption. A new methodology based on Artificial Neural Networks (ANNs using principal components is also used. Data of 29 years used for training and data of 10 years used for testing the ANNs. Comparison made with multiple linear regression (based on original data and the principal components and ANNs with original data as input variables. The results show that the use of ANNs with principal components (PC is more effective.

  9. Network systems security analysis

    Science.gov (United States)

    Yilmaz, Ä.°smail

    2015-05-01

    Network Systems Security Analysis has utmost importance in today's world. Many companies, like banks which give priority to data management, test their own data security systems with "Penetration Tests" by time to time. In this context, companies must also test their own network/server systems and take precautions, as the data security draws attention. Based on this idea, the study cyber-attacks are researched throughoutly and Penetration Test technics are examined. With these information on, classification is made for the cyber-attacks and later network systems' security is tested systematically. After the testing period, all data is reported and filed for future reference. Consequently, it is found out that human beings are the weakest circle of the chain and simple mistakes may unintentionally cause huge problems. Thus, it is clear that some precautions must be taken to avoid such threats like updating the security software.

  10. Neural networks-based operational prototype for flash flood forecasting: application to Liane flash floods (France

    Directory of Open Access Journals (Sweden)

    Bertin Dominique

    2016-01-01

    Full Text Available The Liane River is a small costal river, famous for its floods, which can affect the city of Boulogne-sur-Mer. Due to the complexity of land cover and hydrologic processes, a black-box non-linear modelling was chosen using neural networks. The multilayer perceptron model, known for its property of universal approximation is thus chosen. Four models were designed, each one for one forecasting horizon using rainfall forecasts: 24h, 12h, 6h, 3h. The desired output of the model is original: it represents the maximal value of the water level respectively 24h, 12h, 6h, 3h ahead. Working with best forecasts of rain (the observed ones during the event in the past, on the major flood of the database in test set, the model provides excellent forecasts. Nash criteria calculated for the four lead times are 0.98 (3h, 0.97 (6h, 0.91 (12h, 0.89 (24h. Designed models were thus estimated as efficient enough to be implemented in a specific tool devoted to real time operational use. The software tool is described hereafter: designed in Java, it presents a friendly interface allowing applying various scenarios of future rainfalls, and a graphical visualization of the predicted maximum water levels and their associated real time observed values.

  11. A hybrid ARIMA and neural network model applied to forecast catch volumes of Selar crumenophthalmus

    Science.gov (United States)

    Aquino, Ronald L.; Alcantara, Nialle Loui Mar T.; Addawe, Rizavel C.

    2017-11-01

    The Selar crumenophthalmus with the English name big-eyed scad fish, locally known as matang-baka, is one of the fishes commonly caught along the waters of La Union, Philippines. The study deals with the forecasting of catch volumes of big-eyed scad fish for commercial consumption. The data used are quarterly caught volumes of big-eyed scad fish from 2002 to first quarter of 2017. This actual data is available from the open stat database published by the Philippine Statistics Authority (PSA)whose task is to collect, compiles, analyzes and publish information concerning different aspects of the Philippine setting. Autoregressive Integrated Moving Average (ARIMA) models, Artificial Neural Network (ANN) model and the Hybrid model consisting of ARIMA and ANN were developed to forecast catch volumes of big-eyed scad fish. Statistical errors such as Mean Absolute Errors (MAE) and Root Mean Square Errors (RMSE) were computed and compared to choose the most suitable model for forecasting the catch volume for the next few quarters. A comparison of the results of each model and corresponding statistical errors reveals that the hybrid model, ARIMA-ANN (2,1,2)(6:3:1), is the most suitable model to forecast the catch volumes of the big-eyed scad fish for the next few quarters.

  12. Long-range forecast of all India summer monsoon rainfall using adaptive neuro-fuzzy inference system: skill comparison with CFSv2 model simulation and real-time forecast for the year 2015

    Science.gov (United States)

    Chaudhuri, S.; Das, D.; Goswami, S.; Das, S. K.

    2016-11-01

    All India summer monsoon rainfall (AISMR) characteristics play a vital role for the policy planning and national economy of the country. In view of the significant impact of monsoon system on regional as well as global climate systems, accurate prediction of summer monsoon rainfall has become a challenge. The objective of this study is to develop an adaptive neuro-fuzzy inference system (ANFIS) for long range forecast of AISMR. The NCEP/NCAR reanalysis data of temperature, zonal and meridional wind at different pressure levels have been taken to construct the input matrix of ANFIS. The membership of the input parameters for AISMR as high, medium or low is estimated with trapezoidal membership function. The fuzzified standardized input parameters and the de-fuzzified target output are trained with artificial neural network models. The forecast of AISMR with ANFIS is compared with non-hybrid multi-layer perceptron model (MLP), radial basis functions network (RBFN) and multiple linear regression (MLR) models. The forecast error analyses of the models reveal that ANFIS provides the best forecast of AISMR with minimum prediction error of 0.076, whereas the errors with MLP, RBFN and MLR models are 0.22, 0.18 and 0.73 respectively. During validation with observations, ANFIS shows its potency over the said comparative models. Performance of the ANFIS model is verified through different statistical skill scores, which also confirms the aptitude of ANFIS in forecasting AISMR. The forecast skill of ANFIS is also observed to be better than Climate Forecast System version 2. The real-time forecast with ANFIS shows possibility of deficit (65-75 cm) AISMR in the year 2015.

  13. AIRS Impact on the Analysis and Forecast Track of Tropical Cyclone Nargis in a Global Data Assimilation and Forecasting System

    Science.gov (United States)

    Reale, O.; Lau, W.K.; Susskind, J.; Brin, E.; Liu, E.; Riishojgaard, L. P.; Rosenburg, R.; Fuentes, M.

    2009-01-01

    Tropical cyclones in the northern Indian Ocean pose serious challenges to operational weather forecasting systems, partly due to their shorter lifespan and more erratic track, compared to those in the Atlantic and the Pacific. Moreover, the automated analyses of cyclones over the northern Indian Ocean, produced by operational global data assimilation systems (DASs), are generally of inferior quality than in other basins. In this work it is shown that the assimilation of Atmospheric Infrared Sounder (AIRS) temperature retrievals under partial cloudy conditions can significantly impact the representation of the cyclone Nargis (which caused devastating loss of life in Myanmar in May 2008) in a global DAS. Forecasts produced from these improved analyses by a global model produce substantially smaller track errors. The impact of the assimilation of clear-sky radiances on the same DAS and forecasting system is positive, but smaller than the one obtained by ingestion of AIRS retrievals, possibly due to poorer coverage.

  14. Resilient Sensor Networks with Spatiotemporal Interpolation of Missing Sensors: An Example of Space Weather Forecasting by Multiple Satellites.

    Science.gov (United States)

    Tokumitsu, Masahiro; Hasegawa, Keisuke; Ishida, Yoshiteru

    2016-04-15

    This paper attempts to construct a resilient sensor network model with an example of space weather forecasting. The proposed model is based on a dynamic relational network. Space weather forecasting is vital for a satellite operation because an operational team needs to make a decision for providing its satellite service. The proposed model is resilient to failures of sensors or missing data due to the satellite operation. In the proposed model, the missing data of a sensor is interpolated by other sensors associated. This paper demonstrates two examples of space weather forecasting that involves the missing observations in some test cases. In these examples, the sensor network for space weather forecasting continues a diagnosis by replacing faulted sensors with virtual ones. The demonstrations showed that the proposed model is resilient against sensor failures due to suspension of hardware failures or technical reasons.

  15. The Experimental Regional Ensemble Forecast System (ExREF): Its Use in NWS Forecast Operations and Preliminary Verification

    Science.gov (United States)

    Reynolds, David; Rasch, William; Kozlowski, Daniel; Burks, Jason; Zavodsky, Bradley; Bernardet, Ligia; Jankov, Isidora; Albers, Steve

    2014-01-01

    The Experimental Regional Ensemble Forecast (ExREF) system is a tool for the development and testing of new Numerical Weather Prediction (NWP) methodologies. ExREF is run in near-realtime by the Global Systems Division (GSD) of the NOAA Earth System Research Laboratory (ESRL) and its products are made available through a website, an ftp site, and via the Unidata Local Data Manager (LDM). The ExREF domain covers most of North America and has 9-km horizontal grid spacing. The ensemble has eight members, all employing WRF-ARW. The ensemble uses a variety of initial conditions from LAPS and the Global Forecasting System (GFS) and multiple boundary conditions from the GFS ensemble. Additionally, a diversity of physical parameterizations is used to increase ensemble spread and to account for the uncertainty in forecasting extreme precipitation events. ExREF has been a component of the Hydrometeorology Testbed (HMT) NWP suite in the 2012-2013 and 2013-2014 winters. A smaller domain covering just the West Coast was created to minimize band-width consumption for the NWS. This smaller domain has and is being distributed to the National Weather Service (NWS) Weather Forecast Office and California Nevada River Forecast Center in Sacramento, California, where it is ingested into the Advanced Weather Interactive Processing System (AWIPS I and II) to provide guidance on the forecasting of extreme precipitation events. This paper will review the cooperative effort employed by NOAA ESRL, NASA SPoRT (Short-term Prediction Research and Transition Center), and the NWS to facilitate the ingest and display of ExREF data utilizing the AWIPS I and II D2D and GFE (Graphical Software Editor) software. Within GFE is a very useful verification software package called BoiVer that allows the NWS to utilize the River Forecast Center's 4 km gridded QPE to compare with all operational NWP models 6-hr QPF along with the ExREF mean 6-hr QPF so the forecasters can build confidence in the use of the

  16. Group on Earth Observations (GEO) Global Drought Monitor Portal: Adding Capabilities for Forecasting Hydrological Extremes and Early Warning Networking

    Science.gov (United States)

    Pozzi, W.; de Roo, A.; Vogt, J.; Lawford, R. G.; Pappenberger, F.; Heim, R. R.; Stefanski, R.

    2011-12-01

    for Africa (DEWFORA) to strengthen preparedness and adaptation; 3) setting up an Early Warning System network for drought ( to be developed through World Meteorological Organization WMO); and 4) adding global remote sensing drought monitoring capabilities (soil moisture anomalies). Flooding represents positive precipitation anomalies, whereas drought represents negative precipitation anomalies. The JRC combined Hydrologic Extremes platform will include multiple models and tools, such as; 1) JRC Global Flood Detection System and Global Flood Early Warning System; 2) the WMO Flash Flood Guidance system; 3) the Dartmouth Flood Observatory; 4) a suite of monitored and forecasted drought and water scarcity indicators through the various drought observatories accessible through the GEO Global Drought Monitor Portal. The GEO Global Drought and Flooding systems represent the "applications-side" of water activities within the GEO Work Plan and are supported by the "Research and Development (R&D) side" of water activities within the new 2012-2015 GEO Work Plan.

  17. The Establishment of an Operational Earthquake Forecasting System in Italy

    Science.gov (United States)

    Marzocchi, Warner; Lombardi, Anna Maria; Casarotti, Emanuele

    2014-05-01

    Just after the Mw 6.2 earthquake that hit L'Aquila, on April 6 2009, the Civil Protection nominated an International Commission on Earthquake Forecasting (ICEF) that paved the way to the development of the Operational Earthquake Forecasting (OEF), defined as the "procedures for gathering and disseminating authoritative information about the time dependence of seismic hazards to help communities prepare for potentially destructive earthquakes". In this paper we introduce the first official OEF system in Italy that has been developed by the new-born Centro di Pericolosità Sismica at the Istituto Nazionale di Geofisica e Vulcanologia. The system provides every day an update of the weekly probabilities of ground shaking over the whole Italian territory. In this presentation, we describe in detail the philosophy behind the system, the scientific details, and the output format that has been preliminary defined in agreement with Civil Protection. To our knowledge, this is the first operational system that fully satisfies the ICEF guidelines. Probably, the most sensitive issue is related to the communication of such a kind of message to the population. Acknowledging this inherent difficulty, in agreement with Civil Protection we are planning pilot tests to be carried out in few selected areas in Italy; the purpose of such tests is to check the effectiveness of the message and to receive feedbacks.

  18. Modeling and Computing of Stock Index Forecasting Based on Neural Network and Markov Chain

    Directory of Open Access Journals (Sweden)

    Yonghui Dai

    2014-01-01

    Full Text Available The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market.

  19. Global Ocean Forecast System 3.1 Validation Test

    Science.gov (United States)

    2017-05-04

    mission (Kurtz et al., 2013) collects airborne remote sensing measurements to bridge the gap between NASA’s Ice , Cloud and land Elevation Satellite...Forecast System (GOFS) 3.1 is comprised of the 1/12° HYbrid Coordinate Ocean Model that is two-way coupled to the Community Ice CodE in a daily update...structure, the surface mixed layer, the location of mesoscale features, and ice concentration, thickness and drift in both hemispheres. It is scheduled to

  20. A Hybrid Neural Network Model for Sales Forecasting Based on ARIMA and Search Popularity of Article Titles

    Directory of Open Access Journals (Sweden)

    Hani Omar

    2016-01-01

    Full Text Available Enhancing sales and operations planning through forecasting analysis and business intelligence is demanded in many industries and enterprises. Publishing industries usually pick attractive titles and headlines for their stories to increase sales, since popular article titles and headlines can attract readers to buy magazines. In this paper, information retrieval techniques are adopted to extract words from article titles. The popularity measures of article titles are then analyzed by using the search indexes obtained from Google search engine. Backpropagation Neural Networks (BPNNs have successfully been used to develop prediction models for sales forecasting. In this study, we propose a novel hybrid neural network model for sales forecasting based on the prediction result of time series forecasting and the popularity of article titles. The proposed model uses the historical sales data, popularity of article titles, and the prediction result of a time series, Autoregressive Integrated Moving Average (ARIMA forecasting method to learn a BPNN-based forecasting model. Our proposed forecasting model is experimentally evaluated by comparing with conventional sales prediction techniques. The experimental result shows that our proposed forecasting method outperforms conventional techniques which do not consider the popularity of title words.

  1. A Hybrid Neural Network Model for Sales Forecasting Based on ARIMA and Search Popularity of Article Titles.

    Science.gov (United States)

    Omar, Hani; Hoang, Van Hai; Liu, Duen-Ren

    2016-01-01

    Enhancing sales and operations planning through forecasting analysis and business intelligence is demanded in many industries and enterprises. Publishing industries usually pick attractive titles and headlines for their stories to increase sales, since popular article titles and headlines can attract readers to buy magazines. In this paper, information retrieval techniques are adopted to extract words from article titles. The popularity measures of article titles are then analyzed by using the search indexes obtained from Google search engine. Backpropagation Neural Networks (BPNNs) have successfully been used to develop prediction models for sales forecasting. In this study, we propose a novel hybrid neural network model for sales forecasting based on the prediction result of time series forecasting and the popularity of article titles. The proposed model uses the historical sales data, popularity of article titles, and the prediction result of a time series, Autoregressive Integrated Moving Average (ARIMA) forecasting method to learn a BPNN-based forecasting model. Our proposed forecasting model is experimentally evaluated by comparing with conventional sales prediction techniques. The experimental result shows that our proposed forecasting method outperforms conventional techniques which do not consider the popularity of title words.

  2. A Hybrid Neural Network Model for Sales Forecasting Based on ARIMA and Search Popularity of Article Titles

    Science.gov (United States)

    Omar, Hani; Hoang, Van Hai; Liu, Duen-Ren

    2016-01-01

    Enhancing sales and operations planning through forecasting analysis and business intelligence is demanded in many industries and enterprises. Publishing industries usually pick attractive titles and headlines for their stories to increase sales, since popular article titles and headlines can attract readers to buy magazines. In this paper, information retrieval techniques are adopted to extract words from article titles. The popularity measures of article titles are then analyzed by using the search indexes obtained from Google search engine. Backpropagation Neural Networks (BPNNs) have successfully been used to develop prediction models for sales forecasting. In this study, we propose a novel hybrid neural network model for sales forecasting based on the prediction result of time series forecasting and the popularity of article titles. The proposed model uses the historical sales data, popularity of article titles, and the prediction result of a time series, Autoregressive Integrated Moving Average (ARIMA) forecasting method to learn a BPNN-based forecasting model. Our proposed forecasting model is experimentally evaluated by comparing with conventional sales prediction techniques. The experimental result shows that our proposed forecasting method outperforms conventional techniques which do not consider the popularity of title words. PMID:27313605

  3. Recurrent Neural Network For Forecasting Time Series With Long Memory Pattern

    Science.gov (United States)

    Walid; Alamsyah

    2017-04-01

    Recurrent Neural Network as one of the hybrid models are often used to predict and estimate the issues related to electricity, can be used to describe the cause of the swelling of electrical load which experienced by PLN. In this research will be developed RNN forecasting procedures at the time series with long memory patterns. Considering the application is the national electrical load which of course has a different trend with the condition of the electrical load in any country. This research produces the algorithm of time series forecasting which has long memory pattern using E-RNN after this referred to the algorithm of integrated fractional recurrent neural networks (FIRNN).The prediction results of long memory time series using models Fractional Integrated Recurrent Neural Network (FIRNN) showed that the model with the selection of data difference in the range of [-1,1] and the model of Fractional Integrated Recurrent Neural Network (FIRNN) (24,6,1) provides the smallest MSE value, which is 0.00149684.

  4. A quality assessment of the MARS crop yield forecasting system for the European Union

    Science.gov (United States)

    van der Velde, Marijn; Bareuth, Bettina

    2015-04-01

    Timely information on crop production forecasts can become of increasing importance as commodity markets are more and more interconnected. Impacts across large crop production areas due to (e.g.) extreme weather and pest outbreaks can create ripple effects that may affect food prices and availability elsewhere. The MARS Unit (Monitoring Agricultural ResourceS), DG Joint Research Centre, European Commission, has been providing forecasts of European crop production levels since 1993. The operational crop production forecasting is carried out with the MARS Crop Yield Forecasting System (M-CYFS). The M-CYFS is used to monitor crop growth development, evaluate short-term effects of anomalous meteorological events, and provide monthly forecasts of crop yield at national and European Union level. The crop production forecasts are published in the so-called MARS bulletins. Forecasting crop yield over large areas in the operational context requires quality benchmarks. Here we present an analysis of the accuracy and skill of past crop yield forecasts of the main crops (e.g. soft wheat, grain maize), throughout the growing season, and specifically for the final forecast before harvest. Two simple benchmarks to assess the skill of the forecasts were defined as comparing the forecasts to 1) a forecast equal to the average yield and 2) a forecast using a linear trend established through the crop yield time-series. These reveal a variability in performance as a function of crop and Member State. In terms of production, the yield forecasts of 67% of the EU-28 soft wheat production and 80% of the EU-28 maize production have been forecast superior to both benchmarks during the 1993-2013 period. In a changing and increasingly variable climate crop yield forecasts can become increasingly valuable - provided they are used wisely. We end our presentation by discussing research activities that could contribute to this goal.

  5. A Hybrid Method Based on Singular Spectrum Analysis, Firefly Algorithm, and BP Neural Network for Short-Term Wind Speed Forecasting

    Directory of Open Access Journals (Sweden)

    Yuyang Gao

    2016-09-01

    Full Text Available With increasing importance being attached to big data mining, analysis, and forecasting in the field of wind energy, how to select an optimization model to improve the forecasting accuracy of the wind speed time series is not only an extremely challenging problem, but also a problem of concern for economic forecasting. The artificial intelligence model is widely used in forecasting and data processing, but the individual back-propagation artificial neural network cannot always satisfy the time series forecasting needs. Thus, a hybrid forecasting approach has been proposed in this study, which consists of data preprocessing, parameter optimization and a neural network for advancing the accuracy of short-term wind speed forecasting. According to the case study, in which the data are collected from Peng Lai, a city located in China, the simulation results indicate that the hybrid forecasting method yields better predictions compared to the individual BP, which indicates that the hybrid method exhibits stronger forecasting ability.

  6. A RBF neural network model with GARCH errors: Application to electricity price forecasting

    Energy Technology Data Exchange (ETDEWEB)

    Coelho, Leandro dos Santos [Industrial and Systems Engineering Graduate Program, PPGEPS, Pontifical Catholic University of Parana, Imaculada Conceicao, 1155, Zip code 80215-901, Curitiba, Parana (Brazil); Santos, Andre A.P. [Department of Statistics, Universidad Carlos III de Madrid, C/ Madrid, 126, 28903 Getafe, Madrid (Spain)

    2011-01-15

    In this article, we propose a nonlinear forecasting model based on radial basis function neural networks (RBF-NNs) with Gaussian activation functions and robust clustering algorithms to model the conditional mean and a parametric generalized autoregressive conditional heteroskedasticity (GARCH) specification to model the conditional volatility. Instead of calibrating the parameters of the RBF-NNs via numerical simulations, we propose an estimation procedure by which the number of basis functions, their corresponding widths and the parameters of the GARCH model are jointly estimated via maximum likelihood along with a genetic algorithm to maximize the likelihood function. We use this model to provide multi-step-ahead point and direction-of-change forecasts of the Spanish electricity pool prices. (author)

  7. ARTIFICIAL NEURAL NETWORK AND WAVELET DECOMPOSITION IN THE FORECAST OF GLOBAL HORIZONTAL SOLAR RADIATION

    Directory of Open Access Journals (Sweden)

    Luiz Albino Teixeira Júnior

    2015-04-01

    Full Text Available This paper proposes a method (denoted by WD-ANN that combines the Artificial Neural Networks (ANN and the Wavelet Decomposition (WD to generate short-term global horizontal solar radiation forecasting, which is an essential information for evaluating the electrical power generated from the conversion of solar energy into electrical energy. The WD-ANN method consists of two basic steps: firstly, it is performed the decomposition of level p of the time series of interest, generating p + 1 wavelet orthonormal components; secondly, the p + 1 wavelet orthonormal components (generated in the step 1 are inserted simultaneously into an ANN in order to generate short-term forecasting. The results showed that the proposed method (WD-ANN improved substantially the performance over the (traditional ANN method.

  8. Forecasting of PT. PLN (Persero) revenue using radial basis function neural network

    Science.gov (United States)

    Junior, Cindy Fajarianti; Suprijadi, Jadi; Franty, Yeny Krista

    2017-03-01

    PT. PLN (Persero) Distribusi Jakarta Raya (Disjaya) is a government-owned company that job is to maintain electricity distribution in Jakarta and Tangerang. The company's revenue can be seen from the pattern of the existing data, constantly increasing every year. This research aims to forecast company's revenue. The forecasting method using Artificial Neural Network method with Radial Basis Function (RBF) model based on historic data from January 2010 to December 2015. Based on the result of this research, the best model obtained (1-6-1) with composition 1 Neuron from input layer, 6 Neuron from hidden layer, and 1 Neuron output layer. The MAPE obtained with this model is 1.32 %.

  9. Short-Term Load Forecasting Using Adaptive Annealing Learning Algorithm Based Reinforcement Neural Network

    Directory of Open Access Journals (Sweden)

    Cheng-Ming Lee

    2016-11-01

    Full Text Available A reinforcement learning algorithm is proposed to improve the accuracy of short-term load forecasting (STLF in this article. The proposed model integrates radial basis function neural network (RBFNN, support vector regression (SVR, and adaptive annealing learning algorithm (AALA. In the proposed methodology, firstly, the initial structure of RBFNN is determined by using an SVR. Then, an AALA with time-varying learning rates is used to optimize the initial parameters of SVR-RBFNN (AALA-SVR-RBFNN. In order to overcome the stagnation for searching optimal RBFNN, a particle swarm optimization (PSO is applied to simultaneously find promising learning rates in AALA. Finally, the short-term load demands are predicted by using the optimal RBFNN. The performance of the proposed methodology is verified on the actual load dataset from the Taiwan Power Company (TPC. Simulation results reveal that the proposed AALA-SVR-RBFNN can achieve a better load forecasting precision compared to various RBFNNs.

  10. Advances in electric power and energy systems load and price forecasting

    CERN Document Server

    2017-01-01

    A comprehensive review of state-of-the-art approaches to power systems forecasting from the most respected names in the field, internationally. Advances in Electric Power and Energy Systems is the first book devoted exclusively to a subject of increasing urgency to power systems planning and operations. Written for practicing engineers, researchers, and post-grads concerned with power systems planning and forecasting, this book brings together contributions from many of the world’s foremost names in the field who address a range of critical issues, from forecasting power system load to power system pricing to post-storm service restoration times, river flow forecasting, and more. In a time of ever-increasing energy demands, mounting concerns over the environmental impacts of power generation, and the emergence of new, smart-grid technologies, electricity price forecasting has assumed a prominent role within both the academic and industrial ar nas. Short-run forecasting of electricity prices has become nece...

  11. Application of artificial neural network model for groundwater level forecasting in a river island with artificial influencing factors

    Science.gov (United States)

    Lee, Sanghoon; Yoon, Heesung; Park, Byeong-Hak; Lee, Kang-Kun

    2017-04-01

    Groundwater use has been increased for various purposes like agriculture, industry or drinking water in recent years, the issue related to sustainability on the groundwater use also has been raised. Accordingly, forecasting the groundwater level is of great importance for planning sustainable use of groundwater. In a small island surrounded by the Han River, South Korea, seasonal fluctuation of the groundwater level is characterized by multiple factors such as recharge/discharge event of the Paldang dam, Water Curtain Cultivation (WCC) during the winter season, operation of Groundwater Heat Pump System (GWHP). For a period when the dam operation is only occurred in the study area, a prediction of the groundwater level can be easily achieved by a simple cross-correlation model. However, for a period when the WCC and the GWHP systems are working together, the groundwater level prediction is challenging due to its unpredictable operation of the two systems. This study performed Artificial Neural Network (ANN) model to forecast the groundwater level in the river area reflecting the various predictable/unpredictable factors. For constructing the ANN models, two monitoring wells, YSN1 and YSO8, which are located near the injection and abstraction wells for the GWHP system were selected, respectively. By training with the groundwater level data measured in January 2015 to August 2015, response of groundwater level by each of the surface water level, the WCC and the GWHP system were evaluated. Consequentially, groundwater levels in December 2015 to March 2016 were predicted by ANN models, providing optimal fits in comparison to the observed water levels. This study suggests that the ANN model is a useful tool to forecast the groundwater level in terms of the management of groundwater. Acknowledgement : Financial support was provided by the "R&D Project on Environmental Management of Geologic CO2 Storage" from the KEITI (Project Number: 2014001810003) This research was

  12. A national-scale seasonal hydrological forecast system: development and evaluation over Britain

    Directory of Open Access Journals (Sweden)

    V. A. Bell

    2017-09-01

    Full Text Available Skilful winter seasonal predictions for the North Atlantic circulation and northern Europe have now been demonstrated and the potential for seasonal hydrological forecasting in the UK is now being explored. One of the techniques being used combines seasonal rainfall forecasts provided by operational weather forecast systems with hydrological modelling tools to provide estimates of seasonal mean river flows up to a few months ahead. The work presented here shows how spatial information contained in a distributed hydrological model typically requiring high-resolution (daily or better rainfall data can be used to provide an initial condition for a much simpler forecast model tailored to use low-resolution monthly rainfall forecasts. Rainfall forecasts (hindcasts from the GloSea5 model (1996 to 2009 are used to provide the first assessment of skill in these national-scale flow forecasts. The skill in the combined modelling system is assessed for different seasons and regions of Britain, and compared to what might be achieved using other approaches such as use of an ensemble of historical rainfall in a hydrological model, or a simple flow persistence forecast. The analysis indicates that only limited forecast skill is achievable for Spring and Summer seasonal hydrological forecasts; however, Autumn and Winter flows can be reasonably well forecast using (ensemble mean rainfall forecasts based on either GloSea5 forecasts or historical rainfall (the preferred type of forecast depends on the region. Flow forecasts using ensemble mean GloSea5 rainfall perform most consistently well across Britain, and provide the most skilful forecasts overall at the 3-month lead time. Much of the skill (64 % in the 1-month ahead seasonal flow forecasts can be attributed to the hydrological initial condition (particularly in regions with a significant groundwater contribution to flows, whereas for the 3-month ahead lead time, GloSea5 forecasts account for  ∼ 70

  13. A national-scale seasonal hydrological forecast system: development and evaluation over Britain

    Science.gov (United States)

    Bell, Victoria A.; Davies, Helen N.; Kay, Alison L.; Brookshaw, Anca; Scaife, Adam A.

    2017-09-01

    Skilful winter seasonal predictions for the North Atlantic circulation and northern Europe have now been demonstrated and the potential for seasonal hydrological forecasting in the UK is now being explored. One of the techniques being used combines seasonal rainfall forecasts provided by operational weather forecast systems with hydrological modelling tools to provide estimates of seasonal mean river flows up to a few months ahead. The work presented here shows how spatial information contained in a distributed hydrological model typically requiring high-resolution (daily or better) rainfall data can be used to provide an initial condition for a much simpler forecast model tailored to use low-resolution monthly rainfall forecasts. Rainfall forecasts (hindcasts) from the GloSea5 model (1996 to 2009) are used to provide the first assessment of skill in these national-scale flow forecasts. The skill in the combined modelling system is assessed for different seasons and regions of Britain, and compared to what might be achieved using other approaches such as use of an ensemble of historical rainfall in a hydrological model, or a simple flow persistence forecast. The analysis indicates that only limited forecast skill is achievable for Spring and Summer seasonal hydrological forecasts; however, Autumn and Winter flows can be reasonably well forecast using (ensemble mean) rainfall forecasts based on either GloSea5 forecasts or historical rainfall (the preferred type of forecast depends on the region). Flow forecasts using ensemble mean GloSea5 rainfall perform most consistently well across Britain, and provide the most skilful forecasts overall at the 3-month lead time. Much of the skill (64 %) in the 1-month ahead seasonal flow forecasts can be attributed to the hydrological initial condition (particularly in regions with a significant groundwater contribution to flows), whereas for the 3-month ahead lead time, GloSea5 forecasts account for ˜ 70 % of the forecast

  14. Forecasting of groundwater level fluctuations using ensemble hybrid multi-wavelet neural network-based models.

    Science.gov (United States)

    Barzegar, Rahim; Fijani, Elham; Asghari Moghaddam, Asghar; Tziritis, Evangelos

    2017-12-01

    Accurate prediction of groundwater level (GWL) fluctuations can play an important role in water resources management. The aims of the research are to evaluate the performance of different hybrid wavelet-group method of data handling (WA-GMDH) and wavelet-extreme learning machine (WA-ELM) models and to combine different wavelet based models for forecasting the GWL for one, two and three months step-ahead in the Maragheh-Bonab plain, NW Iran, as a case study. The research used totally 367 monthly GWLs (m) datasets (Sep 1985-Mar 2016) which were split into two subsets; the first 312 datasets (85% of total) were used for model development (training) and the remaining 55 ones (15% of total) for model evaluation (testing). The stepwise selection was used to select appropriate lag times as the inputs of the proposed models. The performance criteria such as coefficient of determination (R2), root mean square error (RMSE) and Nash-Sutcliffe efficiency coefficient (NSC) were used for assessing the efficiency of the models. The results indicated that the ELM models outperformed GMDH models. To construct the hybrid wavelet based models, the inputs and outputs were decomposed into sub-time series employing different maximal overlap discrete wavelet transform (MODWT) functions, namely Daubechies, Symlet, Haar and Dmeyer of different orders at level two. Subsequently, these sub-time series were served in the GMDH and ELM models as an input dataset to forecast the multi-step-ahead GWL. The wavelet based models improved the performances of GMDH and ELM models for multi-step-ahead GWL forecasting. To combine the advantages of different wavelets, a least squares boosting (LSBoost) algorithm was applied. The use of the boosting multi-WA-neural network models provided the best performances for GWL forecasts in comparison with single WA-neural network-based models. Copyright © 2017 Elsevier B.V. All rights reserved.

  15. A New Hybrid Model Based on Data Preprocessing and an Intelligent Optimization Algorithm for Electrical Power System Forecasting

    Directory of Open Access Journals (Sweden)

    Ping Jiang

    2015-01-01

    Full Text Available The establishment of electrical power system cannot only benefit the reasonable distribution and management in energy resources, but also satisfy the increasing demand for electricity. The electrical power system construction is often a pivotal part in the national and regional economic development plan. This paper constructs a hybrid model, known as the E-MFA-BP model, that can forecast indices in the electrical power system, including wind speed, electrical load, and electricity price. Firstly, the ensemble empirical mode decomposition can be applied to eliminate the noise of original time series data. After data preprocessing, the back propagation neural network model is applied to carry out the forecasting. Owing to the instability of its structure, the modified firefly algorithm is employed to optimize the weight and threshold values of back propagation to obtain a hybrid model with higher forecasting quality. Three experiments are carried out to verify the effectiveness of the model. Through comparison with other traditional well-known forecasting models, and models optimized by other optimization algorithms, the experimental results demonstrate that the hybrid model has the best forecasting performance.

  16. A novel multilayer model for missing link prediction and future link forecasting in dynamic complex networks

    Science.gov (United States)

    Yasami, Yasser; Safaei, Farshad

    2018-02-01

    The traditional complex network theory is particularly focused on network models in which all network constituents are dealt with equivalently, while fail to consider the supplementary information related to the dynamic properties of the network interactions. This is a main constraint leading to incorrect descriptions of some real-world phenomena or incomplete capturing the details of certain real-life problems. To cope with the problem, this paper addresses the multilayer aspects of dynamic complex networks by analyzing the properties of intrinsically multilayered co-authorship networks, DBLP and Astro Physics, and presenting a novel multilayer model of dynamic complex networks. The model examines the layers evolution (layers birth/death process and lifetime) throughout the network evolution. Particularly, this paper models the evolution of each node's membership in different layers by an Infinite Factorial Hidden Markov Model considering feature cascade, and thereby formulates the link generation process for intra-layer and inter-layer links. Although adjacency matrixes are useful to describe the traditional single-layer networks, such a representation is not sufficient to describe and analyze the multilayer dynamic networks. This paper also extends a generalized mathematical infrastructure to address the problems issued by multilayer complex networks. The model inference is performed using some Markov Chain Monte Carlo sampling strategies, given synthetic and real complex networks data. Experimental results indicate a tremendous improvement in the performance of the proposed multilayer model in terms of sensitivity, specificity, positive and negative predictive values, positive and negative likelihood ratios, F1-score, Matthews correlation coefficient, and accuracy for two important applications of missing link prediction and future link forecasting. The experimental results also indicate the strong predictivepower of the proposed model for the application of

  17. A Multi Time Scale Wind Power Forecasting Model of a Chaotic Echo State Network Based on a Hybrid Algorithm of Particle Swarm Optimization and Tabu Search

    Directory of Open Access Journals (Sweden)

    Xiaomin Xu

    2015-11-01

    Full Text Available The uncertainty and regularity of wind power generation are caused by wind resources’ intermittent and randomness. Such volatility brings severe challenges to the wind power grid. The requirements for ultrashort-term and short-term wind power forecasting with high prediction accuracy of the model used, have great significance for reducing the phenomenon of abandoned wind power , optimizing the conventional power generation plan, adjusting the maintenance schedule and developing real-time monitoring systems. Therefore, accurate forecasting of wind power generation is important in electric load forecasting. The echo state network (ESN is a new recurrent neural network composed of input, hidden layer and output layers. It can approximate well the nonlinear system and achieves great results in nonlinear chaotic time series forecasting. Besides, the ESN is simpler and less computationally demanding than the traditional neural network training, which provides more accurate training results. Aiming at addressing the disadvantages of standard ESN, this paper has made some improvements. Combined with the complementary advantages of particle swarm optimization and tabu search, the generalization of ESN is improved. To verify the validity and applicability of this method, case studies of multitime scale forecasting of wind power output are carried out to reconstruct the chaotic time series of the actual wind power generation data in a certain region to predict wind power generation. Meanwhile, the influence of seasonal factors on wind power is taken into consideration. Compared with the classical ESN and the conventional Back Propagation (BP neural network, the results verify the superiority of the proposed method.

  18. A hybrid approach to monthly streamflow forecasting: Integrating hydrological model outputs into a Bayesian artificial neural network

    Science.gov (United States)

    Humphrey, Greer B.; Gibbs, Matthew S.; Dandy, Graeme C.; Maier, Holger R.

    2016-09-01

    Monthly streamflow forecasts are needed to support water resources decision making in the South East of South Australia, where baseflow represents a significant proportion of the total streamflow and soil moisture and groundwater are important predictors of runoff. To address this requirement, the utility of a hybrid monthly streamflow forecasting approach is explored, whereby simulated soil moisture from the GR4J conceptual rainfall-runoff model is used to represent initial catchment conditions in a Bayesian artificial neural network (ANN) statistical forecasting model. To assess the performance of this hybrid forecasting method, a comparison is undertaken of the relative performances of the Bayesian ANN, the GR4J conceptual model and the hybrid streamflow forecasting approach for producing 1-month ahead streamflow forecasts at three key locations in the South East of South Australia. Particular attention is paid to the quantification of uncertainty in each of the forecast models and the potential for reducing forecast uncertainty by using the hybrid approach is considered. Case study results suggest that the hybrid models developed in this study are able to take advantage of the complementary strengths of both the ANN models and the GR4J conceptual models. This was particularly the case when forecasting high flows, where the hybrid models were shown to outperform the two individual modelling approaches in terms of the accuracy of the median forecasts, as well as reliability and resolution of the forecast distributions. In addition, the forecast distributions generated by the hybrid models were up to 8 times more precise than those based on climatology; thus, providing a significant improvement on the information currently available to decision makers.

  19. An operational coupled wave-current forecasting system for the northern Adriatic Sea

    Science.gov (United States)

    Russo, A.; Coluccelli, A.; Deserti, M.; Valentini, A.; Benetazzo, A.; Carniel, S.

    2012-04-01

    Since 2005 an Adriatic implementation of the Regional Ocean Modeling System (AdriaROMS) is being producing operational short-term forecasts (72 hours) of some hydrodynamic properties (currents, sea level, temperature, salinity) of the Adriatic Sea at 2 km horizontal resolution and 20 vertical s-levels, on a daily basis. The main objective of AdriaROMS, which is managed by the Hydro-Meteo-Clima Service (SIMC) of ARPA Emilia Romagna, is to provide useful products for civil protection purposes (sea level forecasts, outputs to run other forecasting models as for saline wedge, oil spills and coastal erosion). In order to improve the forecasts in the coastal area, where most of the attention is focused, a higher resolution model (0.5 km, again with 20 vertical s-levels) has been implemented for the northern Adriatic domain. The new implementation is based on the Coupled-Ocean-Atmosphere-Wave-Sediment Transport Modeling System (COAWST)and adopts ROMS for the hydrodynamic and Simulating WAve Nearshore (SWAN) for the wave module, respectively. Air-sea fluxes are computed using forecasts produced by the COSMO-I7 operational atmospheric model. At the open boundary of the high resolution model, temperature, salinity and velocity fields are provided by AdriaROMS while the wave characteristics are provided by an operational SWAN implementation (also managed by SIMC). Main tidal components are imposed as well, derived from a tidal model. Work in progress is oriented now on the validation of model results by means of extensive comparisons with acquired hydrographic measurements (such as CTDs or XBTs from sea-truth campaigns), currents and waves acquired at observational sites (including those of SIMC, CNR-ISMAR network and its oceanographic tower, located off the Venice littoral) and satellite-derived wave-heights data. Preliminary results on the forecast waves denote how, especially during intense storms, the effect of coupling can lead to significant variations in the wave

  20. Forecasting the mixed-layer depth in the Northeast Atlantic: an ensemble approach, with uncertainties based on data from operational ocean forecasting systems

    Science.gov (United States)

    Drillet, Y.; Lellouche, J. M.; Levier, B.; Drévillon, M.; Le Galloudec, O.; Reffray, G.; Regnier, C.; Greiner, E.; Clavier, M.

    2014-12-01

    Operational systems operated by Mercator Ocean provide daily ocean forecasts, and combining these forecasts we can produce ensemble forecast and uncertainty estimates. This study focuses on the mixed-layer depth in the Northeast Atlantic near the Porcupine Abyssal Plain for May 2013. This period is of interest for several reasons: (1) four Mercator Ocean operational systems provide daily forecasts at a horizontal resolution of 1/4, 1/12 and 1/36° with different physics; (2) glider deployment under the OSMOSIS project provides observation of the changes in mixed-layer depth; (3) the ocean stratifies in May, but mixing events induced by gale force wind are observed and forecast by the systems. Statistical scores and forecast error quantification for each system and for the combined products are presented. Skill scores indicate that forecasts are consistently better than persistence, and temporal correlations between forecast and observations are greater than 0.8 even for the 4-day forecast. The impact of atmospheric forecast error, and for the wind field in particular (miss or time delay of a wind burst forecast), is also quantified in terms of occurrence and intensity of mixing or stratification events.

  1. Hydrological-oriented verification for ensemble forecasting systems: the case of the PIT diagram

    Science.gov (United States)

    Bourgin, François; Ramos, Maria-Helena; Perrin, Charles; Renard, Benjamin

    2017-04-01

    The most common way to communicate uncertainty in streamflow predictions for water resources and risk management is through the use of ensemble scenarios or prediction intervals. While the advantages of probabilistic flow forecasting for decision-making are recognized, the evaluation of the quality of ensemble-based or probabilistic forecasts remains a challenge. Reliability is a fundamental attribute when evaluating the quality of probabilistic flow predictions. It is related to the statistical coherence of the associated uncertainty estimates. Reliable predictions are thus important for users who take actions based on prediction intervals (e.g., reservoir inflow volume forecasts) or on the forecast probability of a given critical event (e.g., exceedance of a flood threshold). However, forecast systems are usually developed to serve many users and, in general, they are evaluated without considering the user's specific decision-making problem. This means that a forecasting system must be reliable in all situations (for normal, high or low flows; for peak flow probabilities or volume probabilities of occurrence), regardless of the event of interest for the user. At the same time, users are often interested in knowing if a forecasting system performs well for their case of application. Application-focused evaluations of the quality of a forecast are thus also important to enhance the usefulness of a forecasting system. Here, we investigate the specificities of hydrological-oriented verification of reliability that is commonly assessed with the Probability Integral Transform (PIT) diagram. We applied an ensemble forecasting system to a large set of catchments in France to assess the impact of conditioning strategies used to stratifying the data on the evaluation of forecast performance. For example, we considered separating low and high flows, or focusing on rainfall-driven or recession parts of the hydrographs. We show that the use of conditioning strategies can

  2. Verification of Global Radiation Forecasts from the Ensemble Prediction System at DMI

    DEFF Research Database (Denmark)

    Lundholm, Sisse Camilla

    consumption of the house and the amount of available solar energy. In order to make the most of this solar heating unit, accurate forecasts of the available solar radiation are esstential. However, because of its sensitivity to local meteorological conditions, the solar radiation received at the surface......To comply with an increasing demand for sustainable energy sources, a solar heating unit is being developed at the Technical University of Denmark. To make optimal use — environmentally and economically —, this heating unit is equipped with an intelligent control system using forecasts of the heat...... of the Earth can be highly fluctuating and challenging to forecast accurately. To comply with the accuracy requirements to forecasts of both global, direct, and diffuse radiation, the uncertainty of these forecasts is of interest. Forecast uncertainties can become accessible by running an ensemble of forecasts...

  3. Probabilistic runoff volume forecasting in risk-based optimization for RTC of urban drainage systems

    DEFF Research Database (Denmark)

    Löwe, Roland; Vezzaro, Luca; Mikkelsen, Peter Steen

    2016-01-01

    This article demonstrates the incorporation of stochastic grey-box models for urban runoff forecasting into a full-scale, system-wide control setup where setpoints are dynamically optimized considering forecast uncertainty and sensitivity of overflow locations in order to reduce combined sewer...... overflow risk. The stochastic control framework and the performance of the runoff forecasting models are tested in a case study in Copenhagen (76 km2 with 6 sub-catchments and 7 control points) using 2-h radar rainfall forecasts and inlet flows to control points computed from a variety of noisy....../oscillating in-sewer measurements. Radar rainfall forecasts as model inputs yield considerably lower runoff forecast skills than “perfect” gauge-based rainfall observations (ex-post hindcasting). Nevertheless, the stochastic grey-box models clearly outperform benchmark forecast models based on exponential...

  4. Comparative Study of Hybrid Models Based on a Series of Optimization Algorithms and Their Application in Energy System Forecasting

    Directory of Open Access Journals (Sweden)

    Xuejiao Ma

    2016-08-01

    Full Text Available Big data mining, analysis, and forecasting play vital roles in modern economic and industrial fields, especially in the energy system. Inaccurate forecasting may cause wastes of scarce energy or electricity shortages. However, forecasting in the energy system has proven to be a challenging task due to various unstable factors, such as high fluctuations, autocorrelation and stochastic volatility. To forecast time series data by using hybrid models is a feasible alternative of conventional single forecasting modelling approaches. This paper develops a group of hybrid models to solve the problems above by eliminating the noise in the original data sequence and optimizing the parameters in a back propagation neural network. One of contributions of this paper is to integrate the existing algorithms and models, which jointly show advances over the present state of the art. The results of comparative studies demonstrate that the hybrid models proposed not only satisfactorily approximate the actual value but also can be an effective tool in the planning and dispatching of smart grids.

  5. APLIKASI MODEL ARTIFICIAL NEURAL NETWORKS UNTUK STOCK FORECASTING DI PASAR MODAL INDONESIA

    Directory of Open Access Journals (Sweden)

    Christian Herdinata

    2017-03-01

    Full Text Available This research showed the applicat ion of model Art if icial Neural Networks (ANN orJaringan Syaraf Tiruan (JST at the f ield of monetary science, especially for the applicat ion off inancial forecast ing. ANN or JST was a new alternat ive for the applicat ion of f inancialforecast ing.The purpose of this research was to know whether the stock index instantaneouslyand fully ref lect historical informat ion, in Indonesia Stock Exchange (IDX. The research usedcomparison between return of technical t rading rule based Art if icial Neural Networks (ANNmodel and return of buy & hold st rategy. The result showed that the weakness form ofef f icient market hypothesis was rejected in the Indonesian capital market . Expectat ion ofthis research was giving informat ion and securing the market perpet rators that st ill enabledto get abnormal of return by doing commerce in chnical through forecast ing of model Art ificial Neural Networks (ANN or Jaringan Syaraf Tiruan ( JST.

  6. Proposal for the utilization of neural networks for the forecast of the electric power demand in a distribution system; Propuesta de utilizacion de las redes neuronales para la prediccion de la demanda electrica en un sistema de distribucion

    Energy Technology Data Exchange (ETDEWEB)

    Prado, Pedro O.; Aguero, Carlos A.; Ferreyra, Ruben; Passoni, Lucia Isabel; Clara, Fernando [Universidad Nacional de Mar del Plata, Buenos Aires (Argentina). Facultad de Ingenieria

    1997-12-31

    In this work, the first advances of the investigation project are presented that is developed in the University. The main objective of this project is the recognition of patterns and the definition of models of prediction of the energy demand through the neural networks. Achieved these technical indicators will be possible to analyze, in more complete form, the evolution of a system of electric of distribution. The neural networks is technical not parametric that have demonstrated their aptitude so much in the recognition of patterns as in the recognition of patterns as in the prediction of parameters, in diverse areas. At the moment its use in the field of the energy planning, is still a beginner topic. (author) 12 refs., 5 figs.;poprado at fi.mdp.edu.ar; lpassoni at fi.mdp.edu.ar

  7. GARCH based artificial neural networks in forecasting conditional variance of stock returns

    Directory of Open Access Journals (Sweden)

    Josip Arnerić

    2014-12-01

    Full Text Available Portfolio managers, option traders and market makers are all interested in volatility forecasting in order to get higher profits or less risky positions. Based on the fact that volatility is time varying in high frequency data and that periods of high volatility tend to cluster, the most popular models in modelling volatility are GARCH type models because they can account excess kurtosis and asymmetric effects of financial time series. A standard GARCH(1,1 model usually indicates high persistence in the conditional variance, which may originate from structural changes. The first objective of this paper is to develop a parsimonious neural networks (NN model, which can capture the nonlinear relationship between past return innovations and conditional variance. Therefore, the goal is to develop a neural network with an appropriate recurrent connection in the context of nonlinear ARMA models, i.e., the Jordan neural network (JNN. The second objective of this paper is to determine if JNN outperforms the standard GARCH model. Out-of-sample forecasts of the JNN and the GARCH model will be compared to determine their predictive accuracy. The data set consists of returns of the CROBEX index daily closing prices obtained from the Zagreb Stock Exchange. The results indicate that the selected JNN(1,1,1 model has superior performances compared to the standard GARCH(1,1 model. The contribution of this paper can be seen in determining the appropriate NN that is comparable to the standard GARCH(1,1 model and its application in forecasting conditional variance of stock returns. Moreover, from the econometric perspective, NN models are used as a semi-parametric method that combines flexibility of nonparametric methods and the interpretability of parameters of parametric methods.

  8. Comparison of different forms of the Multi-layer Feed-Forward Neural Network method used for river flow forecasting

    Directory of Open Access Journals (Sweden)

    A. Y. Shamseldin

    2002-01-01

    Full Text Available The Multi-Layer Feed-Forward Neural Network (MLFFNN is applied in the context of river flow forecast combination, where a number of rainfall-runoff models are used simultaneously to produce an overall combined river flow forecast. The operation of the MLFFNN depends not only on its neuron configuration but also on the choice of neuron transfer function adopted, which is non-linear for the hidden and output layers. These models, each having a different structure to simulate the perceived mechanisms of the runoff process, utilise the information carrying capacity of the model calibration data in different ways. Hence, in a discharge forecast combination procedure, the discharge forecasts of each model provide a source of information different from that of the other models used in the combination. In the present work, the significance of the choice of the transfer function type in the overall performance of the MLFFNN, when used in the river flow forecast combination context, is investigated critically. Five neuron transfer functions are used in this investigation, namely, the logistic function, the bipolar function, the hyperbolic tangent function, the arctan function and the scaled arctan function. The results indicate that the logistic function yields the best model forecast combination performance. Keywords: River flow forecast combination, multi-layer feed-forward neural network, neuron transfer functions, rainfall-runoff models

  9. Development and application of Artificial Neural Networks in forecasting the maximum daily precipitation at Athens, Greece

    Science.gov (United States)

    Nastos, P. T.; Paliatsos, A. G.; Larissi, I. K.; Moustris, K. P.

    2012-04-01

    Extreme daily precipitation events are involved in significant environmental damages, even in life loss, because of causing adverse impacts, such as flash floods, in urban and sometimes in rural areas. Thus, long-term forecast of such events is of great importance, in order to be prepared the local authorities to confront and mitigate the adverse consequences. The objective of this study is to estimate the possibility of forecasting the maximum daily precipitation for the next coming year. For this reason, appropriate prognostic models, such as Artificial Neural Networks (ANNs) were developed and applied. The data used for the analysis concern daily precipitation totals, which have been recorded at National Observatory of Athens (NOA), during the period 1891-2009. To evaluate the potential of daily extreme precipitation prognosis by the applied ANNs, a different period was considered than the one used for the ANNs training. Thus, the datasets of the period 1891-1980 were used as training datasets, while the datasets of the period 1981-2009 as validation datasets. Appropriate statistical indices, such as the Coefficient of Determination (R2), the Index of Agreement (IA), the Root Mean Square Error (RMSE), and the Mean Bias Error (MBE) were applied to test the reliability of the models. The findings of the analysis showed that, a quite satisfactory relationship at the statistically significant level of p<0.01 appears between the forecasted maximum daily precipitation totals for the next coming year and the respective observed ones.

  10. Short-Term Wind Speed Forecasting Using Decomposition-Based Neural Networks Combining Abnormal Detection Method

    Directory of Open Access Journals (Sweden)

    Xuejun Chen

    2014-01-01

    Full Text Available As one of the most promising renewable resources in electricity generation, wind energy is acknowledged for its significant environmental contributions and economic competitiveness. Because wind fluctuates with strong variation, it is quite difficult to describe the characteristics of wind or to estimate the power output that will be injected into the grid. In particular, short-term wind speed forecasting, an essential support for the regulatory actions and short-term load dispatching planning during the operation of wind farms, is currently regarded as one of the most difficult problems to be solved. This paper contributes to short-term wind speed forecasting by developing two three-stage hybrid approaches; both are combinations of the five-three-Hanning (53H weighted average smoothing method, ensemble empirical mode decomposition (EEMD algorithm, and nonlinear autoregressive (NAR neural networks. The chosen datasets are ten-minute wind speed observations, including twelve samples, and our simulation indicates that the proposed methods perform much better than the traditional ones when addressing short-term wind speed forecasting problems.

  11. Forecasting recruitment and stock biomass of Northeast Arctic cod using neural networks

    Directory of Open Access Journals (Sweden)

    Geir Huse

    2003-04-01

    Full Text Available We apply an artificial neural network (ANN to predict recruitment and biomass development of Northeast Arctic cod. The ANN is trained using a genetic algorithm with input time series such as spawning stock biomass of cod, herring and capelin biomass, and temperature. Forecasts were made by training the ANN on parts of the time series (training set, and then using a trained ANN to predict cod recruitment or biomass in years outside of the training set. In general the predictions corresponded well to observations. The correlation (r2 between observed and predicted stock recruitment at age 3 was 0.74, based on a model with temperature, spawning stock biomass, and capelin biomass. The correlation between observed and predicted stock biomass was 0.89, 0.72 and 0.57 for one, two and three year predictions respectively. The best model for the one year predictions was based on input information on cod biomass, temperature, and cod landings. These results illustrate the strong forecasting ability of ANN models. In the light of our findings we discuss the potential benefit of applying ANN models as a forecasting technology in fisheries assessment.

  12. Intelligent Ensemble Forecasting System of Stock Market Fluctuations Based on Symetric and Asymetric Wavelet Functions

    Science.gov (United States)

    Lahmiri, Salim; Boukadoum, Mounir

    2015-08-01

    We present a new ensemble system for stock market returns prediction where continuous wavelet transform (CWT) is used to analyze return series and backpropagation neural networks (BPNNs) for processing CWT-based coefficients, determining the optimal ensemble weights, and providing final forecasts. Particle swarm optimization (PSO) is used for finding optimal weights and biases for each BPNN. To capture symmetry/asymmetry in the underlying data, three wavelet functions with different shapes are adopted. The proposed ensemble system was tested on three Asian stock markets: The Hang Seng, KOSPI, and Taiwan stock market data. Three statistical metrics were used to evaluate the forecasting accuracy; including, mean of absolute errors (MAE), root mean of squared errors (RMSE), and mean of absolute deviations (MADs). Experimental results showed that our proposed ensemble system outperformed the individual CWT-ANN models each with different wavelet function. In addition, the proposed ensemble system outperformed the conventional autoregressive moving average process. As a result, the proposed ensemble system is suitable to capture symmetry/asymmetry in financial data fluctuations for better prediction accuracy.

  13. Financial forecasts accuracy in Brazil’s social security system

    Science.gov (United States)

    2017-01-01

    Long-term social security statistical forecasts produced and disseminated by the Brazilian government aim to provide accurate results that would serve as background information for optimal policy decisions. These forecasts are being used as support for the government’s proposed pension reform that plans to radically change the Brazilian Constitution insofar as Social Security is concerned. However, the reliability of official results is uncertain since no systematic evaluation of these forecasts has ever been published by the Brazilian government or anyone else. This paper aims to present a study of the accuracy and methodology of the instruments used by the Brazilian government to carry out long-term actuarial forecasts. We base our research on an empirical and probabilistic analysis of the official models. Our empirical analysis shows that the long-term Social Security forecasts are systematically biased in the short term and have significant errors that render them meaningless in the long run. Moreover, the low level of transparency in the methods impaired the replication of results published by the Brazilian Government and the use of outdated data compromises forecast results. In the theoretical analysis, based on a mathematical modeling approach, we discuss the complexity and limitations of the macroeconomic forecast through the computation of confidence intervals. We demonstrate the problems related to error measurement inherent to any forecasting process. We then extend this exercise to the computation of confidence intervals for Social Security forecasts. This mathematical exercise raises questions about the degree of reliability of the Social Security forecasts. PMID:28859172

  14. Financial forecasts accuracy in Brazil's social security system.

    Science.gov (United States)

    Silva, Carlos Patrick Alves da; Puty, Claudio Alberto Castelo Branco; Silva, Marcelino Silva da; Carvalho, Solon Venâncio de; Francês, Carlos Renato Lisboa

    2017-01-01

    Long-term social security statistical forecasts produced and disseminated by the Brazilian government aim to provide accurate results that would serve as background information for optimal policy decisions. These forecasts are being used as support for the government's proposed pension reform that plans to radically change the Brazilian Constitution insofar as Social Security is concerned. However, the reliability of official results is uncertain since no systematic evaluation of these forecasts has ever been published by the Brazilian government or anyone else. This paper aims to present a study of the accuracy and methodology of the instruments used by the Brazilian government to carry out long-term actuarial forecasts. We base our research on an empirical and probabilistic analysis of the official models. Our empirical analysis shows that the long-term Social Security forecasts are systematically biased in the short term and have significant errors that render them meaningless in the long run. Moreover, the low level of transparency in the methods impaired the replication of results published by the Brazilian Government and the use of outdated data compromises forecast results. In the theoretical analysis, based on a mathematical modeling approach, we discuss the complexity and limitations of the macroeconomic forecast through the computation of confidence intervals. We demonstrate the problems related to error measurement inherent to any forecasting process. We then extend this exercise to the computation of confidence intervals for Social Security forecasts. This mathematical exercise raises questions about the degree of reliability of the Social Security forecasts.

  15. Artificial neural networks modeling for forecasting the maximum daily total precipitation at Athens, Greece

    Science.gov (United States)

    Nastos, P. T.; Paliatsos, A. G.; Koukouletsos, K. V.; Larissi, I. K.; Moustris, K. P.

    2014-07-01

    Extreme daily precipitation events are involved in significant environmental damages, even in life loss, because of causing adverse impacts, such as flash floods, in urban and sometimes in rural areas. Thus, long-term forecast of such events is of great importance for the preparation of local authorities in order to confront and mitigate the adverse consequences. The objective of this study is to estimate the possibility of forecasting the maximum daily precipitation for the next coming year. For this reason, appropriate prognostic models, such as Artificial Neural Networks (ANNs) were developed and applied. The data used for the analysis concern annual maximum daily precipitation totals, which have been recorded at the National Observatory of Athens (NOA), during the long term period 1891-2009. To evaluate the potential of daily extreme precipitation forecast by the applied ANNs, a different period for validation was considered than the one used for the ANNs training. Thus, the datasets of the period 1891-1980 were used as training datasets, while the datasets of the period 1981-2009 as validation datasets. Appropriate statistical indices, such as the coefficient of determination (R2), the index of agreement (IA), the Root Mean Square Error (RMSE) and the Mean Bias Error (MBE), were applied to test the reliability of the models. The findings of the analysis showed that, a quite satisfactory relationship (R2 = 0.482, IA = 0.817, RMSE = 16.4 mm and MBE = + 5.2 mm) appears between the forecasted and the respective observed maximum daily precipitation totals one year ahead. The developed ANN seems to overestimate the maximum daily precipitation totals appeared in 1988 while underestimate the maximum in 1999, which could be attributed to the relatively low frequency of occurrence of these extreme events within GAA having impact on the optimum training of ANN.

  16. Advanced Intelligent System Application to Load Forecasting and Control for Hybrid Electric Bus

    Science.gov (United States)

    Momoh, James; Chattopadhyay, Deb; Elfayoumy, Mahmoud

    1996-01-01

    The primary motivation for this research emanates from providing a decision support system to the electric bus operators in the municipal and urban localities which will guide the operators to maintain an optimal compromise among the noise level, pollution level, fuel usage etc. This study is backed up by our previous studies on study of battery characteristics, permanent magnet DC motor studies and electric traction motor size studies completed in the first year. The operator of the Hybrid Electric Car must determine optimal power management schedule to meet a given load demand for different weather and road conditions. The decision support system for the bus operator comprises three sub-tasks viz. forecast of the electrical load for the route to be traversed divided into specified time periods (few minutes); deriving an optimal 'plan' or 'preschedule' based on the load forecast for the entire time-horizon (i.e., for all time periods) ahead of time; and finally employing corrective control action to monitor and modify the optimal plan in real-time. A fully connected artificial neural network (ANN) model is developed for forecasting the kW requirement for hybrid electric bus based on inputs like climatic conditions, passenger load, road inclination, etc. The ANN model is trained using back-propagation algorithm employing improved optimization techniques like projected Lagrangian technique. The pre-scheduler is based on a Goal-Programming (GP) optimization model with noise, pollution and fuel usage as the three objectives. GP has the capability of analyzing the trade-off among the conflicting objectives and arriving at the optimal activity levels, e.g., throttle settings. The corrective control action or the third sub-task is formulated as an optimal control model with inputs from the real-time data base as well as the GP model to minimize the error (or deviation) from the optimal plan. These three activities linked with the ANN forecaster proving the output to the

  17. CEREF: A hybrid data-driven model for forecasting annual streamflow from a socio-hydrological system

    Science.gov (United States)

    Zhang, Hongbo; Singh, Vijay P.; Wang, Bin; Yu, Yinghao

    2016-09-01

    Hydrological forecasting is complicated by flow regime alterations in a coupled socio-hydrologic system, encountering increasingly non-stationary, nonlinear and irregular changes, which make decision support difficult for future water resources management. Currently, many hybrid data-driven models, based on the decomposition-prediction-reconstruction principle, have been developed to improve the ability to make predictions of annual streamflow. However, there exist many problems that require further investigation, the chief among which is the direction of trend components decomposed from annual streamflow series and is always difficult to ascertain. In this paper, a hybrid data-driven model was proposed to capture this issue, which combined empirical mode decomposition (EMD), radial basis function neural networks (RBFNN), and external forces (EF) variable, also called the CEREF model. The hybrid model employed EMD for decomposition and RBFNN for intrinsic mode function (IMF) forecasting, and determined future trend component directions by regression with EF as basin water demand representing the social component in the socio-hydrologic system. The Wuding River basin was considered for the case study, and two standard statistical measures, root mean squared error (RMSE) and mean absolute error (MAE), were used to evaluate the performance of CEREF model and compare with other models: the autoregressive (AR), RBFNN and EMD-RBFNN. Results indicated that the CEREF model had lower RMSE and MAE statistics, 42.8% and 7.6%, respectively, than did other models, and provided a superior alternative for forecasting annual runoff in the Wuding River basin. Moreover, the CEREF model can enlarge the effective intervals of streamflow forecasting compared to the EMD-RBFNN model by introducing the water demand planned by the government department to improve long-term prediction accuracy. In addition, we considered the high-frequency component, a frequent subject of concern in EMD

  18. Tax forecasting as part of a macro financial controlling system: the case of Ukraine

    Directory of Open Access Journals (Sweden)

    Tetiana Paientko

    2017-09-01

    Full Text Available Tax forecasting as part of a macro financial controlling system: the case of Ukraine The current system of forecasting and tax planning in Ukraine is oriented to the needs of the government, its goal being to calculate the desired amounts of tax revenue. Fiscal authorities apply administrative pressure on businesses to implement tax plans. In Ukraine, tax forecasting is a process that is focused on achieving short-term goals without taking into account the impact of such actions on the future economic environment, therefore negatively affecting the quality of forecasts. The aim of this article is to justify the directions of tax forecasting improvement in the macro financial controlling system. Elements of tax forecasting and the planning system are examined. The main methods of tax forecasting that are applied by the Ministry of Finance of Ukraine are analyzed. The need to improve the methodology for tax fore-casting, taking into account the expectations of economic agents, is proved. Tools and criteria for effec-tive tax planning and forecasting in Ukraine for controlling bases are developed.

  19. Short-Term Solar Irradiance Forecasting Model Based on Artificial Neural Network Using Statistical Feature Parameters

    Directory of Open Access Journals (Sweden)

    Hongshan Zhao

    2012-05-01

    Full Text Available Short-term solar irradiance forecasting (STSIF is of great significance for the optimal operation and power predication of grid-connected photovoltaic (PV plants. However, STSIF is very complex to handle due to the random and nonlinear characteristics of solar irradiance under changeable weather conditions. Artificial Neural Network (ANN is suitable for STSIF modeling and many research works on this topic are presented, but the conciseness and robustness of the existing models still need to be improved. After discussing the relation between weather variations and irradiance, the characteristics of the statistical feature parameters of irradiance under different weather conditions are figured out. A novel ANN model using statistical feature parameters (ANN-SFP for STSIF is proposed in this paper. The input vector is reconstructed with several statistical feature parameters of irradiance and ambient temperature. Thus sufficient information can be effectively extracted from relatively few inputs and the model complexity is reduced. The model structure is determined by cross-validation (CV, and the Levenberg-Marquardt algorithm (LMA is used for the network training. Simulations are carried out to validate and compare the proposed model with the conventional ANN model using historical data series (ANN-HDS, and the results indicated that the forecast accuracy is obviously improved under variable weather conditions.

  20. Inferential, non-parametric statistics to assess the quality of probabilistic forecast systems

    NARCIS (Netherlands)

    Maia, A.H.N.; Meinke, H.B.; Lennox, S.; Stone, R.C.

    2007-01-01

    Many statistical forecast systems are available to interested users. To be useful for decision making, these systems must be based on evidence of underlying mechanisms. Once causal connections between the mechanism and its statistical manifestation have been firmly established, the forecasts must

  1. Mediterranea Forecasting System: a focus on wave-current coupling

    Science.gov (United States)

    Clementi, Emanuela; Delrosso, Damiano; Pistoia, Jenny; Drudi, Massimiliano; Fratianni, Claudia; Grandi, Alessandro; Pinardi, Nadia; Oddo, Paolo; Tonani, Marina

    2016-04-01

    The Mediterranean Forecasting System (MFS) is a numerical ocean prediction system that produces analyses, reanalyses and short term forecasts for the entire Mediterranean Sea and its Atlantic Ocean adjacent areas. MFS became operational in the late 90's and has been developed and continuously improved in the framework of a series of EU and National funded programs and is now part of the Copernicus Marine Service. The MFS is composed by the hydrodynamic model NEMO (Nucleus for European Modelling of the Ocean) 2-way coupled with the third generation wave model WW3 (WaveWatchIII) implemented in the Mediterranean Sea with 1/16 horizontal resolution and forced by ECMWF atmospheric fields. The model solutions are corrected by the data assimilation system (3D variational scheme adapted to the oceanic assimilation problem) with a daily assimilation cycle, using a background error correlation matrix varying seasonally and in different sub-regions of the Mediterranean Sea. The focus of this work is to present the latest modelling system upgrades and the related achieved improvements. In order to evaluate the performance of the coupled system a set of experiments has been built by coupling the wave and circulation models that hourly exchange the following fields: the sea surface currents and air-sea temperature difference are transferred from NEMO model to WW3 model modifying respectively the mean momentum transfer of waves and the wind speed stability parameter; while the neutral drag coefficient computed by WW3 model is passed to NEMO that computes the turbulent component. In order to validate the modelling system, numerical results have been compared with in-situ and remote sensing data. This work suggests that a coupled model might be capable of a better description of wave-current interactions, in particular feedback from the ocean to the waves might assess an improvement on the prediction capability of wave characteristics, while suggests to proceed toward a fully

  2. Forecasting Hoabinh Reservoir’s Incoming Flow: An Application of Neural Networks with the Cuckoo Search Algorithm

    Directory of Open Access Journals (Sweden)

    Jeng-Fung Chen

    2014-11-01

    Full Text Available The accuracy of reservoir flow forecasting has the most significant influence on the assurance of stability and annual operations of hydro-constructions. For instance, accurate forecasting on the ebb and flow of Vietnam’s Hoabinh Reservoir can aid in the preparation and prevention of lowland flooding and drought, as well as regulating electric energy. This raises the need to propose a model that accurately forecasts the incoming flow of the Hoabinh Reservoir. In this study, a solution to this problem based on neural network with the Cuckoo Search (CS algorithm is presented. In particular, we used hydrographic data and predicted total incoming flows of the Hoabinh Reservoir over a period of 10 days. The Cuckoo Search algorithm was utilized to train the feedforward neural network (FNN for prediction. The algorithm optimized the weights between layers and biases of the neuron network. Different forecasting models for the three scenarios were developed. The constructed models have shown high forecasting performance based on the performance indices calculated. These results were also compared with those obtained from the neural networks trained by the particle swarm optimization (PSO and back-propagation (BP, indicating that the proposed approach performed more effectively. Based on the experimental results, the scenario using the rainfall and the flow as input yielded the highest forecasting accuracy when compared with other scenarios. The performance criteria RMSE, MAPE, and R obtained by the CS-FNN in this scenario were calculated as 48.7161, 0.067268 and 0.8965, respectively. These results were highly correlated to actual values. It is expected that this work may be useful for hydrographic forecasting.

  3. Forecasting and observability: critical technologies for system operations with high PV penetration

    DEFF Research Database (Denmark)

    Alet, Pierre-Jean; Efthymiou, Venizelos; Graditi, Giorgio

    2016-01-01

    Forecasting and monitoring technologies for photovoltaics are required on different spatial and temporal scales by multiple actors, from the owners of PV systems to transmission system operators. In this paper the Grid integration working group of the European Technology and Innovation Platform –...... for a cost/benefit analysis since the forecasting error can be linked to the prices charged for energy imbalance......Forecasting and monitoring technologies for photovoltaics are required on different spatial and temporal scales by multiple actors, from the owners of PV systems to transmission system operators. In this paper the Grid integration working group of the European Technology and Innovation Platform...... – Photovoltaics (ETIP PV) reviews the different use cases for these technologies, their current status, and the need for future developments. Power system operations require a real-time view of PV production for managing power reserves and for feeding shortterm forecasts. They also require forecasts on all...

  4. Towards a GME ensemble forecasting system: Ensemble initialization using the breeding technique

    Directory of Open Access Journals (Sweden)

    Jan D. Keller

    2008-12-01

    Full Text Available The quantitative forecast of precipitation requires a probabilistic background particularly with regard to forecast lead times of more than 3 days. As only ensemble simulations can provide useful information of the underlying probability density function, we built a new ensemble forecasting system (GME-EFS based on the GME model of the German Meteorological Service (DWD. For the generation of appropriate initial ensemble perturbations we chose the breeding technique developed by Toth and Kalnay (1993, 1997, which develops perturbations by estimating the regions of largest model error induced uncertainty. This method is applied and tested in the framework of quasi-operational forecasts for a three month period in 2007. The performance of the resulting ensemble forecasts are compared to the operational ensemble prediction systems ECMWF EPS and NCEP GFS by means of ensemble spread of free atmosphere parameters (geopotential and temperature and ensemble skill of precipitation forecasting. This comparison indicates that the GME ensemble forecasting system (GME-EFS provides reasonable forecasts with spread skill score comparable to that of the NCEP GFS. An analysis with the continuous ranked probability score exhibits a lack of resolution for the GME forecasts compared to the operational ensembles. However, with significant enhancements during the 3 month test period, the first results of our work with the GME-EFS indicate possibilities for further development as well as the potential for later operational usage.

  5. Network operating system

    Science.gov (United States)

    Perotto, E.

    1987-08-01

    The Network Operating System is an addition to CMS designed to allow multitasking operation, while conserving all the facilities of CMS: file system, interactivity, high level language environment. Multitasking is useful for server virtual machines, e.g. Network Transport Managers, File Managers, Disk space Managers, Tape Unit Managers, where the execution of a task involves long waits due to I/O completion, VCMF communication delays or human responses, during which the task status stays as a control block in memory, while the virtual machine serves other users executing the same lines of code. Multitasking is not only for multi-user service: a big data reduction program may run as a main task, while a side task, connected to the virtual console, gives reports on the ongoing work of the main task in response to user commands and steers the main task through common data. All the service routines (Wait, Create and Delete Task, Get and Release Buffer, VMCF Open and Close Link, Send and Receive, I/O and Console Routines) are FORTRAN callable, and may be used from any language environment consistent with the same parameter passing conventions. The outstanding feature of this system is efficiency, no user defined SVC are used, and the use of other privileged instructions as LPSW or SSM is the bare necessary, so that CP (with the associated overhead) is not too involved. System code and read-only data are write-protected with a different storage key from CMS and user program.

  6. Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

    Directory of Open Access Journals (Sweden)

    Svitlana Volkova

    Full Text Available This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs units capable of nowcasting (predicting in "real-time" and forecasting (predicting the future ILI dynamics in the 2011 - 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus

  7. Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

    Science.gov (United States)

    Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D

    2017-01-01

    This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in "real-time") and forecasting (predicting the future) ILI dynamics in the 2011 - 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from

  8. Load forecasting using different architectures of neural networks with the assistance of the MATLAB toolboxes; Previsao de cargas eletricas utilizando diferentes arquiteturas de redes neurais artificiais com o auxilio das toolboxes do MATLAB

    Energy Technology Data Exchange (ETDEWEB)

    Nose Filho, Kenji; Araujo, Klayton A.M.; Maeda, Jorge L.Y.; Lotufo, Anna Diva P. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil)], Emails: kenjinose@yahoo.com.br, klayton_ama@hotmail.com, jorge-maeda@hotmail.com, annadiva@dee.feis.unesp.br

    2009-07-01

    This paper presents a development and implementation of a program to electrical load forecasting with data from a Brazilian electrical company, using four different architectures of neural networks of the MATLAB toolboxes: multilayer backpropagation gradient descendent with momentum, multilayer backpropagation Levenberg-Marquardt, adaptive network based fuzzy inference system and general regression neural network. The program presented a satisfactory performance, guaranteeing very good results. (author)

  9. Forecasting of Energy Expenditure of Induced Seismicity with Use of Artificial Neural Network

    Science.gov (United States)

    Cichy, Tomasz; Banka, Piotr

    2017-12-01

    Coal mining in many Polish mines in the Upper Silesian Coal Basin is accompanied by high levels of induced seismicity. In mining plants, the methods of shock monitoring are improved, allowing for more accurate localization of the occurring phenomena and determining their seismic energy. Equally important is the development of ways of forecasting seismic hazards that may occur while implementing mine design projects. These methods, depending on the length of time for which the forecasts are made, can be divided into: longterm, medium-term, short-term and so-called alarm. Long-term forecasts are particularly useful for the design of seam exploitations. The paper presents a method of predicting changes in energy expenditure of shock using a properly trained artificial neural network. This method allows to make long-term forecasts at the stage of the mine’s exploitation design, thus enabling the mining work plans to be reviewed to minimize the potential for tremors. The information given at the input of the neural network is indicative of the specific energy changes of the elastic deformation occurring in the selected, thick, resistant rock layers (tremor-prone layers). Energy changes, taking place in one or more tremor-prone layers are considered. These indicators describe only the specific energy changes of the elastic deformation accumulating in the rock as a consequence of the mining operation, but does not determine the amount of energy released during the destruction of a given volume of rock. In this process, the potential energy of elastic strain transforms into other, non-measurable energy types, including the seismic energy of recorded tremors. In this way, potential energy changes affect the observed induced seismicity. The parameters used are characterized by increases (declines) of specific energy with separation to occur before the hypothetical destruction of the rock and after it. Additional input information is an index characterizing the rate of

  10. Forecasting of Hourly Photovoltaic Energy in Canarian Electrical System

    Science.gov (United States)

    Henriquez, D.; Castaño, C.; Nebot, R.; Piernavieja, G.; Rodriguez, A.

    2010-09-01

    The Canarian Archipelago face similar problems as most insular region lacking of endogenous conventional energy resources and not connected to continental electrical grids. A consequence of the "insular fact" is the existence of isolated electrical systems that are very difficult to interconnect due to the considerable sea depths between the islands. Currently, the Canary Islands have six isolated electrical systems, only one utility generating most of the electricity (burning fuel), a recently arrived TSO (REE) and still a low implementation of Renewable Energy Resources (RES). The low level of RES deployment is a consequence of two main facts: the weakness of the stand-alone grids (from 12 MW in El Hierro up to only 1 GW in Gran Canaria) and the lack of space to install RES systems (more than 50% of the land protected due to environmental reasons). To increase the penetration of renewable energy generation, like solar or wind energy, is necessary to develop tools to manage them. The penetration of non manageable sources into weak grids like the Canarian ones causes a big problem to the grid operator. There are currently 104 MW of PV connected to the islands grids (Dec. 2009) and additional 150 MW under licensing. This power presents a serious challenge for the operation and stability of the electrical system. ITC, together with the local TSO (Red Eléctrica de España, REE) started in 2008 and R&D project to develop a PV energy prediction tool for the six Canarian Insular electrical systems. The objective is to supply reliable information for hourly forecast of the generation dispatch programme and to predict daily solar radiation patterns, in order to help program spinning reserves. ITC has approached the task of weather forecasting using different numerical model (MM5 and WRF) in combination with MSG (Meteosat Second Generation) images. From the online data recorded at several monitored PV plants and meteorological stations, PV nominal power and energy produced

  11. A production throughput forecasting system in an automated hard disk drive test operation using GRNN

    Directory of Open Access Journals (Sweden)

    Nara Samattapapong

    2016-04-01

    Originality/value: The production throughput volume is a key performance index of hard disk drive manufacturing systems that need to be forecast. Because of the production throughput forecasting result is useful information for management team to respond to any changing in production processes and resources allocation. However, a practically forecasting system for production throughput has not been described in detail yet. The experiments were conducted on a real data set from the final testing operation of hard disk drive manufacturing factory by using Visual Basics Application on Microsoft Excel© to develop preliminary forecasting system on testing and verification process. The experimental result shows that the proposed model is superior to the performance of the current forecasting system.

  12. An evaluation of the Canadian global meteorological ensemble prediction system for short-term hydrological forecasting

    Directory of Open Access Journals (Sweden)

    F. Anctil

    2009-11-01

    Full Text Available Hydrological forecasting consists in the assessment of future streamflow. Current deterministic forecasts do not give any information concerning the uncertainty, which might be limiting in a decision-making process. Ensemble forecasts are expected to fill this gap.

    In July 2007, the Meteorological Service of Canada has improved its ensemble prediction system, which has been operational since 1998. It uses the GEM model to generate a 20-member ensemble on a 100 km grid, at mid-latitudes. This improved system is used for the first time for hydrological ensemble predictions. Five watersheds in Quebec (Canada are studied: Chaudière, Châteauguay, Du Nord, Kénogami and Du Lièvre. An interesting 17-day rainfall event has been selected in October 2007. Forecasts are produced in a 3 h time step for a 3-day forecast horizon. The deterministic forecast is also available and it is compared with the ensemble ones. In order to correct the bias of the ensemble, an updating procedure has been applied to the output data. Results showed that ensemble forecasts are more skilful than the deterministic ones, as measured by the Continuous Ranked Probability Score (CRPS, especially for 72 h forecasts. However, the hydrological ensemble forecasts are under dispersed: a situation that improves with the increasing length of the prediction horizons. We conjecture that this is due in part to the fact that uncertainty in the initial conditions of the hydrological model is not taken into account.

  13. Harmful algal bloom forecast system for SW Ireland. Part I: Description and validation of an operational forecasting model.

    Science.gov (United States)

    Dabrowski, Tomasz; Lyons, Kieran; Nolan, Glenn; Berry, Alan; Cusack, Caroline; Silke, Joe

    2016-03-01

    A 3D primitive equation coastal ocean model for southwest Ireland, called the Bantry Bay model, was developed and implemented operationally. Validated model outputs have multiple uses. One of the incentives to develop the model was to explore the possible transport pathways that carry harmful algae blooms (HAB) into Bantry Bay. The model is nested offline in a regional North East Atlantic operational model. Surface forcing is taken from the half-degree Global Forecasting System, available at three-hourly intervals. Heat fluxes are calculated from the bulk formulae. Surface freshwater fluxes are obtained from the prescribed rainfall rates and the evaporation rates calculated by the model. Freshwater discharges from five rivers are included in the model. Model validation and the model skill in representing the water level, currents, temperature and salinity in the bay are reported. A scoring system based on the average adjusted relative mean absolute error for the predicted currents was used. An upgrade to a higher score was achieved through the incorporation of local winds into the surface forcing and by varying the bottom roughness coefficient. The model, designed to work in forecast mode, can replicate the main oceanographic features in the region. The model forecast is used in a decision support system for HAB alerts. An operational HAB alert system did not exist in Ireland prior to the use of this model. Copyright © 2015 Elsevier B.V. All rights reserved.

  14. Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach

    Directory of Open Access Journals (Sweden)

    Ajit Kumar Rout

    2017-10-01

    Full Text Available The paper presents a low complexity recurrent Functional Link Artificial Neural Network for predicting the financial time series data like the stock market indices over a time frame varying from 1 day ahead to 1 month ahead. Although different types of basis functions have been used for low complexity neural networks earlier for stock market prediction, a comparative study is needed to choose the optimal combinations of these for a reasonably accurate forecast. Further several evolutionary learning methods like the Particle Swarm Optimization (PSO and modified version of its new variant (HMRPSO, and the Differential Evolution (DE are adopted here to find the optimal weights for the recurrent computationally efficient functional link neural network (RCEFLANN using a combination of linear and hyperbolic tangent basis functions. The performance of the recurrent computationally efficient FLANN model is compared with that of low complexity neural networks using the Trigonometric, Chebyshev, Laguerre, Legendre, and tangent hyperbolic basis functions in predicting stock prices of Bombay Stock Exchange data and Standard & Poor’s 500 data sets using different evolutionary methods and has been presented in this paper and the results clearly reveal that the recurrent FLANN model trained with the DE outperforms all other FLANN models similarly trained.

  15. Stochastic Optimization for Network-Constrained Power System Scheduling Problem

    Directory of Open Access Journals (Sweden)

    D. F. Teshome

    2015-01-01

    Full Text Available The stochastic nature of demand and wind generation has a considerable effect on solving the scheduling problem of a modern power system. Network constraints such as power flow equations and transmission capacities also need to be considered for a comprehensive approach to model renewable energy integration and analyze generation system flexibility. Firstly, this paper accounts for the stochastic inputs in such a way that the uncertainties are modeled as normally distributed forecast errors. The forecast errors are then superimposed on the outputs of load and wind forecasting tools. Secondly, it efficiently models the network constraints and tests an iterative algorithm and a piecewise linear approximation for representing transmission losses in mixed integer linear programming (MILP. It also integrates load shedding according to priority factors set by the system operator. Moreover, the different interactions among stochastic programming, network constraints, and prioritized load shedding are thoroughly investigated in the paper. The stochastic model is tested on a power system adopted from Jeju Island, South Korea. Results demonstrate the impact of wind speed variability and network constraints on the flexibility of the generation system. Further analysis shows the effect of loss modeling approaches on total cost, accuracy, computational time, and memory requirement.

  16. Forecasting Wind and Solar Generation: Improving System Operations, Greening the Grid (Spanish Version)

    Energy Technology Data Exchange (ETDEWEB)

    Tian, Tian; Chernyakhovskiy, Ilya; Brancucci Martinez-Anido, Carlo

    2016-04-01

    This document is the Spanish version of 'Greening the Grid- Forecasting Wind and Solar Generation Improving System Operations'. It discusses improving system operations with forecasting with and solar generation. By integrating variable renewable energy (VRE) forecasts into system operations, power system operators can anticipate up- and down-ramps in VRE generation in order to cost-effectively balance load and generation in intra-day and day-ahead scheduling. This leads to reduced fuel costs, improved system reliability, and maximum use of renewable resources.

  17. Skill of a global forecasting system in seasonal ensemble streamflow prediction

    Science.gov (United States)

    Candogan Yossef, Naze; van Beek, Rens; Weerts, Albrecht; Winsemius, Hessel; Bierkens, Marc F. P.

    2017-08-01

    In this study we assess the skill of seasonal streamflow forecasts with the global hydrological forecasting system Flood Early Warning System (FEWS)-World, which has been set up within the European Commission 7th Framework Programme Project Global Water Scarcity Information Service (GLOWASIS). FEWS-World incorporates the distributed global hydrological model PCR-GLOBWB (PCRaster Global Water Balance). We produce ensemble forecasts of monthly discharges for 20 large rivers of the world, with lead times of up to 6 months, forcing the system with bias-corrected seasonal meteorological forecast ensembles from the European Centre for Medium-range Weather Forecasts (ECMWF) and with probabilistic meteorological ensembles obtained following the ESP procedure. Here, the ESP ensembles, which contain no actual information on weather, serve as a benchmark to assess the additional skill that may be obtained using ECMWF seasonal forecasts. We use the Brier skill score (BSS) to quantify the skill of the system in forecasting high and low flows, defined as discharges higher than the 75th and lower than the 25th percentiles for a given month, respectively. We determine the theoretical skill by comparing the results against model simulations and the actual skill in comparison to discharge observations. We calculate the ratios of actual-to-theoretical skill in order to quantify the percentage of the potential skill that is achieved. The results suggest that the performance of ECMWF S3 forecasts is close to that of the ESP forecasts. While better meteorological forecasts could potentially lead to an improvement in hydrological forecasts, this cannot be achieved yet using the ECMWF S3 dataset.

  18. Crime Forecasting System (An exploratory web-based approach

    Directory of Open Access Journals (Sweden)

    Yaseen Ahmed Meenai

    2011-08-01

    Full Text Available With the continuous rise in crimes in some big cities of the world like Karachi and the increasing complexity of these crimes, the difficulties the law enforcing agencies are facing in tracking down and taking out culprits have increased manifold. To help cut back the crime rate, a Crime Forecasting System (CFS can be used which uses historical information maintained by the local Police to help them predict crime patterns with the support of a huge and self-updating database. This system operates to prevent crime, helps in apprehending criminals, and to reduce disorder. This system is also vital in helping the law enforcers in forming a proactive approach by helping them in identifying early warning signs, take timely and necessary actions, and eventually help stop crime before it actually happens. It will also be beneficial in maintaining an up to date database of criminal suspects includes information on arrest records, communication with police department, associations with other known suspects, and membership in gangs/activist groups. After exploratory analysis of the online data acquired from the victims of these crimes, a broad picture of the scenario can be analyzed. The degree of vulnerability of an area at some particular moment can be highlighted by different colors aided by Google Maps. Some statistical diagrams have also been incorporated. The future of CFS can be seen as an information engine for the analysis, study and prediction of crimes.

  19. Forecasting the Dst index using a swarm-optimized neural network

    Science.gov (United States)

    Lazzús, J. A.; Vega, P.; Rojas, P.; Salfate, I.

    2017-08-01

    A hybrid technique that combines an artificial neural network with a particle swarm optimization (ANN+PSO) was used to forecast the disturbance storm time (Dst) index from 1 to 6 h ahead. Our ANN was optimized by PSO to update ANN weights and to predict the short-term Dst index using past values as input parameters. The database used contains 233,760 hourly data from 1 January 1990 to 31 August 2016, considering storms and quiet period, grouped into three data sets: learning set (with 116,880 hourly data points), validation set (with 58,440 data points), and testing set (with 58,440 data points). Several ANN topologies were studied, and the best architecture was determined by systematically adding neurons and evaluating the root-mean-square error (RMSE) and the correlation coefficient (R) during the training process. These results show that the hybrid algorithm is a powerful technique for forecasting the Dst index a short time in advance like t + 1 to t + 3, with RMSE from 3.5 nT to 7.5 nT, and R from 0.98 to 0.90. However, t + 4 to t + 6 predictions become slightly more uncertain, with RMSE from 8.8 nT to 10.9 nT, and R from 0.86 to 0.79. Additionally, an exhaustive analysis according to geomagnetic storm magnitude was conducted. In general, the results show that our hybrid algorithm can be correctly trained to forecast the Dst index with appropriate precision and that Dst past behavior significantly affects adequate training and predicting capabilities of the implemented ANN.

  20. PM(10) emission forecasting using artificial neural networks and genetic algorithm input variable optimization.

    Science.gov (United States)

    Antanasijević, Davor Z; Pocajt, Viktor V; Povrenović, Dragan S; Ristić, Mirjana Đ; Perić-Grujić, Aleksandra A

    2013-01-15

    This paper describes the development of an artificial neural network (ANN) model for the forecasting of annual PM(10) emissions at the national level, using widely available sustainability and economical/industrial parameters as inputs. The inputs for the model were selected and optimized using a genetic algorithm and the ANN was trained using the following variables: gross domestic product, gross inland energy consumption, incineration of wood, motorization rate, production of paper and paperboard, sawn wood production, production of refined copper, production of aluminum, production of pig iron and production of crude steel. The wide availability of the input parameters used in this model can overcome a lack of data and basic environmental indicators in many countries, which can prevent or seriously impede PM emission forecasting. The model was trained and validated with the data for 26 EU countries for the period from 1999 to 2006. PM(10) emission data, collected through the Convention on Long-range Transboundary Air Pollution - CLRTAP and the EMEP Programme or as emission estimations by the Regional Air Pollution Information and Simulation (RAINS) model, were obtained from Eurostat. The ANN model has shown very good performance and demonstrated that the forecast of PM(10) emission up to two years can be made successfully and accurately. The mean absolute error for two-year PM(10) emission prediction was only 10%, which is more than three times better than the predictions obtained from the conventional multi-linear regression and principal component regression models that were trained and tested using the same datasets and input variables. Copyright © 2012 Elsevier B.V. All rights reserved.

  1. Flow Forecasting in Drainage Systems with Extrapolated Radar Rainfall Data and Auto Calibration on Flow Observations

    DEFF Research Database (Denmark)

    Thorndahl, Søren Liedtke; Grum, M.; Rasmussen, Michael R.

    2011-01-01

    in a small urban catchment has been developed. The forecast is based on application of radar rainfall data, which by a correlation based technique, is extrapolated with a lead time up to two hours. The runoff forecast in the drainage system is based on a fully distributed MOUSE model which is auto...

  2. Skill of a global seasonal streamflow forecasting system, relative roles of initial conditions and meteorological forcing

    NARCIS (Netherlands)

    Yossef, N.C.; Winsemius, H.; Weerts, A.H.; Beek, van R.; Bierkens, M.F.P.

    2013-01-01

    We investigate the relative contributions of initial conditions (ICs) and meteorological forcing (MF) to the skill of the global seasonal streamflow forecasting system FEWS-World, using the global hydrological model PCRaster Global Water Balance. Potential improvement in forecasting skill through

  3. Computer Networks A Systems Approach

    CERN Document Server

    Peterson, Larry L

    2011-01-01

    This best-selling and classic book teaches you the key principles of computer networks with examples drawn from the real world of network and protocol design. Using the Internet as the primary example, the authors explain various protocols and networking technologies. Their systems-oriented approach encourages you to think about how individual network components fit into a larger, complex system of interactions. Whatever your perspective, whether it be that of an application developer, network administrator, or a designer of network equipment or protocols, you will come away with a "big pictur

  4. Operational seasonal forecast system development in South Africa

    CSIR Research Space (South Africa)

    Landman, WA

    2011-09-01

    Full Text Available -Normal Above-Normal New objective multi-model forecast Old subjective consensus forecast MOS post-processing and forecast combination Multi-model ensemble of N1+N2+N3+N4 +N5 +N6 +N7 +N8 +N9 members Ensemble 1 CCAM at CSIR NRE N1 members Ensemble 2... ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?? Example of coupled model work: The state-of-the-art Coupled GCM Implementation: ? ? Coupling procedure: ? ? ? ? Initialization strategy: ? Initialized using best available information of the ocean and atmosphere state ? Each hindcast run...

  5. A combined road weather forecast system to prevent road ice formation in the Adige Valley (Italy)

    Science.gov (United States)

    Di Napoli, Claudia; Piazza, Andrea; Antonacci, Gianluca; Todeschini, Ilaria; Apolloni, Roberto; Pretto, Ilaria

    2016-04-01

    Road ice is a dangerous meteorological hazard to a nation's transportation system and economy. By reducing the pavement friction with vehicle tyres, ice formation on pavements increases accident risk and delays travelling times thus posing a serious threat to road users' safety and the running of economic activities. Keeping roads clear and open is therefore essential, especially in mountainous areas where ice is likely to form during the winter period. Winter road maintenance helps to restore road efficiency and security, and its benefits are up to 8 times the costs sustained for anti-icing strategies [1]. However, the optimization of maintenance costs and the reduction of the environmental damage from over-salting demand further improvements. These can be achieved by reliable road weather forecasts, and in particular by the prediction of road surface temperatures (RSTs). RST is one of the most important parameters in determining road surface conditions. It is well known from literature that ice forms on pavements in high-humidity conditions when RSTs are below 0°C. We have therefore implemented an automatic forecast system to predict critical RSTs on a test route along the Adige Valley complex terrain, in the Italian Alps. The system considers two physical models, each computing heat and energy fluxes between the road and the atmosphere. One is Reuter's radiative cooling model, which predicts RSTs at sunrise as a function of surface temperatures at sunset and the time passed since then [2]. One is METRo (Model of the Environment and Temperature of Roads), a road weather forecast software which also considers heat conduction through road material [3]. We have applied the forecast system to a network of road weather stations (road weather information system, RWIS) installed on the test route [4]. Road and atmospheric observations from RWIS have been used as initial conditions for both METRo and Reuter's model. In METRo observations have also been coupled to

  6. Forecasting Electricity Demand in Thailand with an Artificial Neural Network Approach

    Directory of Open Access Journals (Sweden)

    Karin Kandananond

    2011-08-01

    Full Text Available Demand planning for electricity consumption is a key success factor for the development of any countries. However, this can only be achieved if the demand is forecasted accurately. In this research, different forecasting methods—autoregressive integrated moving average (ARIMA, artificial neural network (ANN and multiple linear regression (MLR—were utilized to formulate prediction models of the electricity demand in Thailand. The objective was to compare the performance of these three approaches and the empirical data used in this study was the historical data regarding the electricity demand (population, gross domestic product: GDP, stock index, revenue from exporting industrial products and electricity consumption in Thailand from 1986 to 2010. The results showed that the ANN model reduced the mean absolute percentage error (MAPE to 0.996%, while those of ARIMA and MLR were 2.80981 and 3.2604527%, respectively. Based on these error measures, the results indicated that the ANN approach outperformed the ARIMA and MLR methods in this scenario. However, the paired test indicated that there was no significant difference among these methods at α = 0.05. According to the principle of parsimony, the ARIMA and MLR models might be preferable to the ANN one because of their simple structure and competitive performance

  7. Forecasting Method for Urban Rail Transit Ridership at Station Level Using Back Propagation Neural Network

    Directory of Open Access Journals (Sweden)

    Junfang Li

    2016-01-01

    Full Text Available Direct forecasting method for Urban Rail Transit (URT ridership at the station level is not able to reflect nonlinear relationship between ridership and its predictors. Also, population is inappropriately expressed in this method since it is not uniformly distributed by area. In this paper, a new variable, population per distance band, is considered and a back propagation neural network (BPNN model which can reflect nonlinear relationship between ridership and its predictors is proposed to forecast ridership. Key predictors are obtained through partial correlation analysis. The performance of the proposed model is compared with three other benchmark models, which are linear model with population per distance band, BPNN model with total population, and linear model with total population, using four measures of effectiveness (MOEs, maximum relative error (MRE, smallest relative error (SRE, average relative error (ARE, and mean square root of relative error (MSRRE. Also, another model for contribution rate of population per distance band to ridership is formulated based on the BPNN model with nonpopulation variables fixed. Case studies with Japanese data show that BPNN model with population per distance band outperforms other three models and the contribution rate of population within special distance band to ridership calculated through the contribution rate model is 70%~92.9% close to actual statistical value. The result confirms the effectiveness of models proposed in this paper.

  8. Oregon Washington Coastal Ocean Forecast System: Real-time Modeling and Data Assimilation

    Science.gov (United States)

    Erofeeva, S.; Kurapov, A. L.; Pasmans, I.

    2016-02-01

    Three-day forecasts of ocean currents, temperature and salinity along the Oregon and Washington coasts are produced daily by a numerical ROMS-based ocean circulation model. NAM is used to derive atmospheric forcing for the model. Fresh water discharge from Columbia River, Fraser River, and small rivers in Puget Sound are included. The forecast is constrained by open boundary conditions derived from the global Navy HYCOM model and once in 3 days assimilation of recent data, including HF radar surface currents, sea surface temperature from the GOES satellite, and SSH from several satellite altimetry missions. 4-dimensional variational data assimilation is implemented in 3-day time windows using the tangent linear and adjoint codes developed at OSU. The system is semi-autonomous - all the data, including NAM and HYCOM fields are automatically updated, and daily operational forecast is automatically initiated. The pre-assimilation data quality control and post-assimilation forecast quality control require the operator's involvement. The daily forecast and 60 days of hindcast fields are available for public on opendap. As part of the system model validation plots to various satellites and SEAGLIDER are also automatically updated and available on the web (http://ingria.coas.oregonstate.edu/rtdavow/). Lessons learned in this pilot real-time coastal ocean forecasting project help develop and test metrics for forecast skill assessment for the West Coast Operational Forecast System (WCOFS), currently at testing and development phase at the National Oceanic and Atmospheric Administration (NOAA).

  9. The state of the art of flood forecasting - Hydrological Ensemble Prediction Systems

    Science.gov (United States)

    Thielen-Del Pozo, J.; Pappenberger, F.; Salamon, P.; Bogner, K.; Burek, P.; de Roo, A.

    2010-09-01

    Flood forecasting systems form a key part of ‘preparedness' strategies for disastrous floods and provide hydrological services, civil protection authorities and the public with information of upcoming events. Provided the warning leadtime is sufficiently long, adequate preparatory actions can be taken to efficiently reduce the impacts of the flooding. Because of the specific characteristics of each catchment, varying data availability and end-user demands, the design of the best flood forecasting system may differ from catchment to catchment. However, despite the differences in concept and data needs, there is one underlying issue that spans across all systems. There has been an growing awareness and acceptance that uncertainty is a fundamental issue of flood forecasting and needs to be dealt with at the different spatial and temporal scales as well as the different stages of the flood generating processes. Today, operational flood forecasting centres change increasingly from single deterministic forecasts to probabilistic forecasts with various representations of the different contributions of uncertainty. The move towards these so-called Hydrological Ensemble Prediction Systems (HEPS) in flood forecasting represents the state of the art in forecasting science, following on the success of the use of ensembles for weather forecasting (Buizza et al., 2005) and paralleling the move towards ensemble forecasting in other related disciplines such as climate change predictions. The use of HEPS has been internationally fostered by initiatives such as "The Hydrologic Ensemble Prediction Experiment" (HEPEX), created with the aim to investigate how best to produce, communicate and use hydrologic ensemble forecasts in hydrological short-, medium- und long term prediction of hydrological processes. The advantages of quantifying the different contributions of uncertainty as well as the overall uncertainty to obtain reliable and useful flood forecasts also for extreme events

  10. Verification of ECMWF System 4 for seasonal hydrological forecasting in a northern climate

    Science.gov (United States)

    Bazile, Rachel; Boucher, Marie-Amélie; Perreault, Luc; Leconte, Robert

    2017-11-01

    Hydropower production requires optimal dam and reservoir management to prevent flooding damage and avoid operation losses. In a northern climate, where spring freshet constitutes the main inflow volume, seasonal forecasts can help to establish a yearly strategy. Long-term hydrological forecasts often rely on past observations of streamflow or meteorological data. Another alternative is to use ensemble meteorological forecasts produced by climate models. In this paper, those produced by the ECMWF (European Centre for Medium-Range Forecast) System 4 are examined and bias is characterized. Bias correction, through the linear scaling method, improves the performance of the raw ensemble meteorological forecasts in terms of continuous ranked probability score (CRPS). Then, three seasonal ensemble hydrological forecasting systems are compared: (1) the climatology of simulated streamflow, (2) the ensemble hydrological forecasts based on climatology (ESP) and (3) the hydrological forecasts based on bias-corrected ensemble meteorological forecasts from System 4 (corr-DSP). Simulated streamflow computed using observed meteorological data is used as benchmark. Accounting for initial conditions is valuable even for long-term forecasts. ESP and corr-DSP both outperform the climatology of simulated streamflow for lead times from 1 to 5 months depending on the season and watershed. Integrating information about future meteorological conditions also improves monthly volume forecasts. For the 1-month lead time, a gain exists for almost all watersheds during winter, summer and fall. However, volume forecasts performance for spring varies from one watershed to another. For most of them, the performance is close to the performance of ESP. For longer lead times, the CRPS skill score is mostly in favour of ESP, even if for many watersheds, ESP and corr-DSP have comparable skill. Corr-DSP appears quite reliable but, in some cases, under-dispersion or bias is observed. A more complex bias

  11. The Stevens Integrated Maritime Surveillance Forecast System: Expansion and Enhancement

    National Research Council Canada - National Science Library

    Bruno, Michael S; Blumberg, Alan F

    2006-01-01

    ... for the real-time assessment of ocean, weather, environmental, and vessel traffic conditions throughout the New York Harbor region, and the forecast of conditions in the near and long-term and under specific threat scenarios...

  12. Forecasting Wind and Solar Generation: Improving System Operations, Greening the Grid

    Energy Technology Data Exchange (ETDEWEB)

    Tian; Tian; Chernyakhovskiy, Ilya

    2016-01-01

    This document discusses improving system operations with forecasting and solar generation. By integrating variable renewable energy (VRE) forecasts into system operations, power system operators can anticipate up- and down-ramps in VRE generation in order to cost-effectively balance load and generation in intra-day and day-ahead scheduling. This leads to reduced fuel costs, improved system reliability, and maximum use of renewable resources.

  13. The combined use of weather radar and geographic information system techniques for flood forecasting

    Directory of Open Access Journals (Sweden)

    E. Baltas

    2007-01-01

    Full Text Available A distributed rainfall-runoff model capable for real time flood forecasting utilizing highly spatial and time resolution data was developed. The study region is located under the WSR-74 S-band 100 km radar umbrella and is equipped with a number of rain gauge recording stations, a permanent installation for flow measurement and a stage recorder. The entire basin was digitized to 2×2 km2 grid squares by implying GIS techniques. A series of rainfall events recorded producing floods were analyzed and processed. The linear channel parameter assigned to each grid-square is based on its location measured by the centroid of the grid square along the channel network. The estimation of the hill-slope and the stream velocity are calculated based on the Geographic Information System (GIS procedures.

  14. Rapid Retrieval and Assimilation of Ground Based GPS-Met Observations at the NOAA Forecast Systems Laboratory: Impact on Weather Forecasts

    Science.gov (United States)

    Gutman, S.

    2003-04-01

    shorter forecast cycles and higher spatial resolution in mesoscale numerical weather prediction (NWP) models, and the use by weather forecasters in subjective forecasting and/or model verification. GPS and ancillary surface meteorological observations, and improved satellite orbits, must be available on demand. Data processing hardware and techniques must provide GPS-Met retrievals in sufficient time to be assimilated into the current model cycle. Model data assimilation techniques must minimize the errors in estimating the initial state of a numerical forecast that come from spatial and temporal aliasing when interpolating discrete observations into an "analysis increment" field. While more GPS-Met retrievals can minimize horizontal aliasing, they can do little to minimize vertical aliasing that comes from assimilating any vertically integrated quantity (e.g. satellite radiances, zenith tropospheric signal delays, or GPS-IPW retrievals) into an NWP model. This is primarily because the forecast background error at a discrete vertical level must be estimated from the difference between observed and forecast integrated quantities. Absent the development of a new observing system or measurement technique, we must rely on improved data assimilation techniques, coupled with the more efficient use of complementary observing systems, to improve the three-dimensional description of moisture in the atmosphere. NOAA/FSL has conducted data denial experiments since 1998 to determine the statistical impact that GPS-IPW retrievals have on 3-hour moisture and precipitation forecasts in the central United States. Results from 5-years of experiments indicate more or less continuous improvement in forecast skill as the GPS-Met network expands. Improvements are observed in relative humidity forecast accuracy at all levels below 500 hPa, and all precipitation levels above “trace”. The impact steadily decreases with the length of the forecast; it is usually substantial from 0-3 hours, and

  15. Forecasting outpatient visits using empirical mode decomposition coupled with back-propagation artificial neural networks optimized by particle swarm optimization.

    Science.gov (United States)

    Huang, Daizheng; Wu, Zhihui

    2017-01-01

    Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods.

  16. Artificial Neural Networks (ANNs for flood forecasting at Dongola Station in the River Nile, Sudan

    Directory of Open Access Journals (Sweden)

    Sulafa Hag Elsafi

    2014-09-01

    Full Text Available Heavy seasonal rains cause the River Nile in Sudan to overflow and flood the surroundings areas. The floods destroy houses, crops, roads, and basic infrastructure, resulting in the displacement of people. This study aimed to forecast the River Nile flow at Dongola Station in Sudan using an Artificial Neural Network (ANN as a modeling tool and validated the accuracy of the model against actual flow. The ANN model was formulated to simulate flows at a certain location in the river reach, based on flow at upstream locations. Different procedures were applied to predict flooding by the ANN. Readings from stations along the Blue Nile, White Nile, Main Nile, and River Atbara between 1965 and 2003 were used to predict the likelihood of flooding at Dongola Station. The analysis indicated that the ANN provides a reliable means of detecting the flood hazard in the River Nile.

  17. Application of Artificial Neural Network into the Water Level Modeling and Forecast

    Directory of Open Access Journals (Sweden)

    Marzenna Sztobryn

    2013-06-01

    Full Text Available The dangerous sea and river water level increase does not only destroy the human lives, but also generate the severe flooding in coastal areas. The rapidly changes in the direction and velocity of wind and associated with them sea level changes could be the severe threat for navigation, especially on the fairways of small fishery harbors located in the river mouth. There is the area of activity of two external forcing: storm surges and flood wave. The aim of the work was the description of an application of Artificial Neural Network (ANN methodology into the water level forecast in the case study field in Swibno harbor located is located at 938.7 km of the Wisla River and at a distance of about 3 km up the mouth (Gulf of Gdansk - Baltic Sea.

  18. Short-term spatio-temporal wind power forecast in robust look-ahead power system dispatch

    KAUST Repository

    Xie, Le

    2014-01-01

    We propose a novel statistical wind power forecast framework, which leverages the spatio-temporal correlation in wind speed and direction data among geographically dispersed wind farms. Critical assessment of the performance of spatio-temporal wind power forecast is performed using realistic wind farm data from West Texas. It is shown that spatio-temporal wind forecast models are numerically efficient approaches to improving forecast quality. By reducing uncertainties in near-term wind power forecasts, the overall cost benefits on system dispatch can be quantified. We integrate the improved forecast with an advanced robust look-ahead dispatch framework. This integrated forecast and economic dispatch framework is tested in a modified IEEE RTS 24-bus system. Numerical simulation suggests that the overall generation cost can be reduced by up to 6% using a robust look-ahead dispatch coupled with spatio-temporal wind forecast as compared with persistent wind forecast models. © 2013 IEEE.

  19. System learning approach to assess sustainability and forecast trends in regional dynamics: The San Luis Basin study, Colorado, U.S.A.

    Science.gov (United States)

    This paper presents a methodology that combines the power of an Artificial Neural Network and Information Theory to forecast variables describing the condition of a regional system. The novelty and strength of this approach is in the application of Fisher information, a key metho...

  20. The use of a dense urban meteorological network to enable long term electricity consumption forecasting

    Science.gov (United States)

    Antunes de Azevedo, J.

    2015-12-01

    High air temperatures have an impact on energy consumption, since the demand for cooling fans and air conditioning increases. With current climate projections indicating a general increase in air temperatures, as well as more frequent and intense heat waves, cooling energy demand will increase with time and should therefore be considered by industry and policy makers. Cooling degree days (CDD) are a standard approach used by energy industry to estimate cooling demand. The methodology compares ambient temperatures with a base value for air temperature considered representative of the city being analysed. However, due to the Urban Heat Island effect, temperature and energy consumption will vary considerably across a city. Hence, for CDD to be estimated across an urban area, air temperature data from dense urban networks are required. This study analysed air temperature data available from a dense urban meteorological network to estimate CDD and cooling needs across Birmingham-UK for summer 2013. From the results, it was possible to identify the potential role and limitations of urban meteorological networks in forecasting electricity demand within a city for future climate scenarios.

  1. Using wavelet-feedforward neural networks to improve air pollution forecasting in urban environments.

    Science.gov (United States)

    Dunea, Daniel; Pohoata, Alin; Iordache, Stefania

    2015-07-01

    The paper presents the screening of various feedforward neural networks (FANN) and wavelet-feedforward neural networks (WFANN) applied to time series of ground-level ozone (O3), nitrogen dioxide (NO2), and particulate matter (PM10 and PM2.5 fractions) recorded at four monitoring stations located in various urban areas of Romania, to identify common configurations with optimal generalization performance. Two distinct model runs were performed as follows: data processing using hourly-recorded time series of airborne pollutants during cold months (O3, NO2, and PM10), when residential heating increases the local emissions, and data processing using 24-h daily averaged concentrations (PM2.5) recorded between 2009 and 2012. Dataset variability was assessed using statistical analysis. Time series were passed through various FANNs. Each time series was decomposed in four time-scale components using three-level wavelets, which have been passed also through FANN, and recomposed into a single time series. The agreement between observed and modelled output was evaluated based on the statistical significance (r coefficient and correlation between errors and data). Daubechies db3 wavelet-Rprop FANN (6-4-1) utilization gave positive results for O3 time series optimizing the exclusive use of the FANN for hourly-recorded time series. NO2 was difficult to model due to time series specificity, but wavelet integration improved FANN performances. Daubechies db3 wavelet did not improve the FANN outputs for PM10 time series. Both models (FANN/WFANN) overestimated PM2.5 forecasted values in the last quarter of time series. A potential improvement of the forecasted values could be the integration of a smoothing algorithm to adjust the PM2.5 model outputs.

  2. Systemic change increases forecast uncertainty of land use change models

    Science.gov (United States)

    Verstegen, J. A.; Karssenberg, D.; van der Hilst, F.; Faaij, A.

    2013-12-01

    Cellular Automaton (CA) models of land use change are based on the assumption that the relationship between land use change and its explanatory processes is stationary. This means that model structure and parameterization are usually kept constant over time, ignoring potential systemic changes in this relationship resulting from societal changes, thereby overlooking a source of uncertainty. Evaluation of the stationarity of the relationship between land use and a set of spatial attributes has been done by others (e.g., Bakker and Veldkamp, 2012). These studies, however, use logistic regression, separate from the land use change model. Therefore, they do not gain information on how to implement the spatial attributes into the model. In addition, they often compare observations for only two points in time and do not check whether the change is statistically significant. To overcome these restrictions, we assimilate a time series of observations of real land use into a land use change CA (Verstegen et al., 2012), using a Bayesian data assimilation technique, the particle filter. The particle filter was used to update the prior knowledge about the parameterization and model structure, i.e. the selection and relative importance of the drivers of location of land use change. In a case study of sugar cane expansion in Brazil, optimal model structure and parameterization were determined for each point in time for which observations were available (all years from 2004 to 2012). A systemic change, i.e. a statistically significant deviation in model structure, was detected for the period 2006 to 2008. In this period the influence on the location of sugar cane expansion of the driver sugar cane in the neighborhood doubled, while the influence of slope and potential yield decreased by 75% and 25% respectively. Allowing these systemic changes to occur in our CA in the future (up to 2022) resulted in an increase in model forecast uncertainty by a factor two compared to the

  3. Comparison of different forms of the Multi-layer Feed-Forward Neural Network method used for river flow forecasting

    Science.gov (United States)

    Shamseldin, A. Y.; Nasr, A. E.; O'Connor, K. M.

    The Multi-Layer Feed-Forward Neural Network (MLFFNN) is applied in the context of river flow forecast combination, where a number of rainfall-runoff models are used simultaneously to produce an overall combined river flow forecast. The operation of the MLFFNN depends not only on its neuron configuration but also on the choice of neuron transfer function adopted, which is non-linear for the hidden and output layers. These models, each having a different structure to simulate the perceived mechanisms of the runoff process, utilise the information carrying capacity of the model calibration data in different ways. Hence, in a discharge forecast combination procedure, the discharge forecasts of each model provide a source of information different from that of the other models used in the combination. In the present work, the significance of the choice of the transfer function type in the overall performance of the MLFFNN, when used in the river flow forecast combination context, is investigated critically. Five neuron transfer functions are used in this investigation, namely, the logistic function, the bipolar function, the hyperbolic tangent function, the arctan function and the scaled arctan function. The results indicate that the logistic function yields the best model forecast combination performance.

  4. Spectral Analysis of Forecast Error Investigated with an Observing System Simulation Experiment

    Science.gov (United States)

    Prive, N. C.; Errico, Ronald M.

    2015-01-01

    The spectra of analysis and forecast error are examined using the observing system simulation experiment (OSSE) framework developed at the National Aeronautics and Space Administration Global Modeling and Assimilation Office (NASAGMAO). A global numerical weather prediction model, the Global Earth Observing System version 5 (GEOS-5) with Gridpoint Statistical Interpolation (GSI) data assimilation, is cycled for two months with once-daily forecasts to 336 hours to generate a control case. Verification of forecast errors using the Nature Run as truth is compared with verification of forecast errors using self-analysis; significant underestimation of forecast errors is seen using self-analysis verification for up to 48 hours. Likewise, self analysis verification significantly overestimates the error growth rates of the early forecast, as well as mischaracterizing the spatial scales at which the strongest growth occurs. The Nature Run-verified error variances exhibit a complicated progression of growth, particularly for low wave number errors. In a second experiment, cycling of the model and data assimilation over the same period is repeated, but using synthetic observations with different explicitly added observation errors having the same error variances as the control experiment, thus creating a different realization of the control. The forecast errors of the two experiments become more correlated during the early forecast period, with correlations increasing for up to 72 hours before beginning to decrease.

  5. Spectral analysis of forecast error investigated with an observing system simulation experiment

    Directory of Open Access Journals (Sweden)

    Nikki C. Privé

    2015-02-01

    Full Text Available The spectra of analysis and forecast error are examined using the observing system simulation experiment framework developed at the National Aeronautics and Space Administration Global Modeling and Assimilation Office. A global numerical weather prediction model, the Global Earth Observing System version 5 with Gridpoint Statistical Interpolation data assimilation, is cycled for 2 months with once-daily forecasts to 336 hours to generate a Control case. Verification of forecast errors using the nature run (NR as truth is compared with verification of forecast errors using self-analysis; significant underestimation of forecast errors is seen using self-analysis verification for up to 48 hours. Likewise, self-analysis verification significantly overestimates the error growth rates of the early forecast, as well as mis-characterising the spatial scales at which the strongest growth occurs. The NR-verified error variances exhibit a complicated progression of growth, particularly for low wavenumber errors. In a second experiment, cycling of the model and data assimilation over the same period is repeated, but using synthetic observations with different explicitly added observation errors having the same error variances as the control experiment, thus creating a different realisation of the control. The forecast errors of the two experiments become more correlated during the early forecast period, with correlations increasing for up to 72 hours before beginning to decrease.

  6. ECMWF seasonal forecast system 3 and its prediction of sea surface temperature

    Energy Technology Data Exchange (ETDEWEB)

    Stockdale, Timothy N.; Anderson, David L.T.; Balmaseda, Magdalena A.; Ferranti, Laura; Mogensen, Kristian; Palmer, Timothy N.; Molteni, Franco; Vitart, Frederic [ECMWF, Reading (United Kingdom); Doblas-Reyes, Francisco [ECMWF, Reading (United Kingdom); Institut Catala de Ciencies del Clima (IC3), Barcelona (Spain)

    2011-08-15

    The latest operational version of the ECMWF seasonal forecasting system is described. It shows noticeably improved skill for sea surface temperature (SST) prediction compared with previous versions, particularly with respect to El Nino related variability. Substantial skill is shown for lead times up to 1 year, although at this range the spread in the ensemble forecast implies a loss of predictability large enough to account for most of the forecast error variance, suggesting only moderate scope for improving long range El Nino forecasts. At shorter ranges, particularly 3-6 months, skill is still substantially below the model-estimated predictability limit. SST forecast skill is higher for more recent periods than earlier ones. Analysis shows that although various factors can affect scores in particular periods, the improvement from 1994 onwards seems to be robust, and is most plausibly due to improvements in the observing system made at that time. The improvement in forecast skill is most evident for 3-month forecasts starting in February, where predictions of NINO3.4 SST from 1994 to present have been almost without fault. It is argued that in situations where the impact of model error is small, the value of improved observational data can be seen most clearly. Significant skill is also shown in the equatorial Indian Ocean, although predictive skill in parts of the tropical Atlantic are relatively poor. SST forecast errors can be especially high in the Southern Ocean. (orig.)

  7. Uncertainty quantification and reliability assessment in operational oil spill forecast modeling system.

    Science.gov (United States)

    Hou, Xianlong; Hodges, Ben R; Feng, Dongyu; Liu, Qixiao

    2017-03-15

    As oil transport increasing in the Texas bays, greater risks of ship collisions will become a challenge, yielding oil spill accidents as a consequence. To minimize the ecological damage and optimize rapid response, emergency managers need to be informed with how fast and where oil will spread as soon as possible after a spill. The state-of-the-art operational oil spill forecast modeling system improves the oil spill response into a new stage. However uncertainty due to predicted data inputs often elicits compromise on the reliability of the forecast result, leading to misdirection in contingency planning. Thus understanding the forecast uncertainty and reliability become significant. In this paper, Monte Carlo simulation is implemented to provide parameters to generate forecast probability maps. The oil spill forecast uncertainty is thus quantified by comparing the forecast probability map and the associated hindcast simulation. A HyosPy-based simple statistic model is developed to assess the reliability of an oil spill forecast in term of belief degree. The technologies developed in this study create a prototype for uncertainty and reliability analysis in numerical oil spill forecast modeling system, providing emergency managers to improve the capability of real time operational oil spill response and impact assessment. Copyright © 2017 Elsevier Ltd. All rights reserved.

  8. An innovative forecasting and dashboard system for Malaysian dengue trends

    Science.gov (United States)

    Jamil, Jastini Mohd; Shaharanee, Izwan Nizal Mohd

    2016-08-01

    Dengue fever has been recognized in over 100 countries and 2.5 billion people live in areas where dengue is endemic. It is currently a serious arthropod-borne disease, affecting around 50-100 million people worldwide every year. Dengue fever is also prevalent in Malaysia with numerous cases including mortality recorded over the past year. In 2012, a total of 21,900 cases of dengue fever were reported with 35 deaths. Dengue, a mosquito-transmitted virus, causes a high fever accompanied by significant pain in afflicted patient and the Aedes Aegypti mosquito is the primary disease carrier. Knowing the dangerous effect of dengue fever, thus one of the solutions is to implement an innovative forecasting and dashboard system of dengue spread in Malaysia, with emphasize on an early prediction of dengue outbreak. Specifically, the model developed will provide with a valuable insight into strategically managing and controlling the future dengue epidemic. Importantly, this research will deliver the message to health policy makers such as The Ministry of Health Malaysia (MOH), practitioners, and researchers of the importance to integrate their collaboration in exploring the potential strategies in order to reduce the future burden of the increase in dengue transmission cases in Malaysia.

  9. Short-term residential load forecasting: Impact of calendar effects and forecast granularity

    DEFF Research Database (Denmark)

    Lusis, Peter; Khalilpour, Kaveh Rajab; Andrew, Lachlan

    2017-01-01

    Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load...... forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads. This paper studies...... how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector...

  10. Network of networks in Linux operating system

    Science.gov (United States)

    Wang, Haoqin; Chen, Zhen; Xiao, Guanping; Zheng, Zheng

    2016-04-01

    Operating system represents one of the most complex man-made systems. In this paper, we analyze Linux Operating System (LOS) as a complex network via modeling functions as nodes and function calls as edges. It is found that for the LOS network and modularized components within it, the out-degree follows an exponential distribution and the in-degree follows a power-law distribution. For better understanding the underlying design principles of LOS, we explore the coupling correlations of components in LOS from aspects of topology and function. The result shows that the component for device drivers has a strong manifestation in topology while a weak manifestation in function. However, the component for process management shows the contrary phenomenon. Moreover, in an effort to investigate the impact of system failures on networks, we make a comparison between the networks traced from normal and failure status of LOS. This leads to a conclusion that the failure will change function calls which should be executed in normal status and introduce new function calls in the meanwhile.

  11. Impact of Improved Solar Forecasts on Bulk Power System Operations in ISO-NE: Preprint

    Energy Technology Data Exchange (ETDEWEB)

    Brancucci Martinez-Anido, C.; Florita, A.; Hodge, B. M.

    2014-09-01

    The diurnal nature of solar power is made uncertain by variable cloud cover and the influence of atmospheric conditions on irradiance scattering processes. Its forecasting has become increasingly important to the unit commitment and dispatch process for efficient scheduling of generators in power system operations. This study examines the value of improved solar power forecasting for the Independent System Operator-New England system. The results show how 25% solar power penetration reduces net electricity generation costs by 22.9%.

  12. Recent advances in operational seasonal forecasting in South Africa: Models, infrastructure and networks

    CSIR Research Space (South Africa)

    Landman, WA

    2011-11-01

    Full Text Available The various institutions involved with seasonal forecast development and production are discussed. New modelling approaches and the establishment of infrastructures to improve forecast dissemination are discussed....

  13. Views of wireless network systems.

    Energy Technology Data Exchange (ETDEWEB)

    Young, William Frederick; Duggan, David Patrick

    2003-10-01

    Wireless networking is becoming a common element of industrial, corporate, and home networks. Commercial wireless network systems have become reliable, while the cost of these solutions has become more affordable than equivalent wired network solutions. The security risks of wireless systems are higher than wired and have not been studied in depth. This report starts to bring together information on wireless architectures and their connection to wired networks. We detail information contained on the many different views of a wireless network system. The method of using multiple views of a system to assist in the determination of vulnerabilities comes from the Information Design Assurance Red Team (IDART{trademark}) Methodology of system analysis developed at Sandia National Laboratories.

  14. Mapping biological systems to network systems

    CERN Document Server

    Rathore, Heena

    2016-01-01

    The book presents the challenges inherent in the paradigm shift of network systems from static to highly dynamic distributed systems – it proposes solutions that the symbiotic nature of biological systems can provide into altering networking systems to adapt to these changes. The author discuss how biological systems – which have the inherent capabilities of evolving, self-organizing, self-repairing and flourishing with time – are inspiring researchers to take opportunities from the biology domain and map them with the problems faced in network domain. The book revolves around the central idea of bio-inspired systems -- it begins by exploring why biology and computer network research are such a natural match. This is followed by presenting a broad overview of biologically inspired research in network systems -- it is classified by the biological field that inspired each topic and by the area of networking in which that topic lies. Each case elucidates how biological concepts have been most successfully ...

  15. Short-Term State Forecasting-Based Optimal Voltage Regulation in Distribution Systems: Preprint

    Energy Technology Data Exchange (ETDEWEB)

    Yang, Rui; Jiang, Huaiguang; Zhang, Yingchen

    2017-05-17

    A novel short-term state forecasting-based optimal power flow (OPF) approach for distribution system voltage regulation is proposed in this paper. An extreme learning machine (ELM) based state forecaster is developed to accurately predict system states (voltage magnitudes and angles) in the near future. Based on the forecast system states, a dynamically weighted three-phase AC OPF problem is formulated to minimize the voltage violations with higher penalization on buses which are forecast to have higher voltage violations in the near future. By solving the proposed OPF problem, the controllable resources in the system are optimally coordinated to alleviate the potential severe voltage violations and improve the overall voltage profile. The proposed approach has been tested in a 12-bus distribution system and simulation results are presented to demonstrate the performance of the proposed approach.

  16. Dynamic Hybrid Model for Short-Term Electricity Price Forecasting

    OpenAIRE

    Marin Cerjan; Marin Matijaš; Marko Delimar

    2014-01-01

    Accurate forecasting tools are essential in the operation of electric power systems, especially in deregulated electricity markets. Electricity price forecasting is necessary for all market participants to optimize their portfolios. In this paper we propose a hybrid method approach for short-term hourly electricity price forecasting. The paper combines statistical techniques for pre-processing of data and a multi-layer (MLP) neural network for forecasting electricity price and price spike det...

  17. Identification of the actual state and entity availability forecasting in power engineering using neural-network technologies

    Science.gov (United States)

    Protalinsky, O. M.; Shcherbatov, I. A.; Stepanov, P. V.

    2017-11-01

    A growing number of severe accidents in RF call for the need to develop a system that could prevent emergency situations. In a number of cases accident rate is stipulated by careless inspections and neglects in developing repair programs. Across the country rates of accidents are growing because of a so-called “human factor”. In this regard, there has become urgent the problem of identification of the actual state of technological facilities in power engineering using data on engineering processes running and applying artificial intelligence methods. The present work comprises four model states of manufacturing equipment of engineering companies: defect, failure, preliminary situation, accident. Defect evaluation is carried out using both data from SCADA and ASEPCR and qualitative information (verbal assessments of experts in subject matter, photo- and video materials of surveys processed using pattern recognition methods in order to satisfy the requirements). Early identification of defects makes possible to predict the failure of manufacturing equipment using mathematical techniques of artificial neural network. In its turn, this helps to calculate predicted characteristics of reliability of engineering facilities using methods of reliability theory. Calculation of the given parameters provides the real-time estimation of remaining service life of manufacturing equipment for the whole operation period. The neural networks model allows evaluating possibility of failure of a piece of equipment consistent with types of actual defects and their previous reasons. The article presents the grounds for a choice of training and testing samples for the developed neural network, evaluates the adequacy of the neural networks model, and shows how the model can be used to forecast equipment failure. There have been carried out simulating experiments using a computer and retrospective samples of actual values for power engineering companies. The efficiency of the developed

  18. Experimental Analysis of the Input Variables’ Relevance to Forecast Next Day’s Aggregated Electric Demand Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Pablo García

    2013-06-01

    Full Text Available Thanks to the built in intelligence (deployment of new intelligent devices and sensors in places where historically they were not present, the Smart Grid and Microgrid paradigms are able to take advantage from aggregated load forecasting, which opens the door for the implementation of new algorithms to seize this information for optimization and advanced planning. Therefore, accuracy in load forecasts will potentially have a big impact on key operation factors for the future Smart Grid/Microgrid-based energy network like user satisfaction and resource saving, and new methods to achieve an efficient prediction in future energy landscapes (very different from the centralized, big area networks studied so far. This paper proposes different improved models to forecast next day’s aggregated load using artificial neural networks, taking into account the variables that are most relevant for the aggregated. In particular, seven models based on the multilayer perceptron will be proposed, progressively adding input variables after analyzing the influence of climate factors on aggregated load. The results section presents the forecast from the proposed models, obtained from real data.

  19. Seasonal scale water deficit forecasting in Africa and the Middle East using NASA's Land Information System (LIS)

    Science.gov (United States)

    Shukla, Shraddhanand; Arsenault, Kristi R.; Getirana, Augusto; Kumar, Sujay V.; Roningen, Jeanne; Zaitchik, Ben; McNally, Amy; Koster, Randal D.; Peters-Lidard, Christa

    2017-04-01

    Drought and water scarcity are among the important issues facing several regions within Africa and the Middle East. A seamless and effective monitoring and early warning system is needed by regional/national stakeholders. Such system should support a proactive drought management approach and mitigate the socio-economic losses up to the extent possible. In this presentation, we report on the ongoing development and validation of a seasonal scale water deficit forecasting system based on NASA's Land Information System (LIS) and seasonal climate forecasts. First, our presentation will focus on the implementation and validation of the LIS models used for drought and water availability monitoring in the region. The second part will focus on evaluating drought and water availability forecasts. Finally, details will be provided of our ongoing collaboration with end-user partners in the region (e.g., USAID's Famine Early Warning Systems Network, FEWS NET), on formulating meaningful early warning indicators, effective communication and seamless dissemination of the monitoring and forecasting products through NASA's web-services. The water deficit forecasting system thus far incorporates NOAA's Noah land surface model (LSM), version 3.3, the Variable Infiltration Capacity (VIC) model, version 4.12, NASA GMAO's Catchment LSM, and the Noah Multi-Physics (MP) LSM (the latter two incorporate prognostic water table schemes). In addition, the LSMs' surface and subsurface runoff are routed through the Hydrological Modeling and Analysis Platform (HyMAP) to simulate surface water dynamics. The LSMs are driven by NASA/GMAO's Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2), and the USGS and UCSB Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) daily rainfall dataset. The LIS software framework integrates these forcing datasets and drives the four LSMs and HyMAP. The Land Verification Toolkit (LVT) is used for the evaluation of the

  20. Comparison of the economic impact of different wind power forecast systems for producers

    Science.gov (United States)

    Alessandrini, S.; Davò, F.; Sperati, S.; Benini, M.; Delle Monache, L.

    2014-05-01

    Deterministic forecasts of wind production for the next 72 h at a single wind farm or at the regional level are among the main end-users requirement. However, for an optimal management of wind power production and distribution it is important to provide, together with a deterministic prediction, a probabilistic one. A deterministic forecast consists of a single value for each time in the future for the variable to be predicted, while probabilistic forecasting informs on probabilities for potential future events. This means providing information about uncertainty (i.e. a forecast of the PDF of power) in addition to the commonly provided single-valued power prediction. A significant probabilistic application is related to the trading of energy in day-ahead electricity markets. It has been shown that, when trading future wind energy production, using probabilistic wind power predictions can lead to higher benefits than those obtained by using deterministic forecasts alone. In fact, by using probabilistic forecasting it is possible to solve economic model equations trying to optimize the revenue for the producer depending, for example, on the specific penalties for forecast errors valid in that market. In this work we have applied a probabilistic wind power forecast systems based on the "analog ensemble" method for bidding wind energy during the day-ahead market in the case of a wind farm located in Italy. The actual hourly income for the plant is computed considering the actual selling energy prices and penalties proportional to the unbalancing, defined as the difference between the day-ahead offered energy and the actual production. The economic benefit of using a probabilistic approach for the day-ahead energy bidding are evaluated, resulting in an increase of 23% of the annual income for a wind farm owner in the case of knowing "a priori" the future energy prices. The uncertainty on price forecasting partly reduces the economic benefit gained by using a

  1. Wind power forecasting system EOlienne SPEO : development, preliminary results and integration at Hydro-Quebec

    Energy Technology Data Exchange (ETDEWEB)

    Forcione, A.; Roberge, G. [Hydro-Quebec, Varennes, PQ (Canada). IREQ; Yu, W.; Glazer, A.; Benoit, R.; Plante, A.; Tran, L.D.; Chardon, L. [Environment Canada, Ottawa, ON (Canada)

    2007-07-01

    Wind generation forecasting at Hydro-Quebec was discussed with particular reference to the collaborative efforts between the utility's Research Institute and Environment Canada in developing the Systeme de Prevision EOlienne (SPEO). The European ANEMOS platform was installed at Hydro-Quebec Distribution in 2006. Operational forecasts using the Global Environmental Multi-scale model (GEM) from the Canadian Meteorological Centre served as input for SPEO. This presentation evaluated the performance of the forecasting model, and presented best approaches for long term use and continuous improvement. SPEO was developed to forecast wind and other atmospheric variables, and not generated power. The development of the software began in September 2006 with the development and integration of necessary components, followed by the calibration of the system, 15 months of operational forecasts, experimentation and final analysis in 2008. The GEM-global model provides 10 days and 240 hours of hourly forecasts with 35 km resolution, while the GEM-regional model provides 2 days and 48 hours of hourly forecasts with 15 km resolution. It was shown that the development of a good forecasting system depends entirely on the availability of a maximum number of observation sources, which for SPEO includes 13 Environment Canada stations and wind farm masts. The final value of a wind forecasting system also depends on compatibility with the electric system management tools and processes. Research is ongoing to improve SPEO through validation tools, integration of newly available observations, recalibration and experimentation. Future tasks will be to extend the 48 hour horizon, to optimize the number crunching efficiency and to characterize wind farms more precisely. figs.

  2. Flood Forecast Accuracy and Decision Support System Approach: the Venice Case

    Science.gov (United States)

    Canestrelli, A.; Di Donato, M.

    2016-02-01

    In the recent years numerical models for weather predictions have experienced continuous advances in technology. As a result, all the disciplines making use of weather forecasts have made significant steps forward. In the case of the Safeguard of Venice, a large effort has been put in order to improve the forecast of tidal levels. In this context, the Istituzione Centro Previsioni e Segnalazioni Maree (ICPSM) of the Venice Municipality has developed and tested many different forecast models, both of the statistical and deterministic type, and has shown to produce very accurate forecasts. For Venice, the maximum admissible forecast error should be (ideally) of the order of ten centimeters at 24 hours. The entity of the forecast error clearly affects the decisional process, which mainly consists of alerting the population, activating the movable barriers installed at the three tidal inlets and contacting the port authority. This process becomes more challenging whenever the weather predictions, and therefore the water level forecasts, suddenly change. These new forecasts have to be quickly transformed into operational tasks. Therefore, it is of the utter importance to set up scheduled alerts and emergency plans by means of easy-to-follow procedures. On this direction, Technital has set up a Decision Support System based on expert procedures that minimizes the human mistakes and, as a consequence, reduces the risk of flooding of the historical center. Moreover, the Decision Support System can communicate predefined alerts to all the interested subjects. The System uses the water levels forecasts produced by the ICPSM by taking into account the accuracy at different leading times. The Decision Support System has been successfully tested with 8 years of data, 6 of them in real time. Venice experience shows that the Decision Support System is an essential tool which assesses the risks associated with a particular event, provides clear operational procedures and minimizes

  3. DEVELOPMENT OF NEURAL NETWORKS FOR FORECASTING OF CHEMICAL SUBSTANCES’ MIGRATION IN SOIL AND ALGORITHMS OF THEIR TRAINING

    Directory of Open Access Journals (Sweden)

    S. P. Kundas

    2010-01-01

    Full Text Available A review of the existing models and methods for forecasting chemical substances' migration in soil is contained in the paper. The paper shows that the most effective decision for solving ecological tasks in this field is an application of artificial neural networks using training «with a tutor» on the basis of an inverse error propagation algorithm. Corresponding structures of  neural networks for solution of the given problem have been developed in the paper.A new method for artificial neural network training based on the modification of an inverse error propagation algorithm while using an additional signal is proposed in the paper. The given method allows to achieve 100% convergence in the forecasting problems pertaining to chemical substances' migration in soil. 

  4. COAWST Forecast System : USGS : US East Coast and Gulf of Mexico (Experimental)

    Data.gov (United States)

    U.S. Geological Survey, Department of the Interior — Experimental forecast model product from the USGS Coupled Ocean Atmosphere Wave Sediment-Transport (COAWST) modeling system. Data required to drive the modeling...

  5. MODELLING AND FORECAST OF CHARCOAL PRICES USING A NEURO-FUZZY SYSTEM

    National Research Council Canada - National Science Library

    Carlos Alberto Araújo Júnior; Liniker Fernandes da Silva; Marcio Lopes da Silva; Helio Garcia Leite; Erlon Barbosa Valdetaro; Danilo Barros Donato; Renato Vinícius Oliveira Castro

    2016-01-01

    Using a monthly time series of charcoal prices in Minas Gerais from January 2000 to September 2014, this study aimed to evaluate the use of neuro-fuzzy system to model the series and forecasting prices...

  6. COAWST Forecast System : USGS : US East Coast and Gulf of Mexico (Experimental)

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — Experimental forecast model product from the USGS Coupled Ocean Atmosphere Wave Sediment-Transport (COAWST) modeling system. Data required to drive the modeling...

  7. Performance of the ocean state forecast system at Indian National Centre for Ocean Information Services

    Digital Repository Service at National Institute of Oceanography (India)

    Nair, T.M.B.; Sirisha, P.; Sandhya, K.G.; Srinivas, K.; SanilKumar, V.; Sabique, L.; Nherakkol, A.; KrishnaPrasad, B.; RakhiKumari; Jeyakumar, C.; Kaviyazhahu, K.; RameshKumar, M.; Harikumar, R.; Shenoi, S.S.C.; Nayak, S.

    The reliability of the operational Ocean State Forecast system at the Indian National Centre for Ocean Information Services (INCOIS) during tropical cyclones that affect the coastline of India is described in this article. The performance...

  8. Real-Time Forecasting System of Winds, Waves and Surge in Tropical Cyclones

    National Research Council Canada - National Science Library

    Graber, Hans C; Donelan, Mark A; Brown, Michael G; Slinn, Donald N; Hagen, Scott C; Thompson, Donald R; Jensen, Robert E; Black, Peter G; Powell, Mark D; Guiney, John L; Cardone, Vincent J; Cox, Andrew T; Augustus, Ellsworth H; Colonnese, Christopher P

    2003-01-01

    The long-term goal of this partnership is to establish an operational forecasting system of the wind field and resulting waves and surge impacting the coastline during the approach and landfall of tropical cyclones...

  9. Real-Time Forecasting System of Winds, Waves and Surge in Tropical Cyclones

    National Research Council Canada - National Science Library

    Graber, Hans C; Donelan, Mark A; Brown, Michael G; Slinn, Donald N; Hagen, Scott C; Thompson, Donald R; Jensen, Robert E; Black, Peter G; Powell, Mark D; Guiney, John L

    2005-01-01

    The long-term goal of this partnership is to establish an operational forecasting system of the wind field and resulting waves and surge impacting the coastline during the approach and landfall of tropical cyclones...

  10. Real-Time Forecasting System of Winds, Waves and Surge in Tropical Cyclones

    National Research Council Canada - National Science Library

    Graber, Hans C; Donelan, Mark A; Brown, Michael G; Slinn, Donald N; Hagen, Scott C; Thompson, Donald R; Jensen, Robert E; Black, Peter G; Powell, Mark D; Guiney, John L

    2004-01-01

    The long-term goal of this partnership is to establish an operational forecasting system of the wind field and resulting waves and surge impacting the coastline during the approach and landfall of tropical cyclones...

  11. An experimental system for flood risk forecasting and monitoring at global scale

    Science.gov (United States)

    Dottori, Francesco; Alfieri, Lorenzo; Kalas, Milan; Lorini, Valerio; Salamon, Peter

    2017-04-01

    Global flood forecasting and monitoring systems are nowadays a reality and are being applied by a wide range of users and practitioners in disaster risk management. Furthermore, there is an increasing demand from users to integrate flood early warning systems with risk based forecasting, combining streamflow estimations with expected inundated areas and flood impacts. Finally, emerging technologies such as crowdsourcing and social media monitoring can play a crucial role in flood disaster management and preparedness. Here, we present some recent advances of an experimental procedure for near-real time flood mapping and impact assessment. The procedure translates in near real-time the daily streamflow forecasts issued by the Global Flood Awareness System (GloFAS) into event-based flood hazard maps, which are then combined with exposure and vulnerability information at global scale to derive risk forecast. Impacts of the forecasted flood events are evaluated in terms of flood prone areas, potential economic damage, and affected population, infrastructures and cities. To increase the reliability of our forecasts we propose the integration of model-based estimations with an innovative methodology for social media monitoring, which allows for real-time verification and correction of impact forecasts. Finally, we present the results of preliminary tests which show the potential of the proposed procedure in supporting emergency response and management.

  12. Verification of Forecast Weather Surface Variables over Vietnam Using the National Numerical Weather Prediction System

    Directory of Open Access Journals (Sweden)

    Tien Du Duc

    2016-01-01

    Full Text Available The national numerical weather prediction system of Vietnam is presented and evaluated. The system is based on three main models, namely, the Japanese Global Spectral Model, the US Global Forecast System, and the US Weather Research and Forecasting (WRF model. The global forecast products have been received at 0.25- and 0.5-degree horizontal resolution, respectively, and the WRF model has been run locally with 16 km horizontal resolution at the National Center for Hydro-Meteorological Forecasting using lateral conditions from GSM and GFS. The model performance is evaluated by comparing model output against observations of precipitation, wind speed, and temperature at 168 weather stations, with daily data from 2010 to 2014. In general, the global models provide more accurate forecasts than the regional models, probably due to the low horizontal resolution in the regional model. Also, the model performance is poorer for stations with altitudes greater than 500 meters above sea level (masl. For tropical cyclone performance validations, the maximum wind surface forecast from global and regional models is also verified against the best track of Joint Typhoon Warning Center. Finally, the model forecast skill during a recent extreme rain event in northeast Vietnam is evaluated.

  13. Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market

    Science.gov (United States)

    Kim, Taegu; Hong, Jungsik

    2017-01-01

    Accurate box office forecasting models are developed by considering competition and word-of-mouth (WOM) effects in addition to screening-related information. Nationality, genre, ratings, and distributors of motion pictures running concurrently with the target motion picture are used to describe the competition, whereas the numbers of informative, positive, and negative mentions posted on social network services (SNS) are used to gauge the atmosphere spread by WOM. Among these candidate variables, only significant variables are selected by genetic algorithm (GA), based on which machine learning algorithms are trained to build forecasting models. The forecasts are combined to improve forecasting performance. Experimental results on the Korean film market show that the forecasting accuracy in early screening periods can be significantly improved by considering competition. In addition, WOM has a stronger influence on total box office forecasting. Considering both competition and WOM improves forecasting performance to a larger extent than when only one of them is considered. PMID:28819355

  14. Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market.

    Science.gov (United States)

    Kim, Taegu; Hong, Jungsik; Kang, Pilsung

    2017-01-01

    Accurate box office forecasting models are developed by considering competition and word-of-mouth (WOM) effects in addition to screening-related information. Nationality, genre, ratings, and distributors of motion pictures running concurrently with the target motion picture are used to describe the competition, whereas the numbers of informative, positive, and negative mentions posted on social network services (SNS) are used to gauge the atmosphere spread by WOM. Among these candidate variables, only significant variables are selected by genetic algorithm (GA), based on which machine learning algorithms are trained to build forecasting models. The forecasts are combined to improve forecasting performance. Experimental results on the Korean film market show that the forecasting accuracy in early screening periods can be significantly improved by considering competition. In addition, WOM has a stronger influence on total box office forecasting. Considering both competition and WOM improves forecasting performance to a larger extent than when only one of them is considered.

  15. Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market

    Directory of Open Access Journals (Sweden)

    Taegu Kim

    2017-01-01

    Full Text Available Accurate box office forecasting models are developed by considering competition and word-of-mouth (WOM effects in addition to screening-related information. Nationality, genre, ratings, and distributors of motion pictures running concurrently with the target motion picture are used to describe the competition, whereas the numbers of informative, positive, and negative mentions posted on social network services (SNS are used to gauge the atmosphere spread by WOM. Among these candidate variables, only significant variables are selected by genetic algorithm (GA, based on which machine learning algorithms are trained to build forecasting models. The forecasts are combined to improve forecasting performance. Experimental results on the Korean film market show that the forecasting accuracy in early screening periods can be significantly improved by considering competition. In addition, WOM has a stronger influence on total box office forecasting. Considering both competition and WOM improves forecasting performance to a larger extent than when only one of them is considered.

  16. Risks in Networked Computer Systems

    OpenAIRE

    Klingsheim, André N.

    2008-01-01

    Networked computer systems yield great value to businesses and governments, but also create risks. The eight papers in this thesis highlight vulnerabilities in computer systems that lead to security and privacy risks. A broad range of systems is discussed in this thesis: Norwegian online banking systems, the Norwegian Automated Teller Machine (ATM) system during the 90's, mobile phones, web applications, and wireless networks. One paper also comments on legal risks to bank cust...

  17. [Network structures in biological systems].

    Science.gov (United States)

    Oleskin, A V

    2013-01-01

    Network structures (networks) that have been extensively studied in the humanities are characterized by cohesion, a lack of a central control unit, and predominantly fractal properties. They are contrasted with structures that contain a single centre (hierarchies) as well as with those whose elements predominantly compete with one another (market-type structures). As far as biological systems are concerned, their network structures can be subdivided into a number of types involving different organizational mechanisms. Network organization is characteristic of various structural levels of biological systems ranging from single cells to integrated societies. These networks can be classified into two main subgroups: (i) flat (leaderless) network structures typical of systems that are composed of uniform elements and represent modular organisms or at least possess manifest integral properties and (ii) three-dimensional, partly hierarchical structures characterized by significant individual and/or intergroup (intercaste) differences between their elements. All network structures include an element that performs structural, protective, and communication-promoting functions. By analogy to cell structures, this element is denoted as the matrix of a network structure. The matrix includes a material and an immaterial component. The material component comprises various structures that belong to the whole structure and not to any of its elements per se. The immaterial (ideal) component of the matrix includes social norms and rules regulating network elements' behavior. These behavioral rules can be described in terms of algorithms. Algorithmization enables modeling the behavior of various network structures, particularly of neuron networks and their artificial analogs.

  18. An integrated system for wind energy forecast using meteorological models and statistical post-processing

    Science.gov (United States)

    Miranda, P.; Rodrigues, A.; Lopes, J.; Palma, J.; Tome, R.; Sousa, J.; Bessa, R.; Matos, J.

    2009-12-01

    With 3GW of installed wind turbines, corresponding to 23% of the total electric grid, and a 5-year plan that will grow that value above 5GW (near 40% of the grid), Portugal has been a recent success case for renewable energy development. Clearly such large share of wind energy in the national electric system implies a strong requirement for accurate wind forecasts, that can be used to forecast this highly variable energy source and allow for timely decision making in the energy markets, namely for on and off switching of alternative conventional sources. In the past 3 years, a system for 72h energy forecast in mainland Portugal was setup, using 6km resolution meteorological forecasts, forced by global GFS forecasts by NCEP. In the development phase, different boundary conditions (from NCEP and ECMWF) were tested, as well as different limited area models (namely MM5, Aladin, MesoNH and WRF) at resolutions from 12 to 2km, which were evaluated by comparison with wind observations at heights relevant for wind turbines (up to 80m) in different locations and for different synoptic conditions. The developed system, which works with a real time connection with wind farms, also includes a post-processing code that merges recent wind observations with the meteorological forecast, and converts the forecasted wind fields into forecasted energy, by incorporating empirical transfer functions of the wind farm. Wind conditions in Portugal are highly influenced by topography, as most wind farms are located in complex terrain, often in mountainous terrain, where stratification plays a significant role. Coastal effects are also highly relevant, especially during the Summer, where a strong diurnal cycle of the sea-breeze is superimposed on an equally strong boundary layer development, both with a significant impact on low level winds. These two ingredients tend to complicate wind forecasts, requiring fully developed meteorological models. In general, results from 2 full years of

  19. Examining High/Low Variability Forecasts of African Easterly Waves in the ECMWF Ensemble Prediction System

    Science.gov (United States)

    Elless, Travis; Torn, Ryan

    2017-04-01

    During the boreal summer, African Easterly Waves (AEWs) are the primary synoptic-scale feature that influences North African weather, and are associated with the majority of summer rainfall found in this region. Although numerous studies have investigated the composite mean structure and evolution of these waves through observational case studies and idealized modeling, few studies have explored the skill and predictability of these systems in operational deterministic or ensemble forecasts. Furthermore, it is unclear whether the predictability of these features depends on the large-scale environmental factors, such as equatorial waves, mid-level moisture, etc. This study investigates the predictability of AEW forecasts, defined here as the ensemble standard deviation, using European Centre for Medium-Range Weather Forecasts (ECMWF) ensemble forecasts, which are available through the THORPEX Interactive Grand Global Ensemble (TIGGE) dataset, during the periods of July-August-September 2007—2009 and 2011—2013. Whereas the ensemble standard deviation in AEW position forecasts increase at a relatively constant rate with time, the ensemble standard deviation in AEW intensity forecasts often exhibit rapid non-linear growth. Therefore, this study explores forecasts exhibiting the largest standard deviation in intensity at 72h (top 10% of forecasts) and compares them against forecasts with the smallest standard deviation in intensity (bottom 10%). Preliminary results from 2007—2009 suggest the growth of variability is strongly associated to large-scale factors that would promote convection near the AEW, after the first diurnal cycle. Whereas variability in forecasts from 2011—2013 are more associated with the initial AEW structure instead of the large-scale environment.

  20. From Research to Operations: Transitioning Noaa's Lake Erie Harmful Algal Bloom Forecast System

    Science.gov (United States)

    Kavanaugh, K. E.; Stumpf, R. P.

    2016-02-01

    A key priority of NOAA's Harmful Algal Bloom Operational Forecast System (HAB-OFS) is to leverage the Ecological Forecasting Roadmap to systematically transition to operations scientifically mature HAB forecasts in regions of the country where there is a strong user need identified and an operational framework can be supported. While in the demonstration phase, the Lake Erie HAB forecast has proven its utility. Over the next two years, NOAA will be transitioning the Lake Erie HAB forecast to operations with an initial operating capability established in the HAB OFS' operational infrastructure by the 2016 bloom season. Blooms of cyanobacteria are a recurring problem in Lake Erie, and the dominant bloom forming species, Microcystis aeruginosa, produces a toxin called microcystin that is poisonous to humans, livestock and pets. Once the toxins have contaminated the source water used for drinking water, it is costly for public water suppliers to remove them. As part of the Lake Erie HAB forecast demonstration, NOAA has provided information regarding the cyanobacterial blooms in a biweekly Experimental HAB Bulletin, which includes information about the current and forecasted distribution, toxicity, potential for vertical mixing or scum formation, mixing of the water column, and predictions of bloom decline. Coastal resource managers, public water suppliers and public health officials use the Experimental HAB Bulletins to respond to and mitigate the impacts of cyanobacterial blooms. The transition to operations will benefit stakeholders through ensuring that future Lake Erie HAB forecast products are sustained, systematic, reliable, and robust. Once operational, the forecasts will continue to be assessed and improvements will be made based on the results of emerging scientific research. In addition, the lessons learned from the Lake Erie transition will be used to streamline the process for future HAB forecasts presently in development.

  1. Language Networks as Complex Systems

    Science.gov (United States)

    Lee, Max Kueiming; Ou, Sheue-Jen

    2008-01-01

    Starting in the late eighties, with a growing discontent with analytical methods in science and the growing power of computers, researchers began to study complex systems such as living organisms, evolution of genes, biological systems, brain neural networks, epidemics, ecology, economy, social networks, etc. In the early nineties, the research…

  2. Financial Network Systemic Risk Contributions

    NARCIS (Netherlands)

    Hautsch, N.; Schaumburg, J.; Schienle, M.

    2015-01-01

    We propose the realized systemic risk beta as a measure of financial companies' contribution to systemic risk, given network interdependence between firms' tail risk exposures. Conditional on statistically pre-identified network spillover effects and market and balance sheet information, we define

  3. Assessing DRAGON Measurements for Evaluation and Assimilation in the GEOS-5 Aerosol Forecasting System

    Science.gov (United States)

    da Silva, A.; Colarco, P. R.; Darmenov, A.; Holben, B. N.

    2013-12-01

    GEOS-5 is the latest version of the NASA Global Modeling and Assimilation Office (GMAO) earth system model. GEOS-5 contains components for atmospheric circulation and composition (including data assimilation), ocean circulation and biogeochemistry, and land surface processes. In addition to traditional meteorological parameters, GEOS-5 includes modules representing the atmospheric composition, most notably aerosols and tropospheric/stratospheric chemical constituents, taking explicit account of the impact of these constituents on the radiative processes of the atmosphere. The assimilation of Aerosol Optical Depth (AOD) in GEOS-5 involves very careful cloud screening and homogenization of the observing system by means of a Neural Net scheme that translates MODIS radiances into AERONET calibrated AOD. These measurements are further quality controlled using an adaptive buddy check scheme, and assimilated using the Local Displacement Ensemble (LDE) methodology. The near real-time GEOS-5 aerosol forecasting system runs at a nominal 25km horizontal resolution with 72 vertical layers (top at ~85km). GEOS-5 is driven by daily biomass burning emissions derived from MODIS fire radiative power retrievals. In this talk we will utilize aerosol measurements from the Distributed Regional Aerosol Gridded Observation Networks (DRAGON) to evaluate the temporal and spatial distribution of aerosols in GEOS-5. While NRT assimilation of MODIS optical depth observations constrains the GEOS-5 aerosol distributions during satellite overpasses, the diurnal cycle, mixing state and optical properties are internally determined by the model parameterizations and require careful validation. By combining DRAGON with other in-situ and remotely sensed measurements from the DISCOVER-AQ and SEAC4RS field campaigns we will present a comprehensive evaluation of the GEOS-5 aerosol state, and examine the impact of assimilating the DRAGON measurements on the quality of the GEOS-5 analysis and forecasts

  4. AIRS Impact on Analysis and Forecast of an Extreme Rainfall Event (Indus River Valley 2010) with a Global Data Assimilation and Forecast System

    Science.gov (United States)

    Reale, O.; Lau, W. K.; Susskind, J.; Rosenberg, R.

    2011-01-01

    A set of data assimilation and forecast experiments are performed with the NASA Global data assimilation and forecast system GEOS-5, to compare the impact of different approaches towards assimilation of Advanced Infrared Spectrometer (AIRS) data on the precipitation analysis and forecast skill. The event chosen is an extreme rainfall episode which occurred in late July 11 2010 in Pakistan, causing massive floods along the Indus River Valley. Results show that the assimilation of quality-controlled AIRS temperature retrievals obtained under partly cloudy conditions produce better precipitation analyses, and substantially better 7-day forecasts, than assimilation of clear-sky radiances. The improvement of precipitation forecast skill up to 7 day is very significant in the tropics, and is caused by an improved representation, attributed to cloudy retrieval assimilation, of two contributing mechanisms: the low-level moisture advection, and the concentration of moisture over the area in the days preceding the precipitation peak.

  5. Space-time wind speed forecasting for improved power system dispatch

    KAUST Repository

    Zhu, Xinxin

    2014-02-27

    To support large-scale integration of wind power into electric energy systems, state-of-the-art wind speed forecasting methods should be able to provide accurate and adequate information to enable efficient, reliable, and cost-effective scheduling of wind power. Here, we incorporate space-time wind forecasts into electric power system scheduling. First, we propose a modified regime-switching, space-time wind speed forecasting model that allows the forecast regimes to vary with the dominant wind direction and with the seasons, hence avoiding a subjective choice of regimes. Then, results from the wind forecasts are incorporated into a power system economic dispatch model, the cost of which is used as a loss measure of the quality of the forecast models. This, in turn, leads to cost-effective scheduling of system-wide wind generation. Potential economic benefits arise from the system-wide generation of cost savings and from the ancillary service cost savings. We illustrate the economic benefits using a test system in the northwest region of the United States. Compared with persistence and autoregressive models, our model suggests that cost savings from integration of wind power could be on the scale of tens of millions of dollars annually in regions with high wind penetration, such as Texas and the Pacific northwest. © 2014 Sociedad de Estadística e Investigación Operativa.

  6. NOAA’s Nested Northern Gulf of Mexico Operational Forecast Systems Development

    Directory of Open Access Journals (Sweden)

    Eugene Wei

    2014-01-01

    Full Text Available The NOAA National Ocean Service’s (NOS Northern Gulf of Mexico Operational Forecast System (NGOFS became operational in March 2012. Implemented with the Finite Volume Coastal Ocean Model (FVCOM as its core three-dimensional oceanographic circulation model, NGOFS produces a real-time nowcast (−6 h to zero and six-hourly, two-day forecast guidance for water levels and three-dimensional currents, water temperature and salinity over the northern Gulf of Mexico continental shelf. Designed as a regional scale prediction system, NGOFS lacks sufficient spatial coverage and/or resolution to fully resolve hydrodynamic features in critical seaports and estuaries. To overcome this shortcoming and better support the needs of marine navigation, emergency response, and environmental management, two FVCOM-based, high-resolution, estuary-scale nested forecast modeling systems, namely the Northwest and Northeast Gulf of Mexico Operational Forecast Systems (NWGOFS and NEGOFS, have been developed through one-way nesting in NGOFS. Using the atmospheric forecast guidance from the NOAA (National Oceanic and Atmospheric Administration/NWS (National Weather Services’ North American Mesoscale (NAM Forecast System, US Geological Survey (USGS river discharge observations, and the NGOFS water level, current, water temperature and salinity as the surface, river, and open ocean boundary forcing, respectively, a six-month model hindcast for the period October 2010–March 2011 has been conducted. Modeled water levels, currents, salinity and water temperature are compared with observations using the NOS standard skill assessment software. Skill assessment scores indicated that NWGOFS and NEGOFS demonstrate improvement over NGOFS. The NWGOFS and NEGOFS are under real-time nowcast/forecast test and evaluation by NOS’s Center for Operational Oceanographic Products and Services (CO-OPS. The forecast systems are scheduled to be implemented operational on NOAA Weather

  7. First evaluation of aerosol profiles forecasted in ECMWF C-IFS model with E-PROFILE ceilometer network

    Science.gov (United States)

    Hervo, Maxime; Haefele, Alexander

    2017-04-01

    E-PROFILE is a EUMETNET observation programme regrouping measurements of Automatic Lidars and Ceilometers (ALC). Twenty National Weather Services are funding E-PROFILE and more than 10 universities are contributing to the network. At the beginning of 2017, 68 ALCs were sending data operationally. Several hundreds of instruments are expected in the next years. ALCs have a strong potential for models evaluations and assimilation: they measure 24/7 and the high number of instruments can compensate for their limited power. ALC measurements from 8 countries were compared with ECMWF Composition Integrated Forecasting System (C-IFS) model. To our knowledge, it is the first time that this kind of comparison is realised on a continental scale. Two forward operators were used to convert aerosol concentration in simulated Lidar profile. First, the methodology used by the Copernicus Atmosphere Monitoring Service (CAMS) was used. Secondly, the experimental forward operator implemented at ECMWF was tested. On a 3-month period, the average difference between ALC measurements and CAMS forward operator was less than 50%, suggesting the good agreement between model and measurements. However, the sea-salt concentration forecasted in central Europe is clearly over-estimated. The concentration of Sulphate aerosol in the free troposphere was also clearly overestimated by the model. Similar results were found with ECMWF experimental forward operator.The comparison between measured and simulated profiles also highlights instrumental limitations like overlap artefacts. After the evaluation, assimilation tesst will be performed to integrate the E-PROFILE observations in the ECMWF assimilation procedure. Acknowledgement: This study was realised in the frame of the COST Action TOPROF (ES1303). The authors would like to acknowledge all the participants for their fruitful collaboration.

  8. Comparison of short term rainfall forecasts for model based flow prediction in urban drainage systems

    DEFF Research Database (Denmark)

    Thorndahl, Søren; Poulsen, Troels Sander; Bøvith, Thomas

    2012-01-01

    Forecast based flow prediction in drainage systems can be used to implement real time control of drainage systems. This study compares two different types of rainfall forecasts – a radar rainfall extrapolation based nowcast model and a numerical weather prediction model. The models are applied...... performance of the system is found using the radar nowcast for the short leadtimes and weather model for larger lead times....... as input to an urban runoff model predicting the inlet flow to a waste water treatment plant. The modelled flows are auto-calibrated against real time flow observations in order to certify the best possible forecast. Results show that it is possible to forecast flows with a lead time of 24 hours. The best...

  9. Comparison Of Short Term Rainfall Forecasts For Model Based Flow Prediction In Urban Drainage Systems

    DEFF Research Database (Denmark)

    Thorndahl, Søren Liedtke; Poulsen, Troels Sander; Bøvith, Thomas

    2012-01-01

    Forecast based flow prediction in drainage systems can be used to implement real time control of drainage systems. This study compares two different types of rainfall forecasts – a radar rainfall extrapolation based nowcast model and a numerical weather prediction model. The models are applied...... performance of the system is found using the radar nowcast for the short leadtimes and weather model for larger lead times....... as input to an urban runoff model predicting the inlet flow to a waste water treatment plant. The modelled flows are auto-calibrated against real time flow observations in order to certify the best possible forecast. Results show that it is possible to forecast flows with a lead time of 24 hours. The best...

  10. Short-Term Forecasting of Loads and Wind Power for Latvian Power System: Accuracy and Capacity of the Developed Tools

    Directory of Open Access Journals (Sweden)

    Radziukynas V.

    2016-04-01

    Full Text Available The paper analyses the performance results of the recently developed short-term forecasting suit for the Latvian power system. The system load and wind power are forecasted using ANN and ARIMA models, respectively, and the forecasting accuracy is evaluated in terms of errors, mean absolute errors and mean absolute percentage errors. The investigation of influence of additional input variables on load forecasting errors is performed. The interplay of hourly loads and wind power forecasting errors is also evaluated for the Latvian power system with historical loads (the year 2011 and planned wind power capacities (the year 2023.

  11. A New Coastal Flood Forecasting System for the Netherlands

    NARCIS (Netherlands)

    De Kleermaeker, S.; Verlaan, M.; Kroos, J.; Zijl, F.

    2012-01-01

    The North Sea is one of the busiest seas in the world with dense ship traffic, fisheries, wind farming, recreation and many other activities. All these activities depend on the ‘marine weather’. Accurate forecasts of waves, currents and sea level are crucial for operational management and for

  12. Navy mobility fuels forecasting system report: World petroleum trade forecasts for the year 2000

    Energy Technology Data Exchange (ETDEWEB)

    Das, S.

    1991-12-01

    The Middle East will continue to play the dominant role of a petroleum supplier in the world oil market in the year 2000, according to business-as-usual forecasts published by the US Department of Energy. However, interesting trade patterns will emerge as a result of the democratization in the Soviet Union and Eastern Europe. US petroleum imports will increase from 46% in 1989 to 49% in 2000. A significantly higher level of US petroleum imports (principally products) will be coming from Japan, the Soviet Union, and Eastern Europe. Several regions, the Far East, Japan, Latin American, and Africa will import more petroleum. Much uncertainty remains about of the level future Soviet crude oil production. USSR net petroleum exports will decrease; however, the United States and Canada will receive some of their imports from the Soviet Union due to changes in the world trade patterns. The Soviet Union can avoid becoming a net petroleum importer as long as it (1) maintains enough crude oil production to meet its own consumption and (2) maintains its existing refining capacities. Eastern Europe will import approximately 50% of its crude oil from the Middle East.

  13. Improved Short-Term Load Forecasting Based on Two-Stage Predictions with Artificial Neural Networks in a Microgrid Environment

    Directory of Open Access Journals (Sweden)

    Jaime Lloret

    2013-08-01

    Full Text Available Short-Term Load Forecasting plays a significant role in energy generation planning, and is specially gaining momentum in the emerging Smart Grids environment, which usually presents highly disaggregated scenarios where detailed real-time information is available thanks to Communications and Information Technologies, as it happens for example in the case of microgrids. This paper presents a two stage prediction model based on an Artificial Neural Network in order to allow Short-Term Load Forecasting of the following day in microgrid environment, which first estimates peak and valley values of the demand curve of the day to be forecasted. Those, together with other variables, will make the second stage, forecast of the entire demand curve, more precise than a direct, single-stage forecast. The whole architecture of the model will be presented and the results compared with recent work on the same set of data, and on the same location, obtaining a Mean Absolute Percentage Error of 1.62% against the original 2.47% of the single stage model.

  14. Application of a deep-learning method to the forecast of daily solar flare occurrence using Convolution Neural Network

    Science.gov (United States)

    Shin, Seulki; Moon, Yong-Jae; Chu, Hyoungseok

    2017-08-01

    As the application of deep-learning methods has been succeeded in various fields, they have a high potential to be applied to space weather forecasting. Convolutional neural network, one of deep learning methods, is specialized in image recognition. In this study, we apply the AlexNet architecture, which is a winner of Imagenet Large Scale Virtual Recognition Challenge (ILSVRC) 2012, to the forecast of daily solar flare occurrence using the MatConvNet software of MATLAB. Our input images are SOHO/MDI, EIT 195Å, and 304Å from January 1996 to December 2010, and output ones are yes or no of flare occurrence. We select training dataset from Jan 1996 to Dec 2000 and from Jan 2003 to Dec 2008. Testing dataset is chosen from Jan 2001 to Dec 2002 and from Jan 2009 to Dec 2010 in order to consider the solar cycle effect. In training dataset, we randomly select one fifth of training data for validation dataset to avoid the overfitting problem. Our model successfully forecasts the flare occurrence with about 0.90 probability of detection (POD) for common flares (C-, M-, and X-class). While POD of major flares (M- and X-class) forecasting is 0.96, false alarm rate (FAR) also scores relatively high(0.60). We also present several statistical parameters such as critical success index (CSI) and true skill statistics (TSS). Our model can immediately be applied to automatic forecasting service when image data are available.

  15. Evaluation of forecasts by accuracy and spread in the MiKlip decadal climate prediction system

    Directory of Open Access Journals (Sweden)

    Christopher Kadow

    2016-12-01

    Full Text Available We present the evaluation of temperature and precipitation forecasts obtained with the MiKlip decadal climate prediction system. These decadal hindcast experiments are verified with respect to the accuracy of the ensemble mean and the ensemble spread as a representative for the forecast uncertainty. The skill assessment follows the verification framework already used by the decadal prediction community, but enhanced with additional evaluation techniques like the logarithmic ensemble spread score. The core of the MiKlip system is the coupled Max Planck Institute Earth System Model. An ensemble of 10 members is initialized annually with ocean and atmosphere reanalyses of the European Centre for Medium-Range Weather Forecasts. For assessing the effect of the initialization, we compare these predictions to uninitialized climate projections with the same model system. Initialization improves the accuracy of temperature and precipitation forecasts in year 1, particularly in the Pacific region. The ensemble spread well represents the forecast uncertainty in lead year 1, except in the tropics. This estimate of prediction skill creates confidence in the respective 2014 forecasts, which depict less precipitation in the tropics and a warming almost everywhere. However, large cooling patterns appear in the Northern Hemisphere, the Pacific South America and the Southern Ocean. Forecasts for 2015 to 2022 show even warmer temperatures than for 2014, especially over the continents. The evaluation of lead years 2 to 9 for temperature shows skill globally with the exception of the eastern Pacific. The ensemble spread can again be used as an estimate of the forecast uncertainty in many regions: It improves over the tropics compared to lead year 1. Due to a reduction of the conditional bias, the decadal predictions of the initialized system gain skill in the accuracy compared to the uninitialized simulations in the lead years 2 to 9. Furthermore, we show that

  16. Networking systems design and development

    CERN Document Server

    Chao, Lee

    2009-01-01

    Effectively integrating theory and hands-on practice, Networking Systems Design and Development provides students and IT professionals with the knowledge and skills needed to design, implement, and manage fully functioning network systems using readily available Linux networking tools. Recognizing that most students are beginners in the field of networking, the text provides step-by-step instruction for setting up a virtual lab environment at home. Grounded in real-world applications, this book provides the ideal blend of conceptual instruction and lab work to give students and IT professional

  17. Electrical Energy Forecasting and Optimal Allocation of ESS in a Hybrid Wind-Diesel Power System

    Directory of Open Access Journals (Sweden)

    Hai Lan

    2017-02-01

    Full Text Available Due to the increasingly serious energy crisis and environmental pollution problem, traditional fossil energy is gradually being replaced by renewable energy in recent years. However, the introduction of renewable energy into power systems will lead to large voltage fluctuations and high capital costs. To solve these problems, an energy storage system (ESS is employed into a power system to reduce total costs and greenhouse gas emissions. Hence, this paper proposes a two-stage method based on a back-propagation neural network (BPNN and hybrid multi-objective particle swarm optimization (HMOPSO to determine the optimal placements and sizes of ESSs in a transmission system. Owing to the uncertainties of renewable energy, a BPNN is utilized to forecast the outputs of the wind power and load demand based on historic data in the city of Madison, USA. Furthermore, power-voltage (P-V sensitivity analysis is conducted in this paper to improve the converge speed of the proposed algorithm, and continuous wind distribution is discretized by a three-point estimation method. The Institute of Electrical and Electronic Engineers (IEEE 30-bus system is adopted to perform case studies. The simulation results of each case clearly demonstrate the necessity for optimal storage allocation and the efficiency of the proposed method.

  18. Evaluation of weather forecast systems for storm surge modeling in the Chesapeake Bay

    Science.gov (United States)

    Garzon, Juan L.; Ferreira, Celso M.; Padilla-Hernandez, Roberto

    2018-01-01

    Accurate forecast of sea-level heights in coastal areas depends, among other factors, upon a reliable coupling of a meteorological forecast system to a hydrodynamic and wave system. This study evaluates the predictive skills of the coupled circulation and wind-wave model system (ADCIRC+SWAN) for simulating storm tides in the Chesapeake Bay, forced by six different products: (1) Global Forecast System (GFS), (2) Climate Forecast System (CFS) version 2, (3) North American Mesoscale Forecast System (NAM), (4) Rapid Refresh (RAP), (5) European Center for Medium-Range Weather Forecasts (ECMWF), and (6) the Atlantic hurricane database (HURDAT2). This evaluation is based on the hindcasting of four events: Irene (2011), Sandy (2012), Joaquin (2015), and Jonas (2016). By comparing the simulated water levels to observations at 13 monitoring stations, we have found that the ADCIR+SWAN System forced by the following: (1) the HURDAT2-based system exhibited the weakest statistical skills owing to a noteworthy overprediction of the simulated wind speed; (2) the ECMWF, RAP, and NAM products captured the moment of the peak and moderately its magnitude during all storms, with a correlation coefficient ranging between 0.98 and 0.77; (3) the CFS system exhibited the worst averaged root-mean-square difference (excepting HURDAT2); (4) the GFS system (the lowest horizontal resolution product tested) resulted in a clear underprediction of the maximum water elevation. Overall, the simulations forced by NAM and ECMWF systems induced the most accurate results best accuracy to support water level forecasting in the Chesapeake Bay during both tropical and extra-tropical storms.

  19. Introduction on the operational storm surge forecasting system in Korea Operational Oceanographic System (KOOS)

    Science.gov (United States)

    Kwon, Jae-Il; Park, Kwang-Soon; Choi, Jung-Woon; Lee, Jong-Chan; Heo, Ki-Young; Kim, Sang-Ik

    2017-04-01

    During last more than 50 years, 258 typhoons passed and affected the Korean peninsula in terms of high winds, storm surges and extreme waves. In this study we explored the performance of the operational storm surge forecasting system in the Korea Operational Oceanographic System (KOOS) with 8 typhoons from 2010 to 2016. The operation storm surge forecasting system for the typhoon in KOOS is based on 2D depth averaged model with tides and CE (U.S. Army Corps of Engineers) wind model. Two key parameters of CE wind model, the locations of typhoon center and its central atmospheric pressure are based from Korea Meteorological administrative (KMA)'s typhoon information provided from 1 day to 3 hour intervals with the approach of typhoon through the KMA's web-site. For 8 typhoons cases, the overall errors, other performances and analysis such as peak time and surge duration are presented in each case. The most important factor in the storm surge errors in the operational forecasting system is the accuracy of typhoon passage prediction.

  20. Communicating embedded systems networks applications

    CERN Document Server

    Krief, Francine

    2013-01-01

    Embedded systems become more and more complex and require having some knowledge in various disciplines such as electronics, data processing, telecommunications and networks. Without detailing all the aspects related to the design of embedded systems, this book, which was written by specialists in electronics, data processing and telecommunications and networks, gives an interesting point of view of communication techniques and problems in embedded systems. This choice is easily justified by the fact that embedded systems are today massively communicating and that telecommunications and network

  1. Improved Weather Forecasting for the Dynamic Scheduling System of the Green Bank Telescope

    Science.gov (United States)

    Henry, Kari; Maddalena, Ronald

    2018-01-01

    The Robert C Byrd Green Bank Telescope (GBT) uses a software system that dynamically schedules observations based on models of vertical weather forecasts produced by the National Weather Service (NWS). The NWS provides hourly forecasted values for ~60 layers that extend into the stratosphere over the observatory. We use models, recommended by the Radiocommunication Sector of the International Telecommunications Union, to derive the absorption coefficient in each layer for each hour in the NWS forecasts and for all frequencies over which the GBT has receivers, 0.1 to 115 GHz. We apply radiative transfer models to derive the opacity and the atmospheric contributions to the system temperature, thereby deriving forecasts applicable to scheduling radio observations for up to 10 days into the future. Additionally, the algorithms embedded in the data processing pipeline use historical values of the forecasted opacity to calibrate observations. Until recently, we have concentrated on predictions for high frequency (> 15 GHz) observing, as these need to be scheduled carefully around bad weather. We have been using simple models for the contribution of rain and clouds since we only schedule low-frequency observations under these conditions. In this project, we wanted to improve the scheduling of the GBT and data calibration at low frequencies by deriving better algorithms for clouds and rain. To address the limitation at low frequency, the observatory acquired a Radiometrics Corporation MP-1500A radiometer, which operates in 27 channels between 22 and 30 GHz. By comparing 16 months of measurements from the radiometer against forecasted system temperatures, we have confirmed that forecasted system temperatures are indistinguishable from those measured under good weather conditions. Small miss-calibrations of the radiometer data dominate the comparison. By using recalibrated radiometer measurements, we looked at bad weather days to derive better models for forecasting the

  2. Validation of the CME Geomagnetic Forecast Alerts Under the COMESEP Alert System

    Science.gov (United States)

    Dumbović, Mateja; Srivastava, Nandita; Rao, Yamini K.; Vršnak, Bojan; Devos, Andy; Rodriguez, Luciano

    2017-08-01

    Under the European Union 7th Framework Programme (EU FP7) project Coronal Mass Ejections and Solar Energetic Particles (COMESEP, http://comesep.aeronomy.be), an automated space weather alert system has been developed to forecast solar energetic particles (SEP) and coronal mass ejection (CME) risk levels at Earth. The COMESEP alert system uses the automated detection tool called Computer Aided CME Tracking (CACTus) to detect potentially threatening CMEs, a drag-based model (DBM) to predict their arrival, and a CME geoeffectiveness tool (CGFT) to predict their geomagnetic impact. Whenever CACTus detects a halo or partial halo CME and issues an alert, the DBM calculates its arrival time at Earth and the CGFT calculates its geomagnetic risk level. The geomagnetic risk level is calculated based on an estimation of the CME arrival probability and its likely geoeffectiveness, as well as an estimate of the geomagnetic storm duration. We present the evaluation of the CME risk level forecast with the COMESEP alert system based on a study of geoeffective CMEs observed during 2014. The validation of the forecast tool is made by comparing the forecasts with observations. In addition, we test the success rate of the automatic forecasts (without human intervention) against the forecasts with human intervention using advanced versions of the DBM and CGFT (independent tools available at the Hvar Observatory website, http://oh.geof.unizg.hr). The results indicate that the success rate of the forecast in its current form is unacceptably low for a realistic operation system. Human intervention improves the forecast, but the false-alarm rate remains unacceptably high. We discuss these results and their implications for possible improvement of the COMESEP alert system.

  3. A Real-Time Eulerian Photochemical Model Forecast System: Overview and Initial Ozone Forecast Performance in the Northeast U.S. Corridor.

    Science.gov (United States)

    McHenry, John N.; Ryan, William F.; Seaman, Nelson L.; Coats, Carlie J., Jr.; Pudykiewicz, Janusz; Arunachalam, Sarav; Vukovich, Jeffery M.

    2004-04-01

    This article reports on the first implementation of a real-time Eulerian photochemical model forecast system in the United States. The forecast system consists of a tripartite set of one-way coupled models that run routinely on a parallel microprocessor supercomputer. The component models are the fifth-generation Pennsylvania State University (PSU) NCAR Mesoscale Model (MM5), the Sparse-Matrix Operator Kernel for Emissions (SMOKE) model, and the Multiscale Air Quality Simulation Platform—Real Time (MAQSIP-RT) photochemical model. Though the system has been run in real time since the summer of 1998, forecast results obtained during August of 2001 at 15-km grid spacing over New England and the northern mid-Atlantic—conducted as part of an “early start” NOAA air quality forecasting initiative—are described in this article.The development and deployment of a real-time numerical air quality prediction (NAQP) system is technically challenging. MAQSIP-RT contains a full pho-tochemical oxidant gas-phase chemical mechanism together with transport, dry deposition, and sophisticated cloud treatment. To enable the NAQP system to run fast enough to meet operational forecast deadlines, significant work was devoted to data flow design and software engineering of the models and control codes. The result is a turnkey system now in use by a number of agencies concerned with operational ozone forecasting.Results of the chosen episode are compared against three other models/modeling techniques: a traditional statistical model used routinely in the metropolitan Philadelphia, Pennsylvania, area, a set of publicly issued forecasts in the northeastern United States, and the operational Canadian Hemispheric and Regional Ozone and NOx System (CHRONOS) model. For the test period it is shown that the NAQP system performs as well or better than all of these operational approaches. Implications for the impending development of an operational U.S. ozone forecasting capability are

  4. Wave ensemble forecast in the Western Mediterranean Sea, application to an early warning system.

    Science.gov (United States)

    Pallares, Elena; Hernandez, Hector; Moré, Jordi; Espino, Manuel; Sairouni, Abdel

    2015-04-01

    The Western Mediterranean Sea is a highly heterogeneous and variable area, as is reflected on the wind field, the current field, and the waves, mainly in the first kilometers offshore. As a result of this variability, the wave forecast in these regions is quite complicated to perform, usually with some accuracy problems during energetic storm events. Moreover, is in these areas where most of the economic activities take part, including fisheries, sailing, tourism, coastal management and offshore renewal energy platforms. In order to introduce an indicator of the probability of occurrence of the different sea states and give more detailed information of the forecast to the end users, an ensemble wave forecast system is considered. The ensemble prediction systems have already been used in the last decades for the meteorological forecast; to deal with the uncertainties of the initial conditions and the different parametrizations used in the models, which may introduce some errors in the forecast, a bunch of different perturbed meteorological simulations are considered as possible future scenarios and compared with the deterministic forecast. In the present work, the SWAN wave model (v41.01) has been implemented for the Western Mediterranean sea, forced with wind fields produced by the deterministic Global Forecast System (GFS) and Global Ensemble Forecast System (GEFS). The wind fields includes a deterministic forecast (also named control), between 11 and 21 ensemble members, and some intelligent member obtained from the ensemble, as the mean of all the members. Four buoys located in the study area, moored in coastal waters, have been used to validate the results. The outputs include all the time series, with a forecast horizon of 8 days and represented in spaghetti diagrams, the spread of the system and the probability at different thresholds. The main goal of this exercise is to be able to determine the degree of the uncertainty of the wave forecast, meaningful

  5. Product demand forecasts using wavelet kernel support vector machine and particle swarm optimization in manufacture system

    Science.gov (United States)

    Wu, Qi

    2010-03-01

    Demand forecasts play a crucial role in supply chain management. The future demand for a certain product is the basis for the respective replenishment systems. Aiming at demand series with small samples, seasonal character, nonlinearity, randomicity and fuzziness, the existing support vector kernel does not approach the random curve of the sales time series in the space (quadratic continuous integral space). In this paper, we present a hybrid intelligent system combining the wavelet kernel support vector machine and particle swarm optimization for demand forecasting. The results of application in car sale series forecasting show that the forecasting approach based on the hybrid PSOWv-SVM model is effective and feasible, the comparison between the method proposed in this paper and other ones is also given, which proves that this method is, for the discussed example, better than hybrid PSOv-SVM and other traditional methods.

  6. Comparing One-Way and Two-Way Coupled Hydrometeorological Forecasting Systems for Flood Forecasting in the Mediterranean Region

    Directory of Open Access Journals (Sweden)

    Amir Givati

    2016-05-01

    Full Text Available A pair of hydro-meteorological modeling systems were calibrated and evaluated for the Ayalon basin in central Israel to assess the advantages and limitations of one-way versus two-way coupled modeling systems for flood prediction. The models used included the Hydrological Engineering Center-Hydrological Modeling System (HEC-HMS model and the Weather Research and Forecasting (WRF Hydro modeling system. The models were forced by observed, interpolated precipitation from rain-gauges within the basin, and with modeled precipitation from the WRF atmospheric model. Detailed calibration and evaluation was carried out for two major winter storms in January and December 2013. Then, both modeling systems were executed and evaluated in an operational mode for the full 2014/2015 rainy season. Outputs from these simulations were compared to observed measurements from the hydrometric station at the Ayalon basin outlet. Various statistical metrics were employed to quantify and analyze the results: correlation, Root Mean Square Error (RMSE and the Nash–Sutcliffe (NS efficiency coefficient. Foremost, the results presented in this study highlight the sensitivity of hydrological responses to different sources of simulated and observed precipitation data, and demonstrate improvement, although not significant, at the Hydrological response, like simulated hydrographs. With observed precipitation data both calibrated models closely simulated the observed hydrographs. The two-way coupled WRF/WRF-Hydro modeling system produced improved both the precipitation and hydrological simulations as compared to the one-way WRF simulations. Findings from this study, as well as previous studies, suggest that the use of two-way atmospheric-hydrological coupling has the potential to improve precipitation and, therefore, hydrological forecasts for early flood warning applications. However, more research needed in order to better understand the land-atmosphere coupling mechanisms

  7. Delays and networked control systems

    CERN Document Server

    Hetel, Laurentiu; Daafouz, Jamal; Johansson, Karl

    2016-01-01

    This edited monograph includes state-of-the-art contributions on continuous time dynamical networks with delays. The book is divided into four parts. The first part presents tools and methods for the analysis of time-delay systems with a particular attention on control problems of large scale or infinite-dimensional systems with delays. The second part of the book is dedicated to the use of time-delay models for the analysis and design of Networked Control Systems. The third part of the book focuses on the analysis and design of systems with asynchronous sampling intervals which occur in Networked Control Systems. The last part of the book exposes several contributions dealing with the design of cooperative control and observation laws for networked control systems. The target audience primarily comprises researchers and experts in the field of control theory, but the book may also be beneficial for graduate students. .

  8. Anvil Forecast Tool in the Advanced Weather Interactive Processing System, Phase II

    Science.gov (United States)

    Barrett, Joe H., III

    2008-01-01

    Meteorologists from the 45th Weather Squadron (45 WS) and Spaceflight Meteorology Group have identified anvil forecasting as one of their most challenging tasks when predicting the probability of violations of the Lightning Launch Commit Criteria and Space Light Rules. As a result, the Applied Meteorology Unit (AMU) created a graphical overlay tool for the Meteorological Interactive Data Display Systems (MIDDS) to indicate the threat of thunderstorm anvil clouds, using either observed or model forecast winds as input.

  9. An Automated Weather Research and Forecasting (WRF)-Based Nowcasting System: Software Description

    Science.gov (United States)

    2013-10-01

    developed to generate high-fidelity mesocale model forecasts that automatically incorporate Global Forecast System (GFS) large-scale initialization...native features of HTML. WRFEE is based on the model-view-controller ( MVC ) paradigm whereby the model controls program flow (see figure 1), the view is...modifications are outlined later in this report. 3 3. Background WRFEE is based on the MVC paradigm whereby the model handles data and the business logic

  10. Pathways to designing and running an operational flood forecasting system: an adventure game!

    Science.gov (United States)

    Arnal, Louise; Pappenberger, Florian; Ramos, Maria-Helena; Cloke, Hannah; Crochemore, Louise; Giuliani, Matteo; Aalbers, Emma

    2017-04-01

    In the design and building of an operational flood forecasting system, a large number of decisions have to be taken. These include technical decisions related to the choice of the meteorological forecasts to be used as input to the hydrological model, the choice of the hydrological model itself (its structure and parameters), the selection of a data assimilation procedure to run in real-time, the use (or not) of a post-processor, and the computing environment to run the models and display the outputs. Additionally, a number of trans-disciplinary decisions are also involved in the process, such as the way the needs of the users will be considered in the modelling setup and how the forecasts (and their quality) will be efficiently communicated to ensure usefulness and build confidence in the forecasting system. We propose to reflect on the numerous, alternative pathways to designing and running an operational flood forecasting system through an adventure game. In this game, the player is the protagonist of an interactive story driven by challenges, exploration and problem-solving. For this presentation, you will have a chance to play this game, acting as the leader of a forecasting team at an operational centre. Your role is to manage the actions of your team and make sequential decisions that impact the design and running of the system in preparation to and during a flood event, and that deal with the consequences of the forecasts issued. Your actions are evaluated by how much they cost you in time, money and credibility. Your aim is to take decisions that will ultimately lead to a good balance between time and money spent, while keeping your credibility high over the whole process. This game was designed to highlight the complexities behind decision-making in an operational forecasting and emergency response context, in terms of the variety of pathways that can be selected as well as the timescale, cost and timing of effective actions.

  11. Development of an aerosol assimilation/forecasting system with Himawari-8 aerosol products

    Science.gov (United States)

    Maki, T.; Yumimoto, K.; Tanaka, T. Y.; Yoshida, M.; Kikuchi, M.; Nagao, T. M.; Murakami, H.; Ogi, A.; Sekiyama, T. T.

    2016-12-01

    A new generation geostationary meteorological satellite (GMS), Himawari-8, was launched on 7 October 2014 and became operational on 7 July 2015. Himawari-8 is equipped with more advanced multispectral imager (Advanced Himawari Imager; AHI) ahead of other planned GMSs (e.g., GEOS-R). The AHI has 16 observational bands including three visible lights (i.e. RGB) with high spatial (0.5-2 km) and temporal (every 10 minutes full-disk images) resolutions, and provides about 50 times more data than previous GMSs. It is attractive characteristics for aerosol study that the visible and near-infrared observational bands allow us to obtain full-disk maps of aerosol optical properties (i.e., aerosol optical thickness (AOT) and ångström exponent) with unprecedented temporal resolution. Meteorological Research Institute (MRI)/JMA and Japan Aerospace Exploration Agency (JAXA) have been developing an aerosol assimilation/forecasting system with a global aerosol transport model (MASINGAR mk-2), 2 dimensional variational (2D-Var) method, and the Himawari-8 AOTs. Forecasting results are quantitatively validated by AOTs measured by AERONET and PM2.5 concentrations obtained by in-situ stations. Figure 1 shows model-predicted and satellite-observed AOTs during the 2016 Siberian wildfire. Upper and lower panels exhibit maps of AOT at analysis time (0000 UTC on May 18, 2016) and 27-hour forecast time (03 UTC on May 19, 2016), respectively. The 27-hour forecasted AOT starting with the analyzed initial condition (Figure 1f) successfully predicts heavy smokes covering the northern part of Japan, which forecast without assimilation (Figure 1e) failed to reproduces. Figure 1: Horizontal distribution of observed and forecasted AOTs at 0000 UTC 18 May, 2016 (analysis time; upper panels) and 0300 UTC 19 May, 2016 (18-h forecast from the analysis time; lower panel). (a, d) observed AOT from Himawari-8, (b, e) forecasted AOT without assimilation, and (c, f) forecast AOT with assimilation.

  12. Interorganizational Innovation in Systemic Networks

    DEFF Research Database (Denmark)

    Seemann, Janne; Dinesen, Birthe; Gustafsson, Jeppe

    2013-01-01

    that linear n-stage models by reducing complexity and flux end up focusing only on the surface of the network and are thus unable to grasp important aspects of network dynamics. The paper suggests that there is a need for a more dynamic innovation model able to grasp the whole picture of dynamics in systemic...... patients with chronic obstructive pulmonary disease (COPD) to avoid readmission, perform self monitoring and to maintain rehabilitation in their homes. The aim of the paper is to identify, analyze and discuss innovation dynamics in the COPD network and on a preliminary basis to identify implications...... for managing innovations in systemic networks. The main argument of this paper is that innovation dynamics in systemic networks should be understood as a complex interplay of four logics: 1) Fragmented innovation, 2) Interface innovation, 3) Competing innovation, 4) Co-innovation. The findings indicate...

  13. Asynchronous control for networked systems

    CERN Document Server

    Rubio, Francisco; Bencomo, Sebastián

    2015-01-01

    This book sheds light on networked control systems; it describes different techniques for asynchronous control, moving away from the periodic actions of classical control, replacing them with state-based decisions and reducing the frequency with which communication between subsystems is required. The text focuses specially on event-based control. Split into two parts, Asynchronous Control for Networked Systems begins by addressing the problems of single-loop networked control systems, laying out various solutions which include two alternative model-based control schemes (anticipatory and predictive) and the use of H2/H∞ robust control to deal with network delays and packet losses. Results on self-triggering and send-on-delta sampling are presented to reduce the need for feedback in the loop. In Part II, the authors present solutions for distributed estimation and control. They deal first with reliable networks and then extend their results to scenarios in which delays and packet losses may occur. The novel ...

  14. Performance of Networked Control Systems

    Directory of Open Access Journals (Sweden)

    Yingwei Zhang

    2013-01-01

    Full Text Available Data packet dropout is a special kind of time delay problem. In this paper, predictive controllers for networked control systems (NCSs with dual-network are designed by model predictive control method. The contributions are as follows. (1 The predictive control problem of the dual-network is considered. (2 The predictive performance of the dual-network is evaluated. (3 Compared to the popular networked control systems, the optimal controller of the new NCSs with data packets dropout is designed, which can minimize infinite performance index at each sampling time and guarantee the closed-loop system stability. Finally, the simulation results show the feasibility and effectiveness of the controllers designed.

  15. Flood forecasting model based on geographical information system

    Science.gov (United States)

    Dong, A.; Zhi-Jia, L.; Yong-Tuo, W.; Cheng, Y.; Yi-Heng, D.

    2015-05-01

    In this paper, the Antecedent Precipitation Index Model (API) combined with Nash's Instantaneous Unit Curve Method is adopted for flood forecasting. The parameters n and k of Nash's Method is obtained by setting up the mathematic relation between these two parameters and topographic characteristics. Based on the DEM information, ArcGIS software is used to get the topographic characteristics and the topographic parameters. The Tunxi basin in the humid region was taken as an example for analysis. Through comparison with the simulation results of the Xinanjiang model, the detailed analysis of our simulation results is carried out giving a Nash-Sutcliffe efficiency 0.80 for the combined model and 0.94 for the Xinanjiang model. This indicates that the combined model as well as the Xinanjiang Model has a good performance in the simulation process. The combined model has great potential as a new efficient approach for flood forecasting in similar basins.

  16. Flood forecasting model based on geographical information system

    Directory of Open Access Journals (Sweden)

    A. Dong

    2015-05-01

    Full Text Available In this paper, the Antecedent Precipitation Index Model (API combined with Nash’s Instantaneous Unit Curve Method is adopted for flood forecasting. The parameters n and k of Nash’s Method is obtained by setting up the mathematic relation between these two parameters and topographic characteristics. Based on the DEM information, ArcGIS software is used to get the topographic characteristics and the topographic parameters. The Tunxi basin in the humid region was taken as an example for analysis. Through comparison with the simulation results of the Xinanjiang model, the detailed analysis of our simulation results is carried out giving a Nash-Sutcliffe efficiency 0.80 for the combined model and 0.94 for the Xinanjiang model. This indicates that the combined model as well as the Xinanjiang Model has a good performance in the simulation process. The combined model has great potential as a new efficient approach for flood forecasting in similar basins.

  17. Decadal Prediction Skill in the GEOS-5 Forecast System

    Science.gov (United States)

    Ham, Yoo-Geun; Rienecker, Michele M.; Suarez, Max J.; Vikhliaev, Yury; Zhao, Bin; Marshak, Jelena; Vernieres, Guillaume; Schubert, Siegfried D.

    2013-01-01

    A suite of decadal predictions has been conducted with the NASA Global Modeling and Assimilation Office's (GMAO's) GEOS-5 Atmosphere-Ocean general circulation model. The hind casts are initialized every December 1st from 1959 to 2010, following the CMIP5 experimental protocol for decadal predictions. The initial conditions are from a multivariate ensemble optimal interpolation ocean and sea-ice reanalysis, and from GMAO's atmospheric reanalysis, the modern-era retrospective analysis for research and applications. The mean forecast skill of a three-member-ensemble is compared to that of an experiment without initialization but also forced with observed greenhouse gases. The results show that initialization increases the forecast skill of North Atlantic sea surface temperature compared to the uninitialized runs, with the increase in skill maintained for almost a decade over the subtropical and mid-latitude Atlantic. On the other hand, the initialization reduces the skill in predicting the warming trend over some regions outside the Atlantic. The annual-mean Atlantic meridional overturning circulation index, which is defined here as the maximum of the zonally-integrated overturning stream function at mid-latitude, is predictable up to a 4-year lead time, consistent with the predictable signal in upper ocean heat content over the North Atlantic. While the 6- to 9-year forecast skill measured by mean squared skill score shows 50 percent improvement in the upper ocean heat content over the subtropical and mid-latitude Atlantic, prediction skill is relatively low in the sub-polar gyre. This low skill is due in part to features in the spatial pattern of the dominant simulated decadal mode in upper ocean heat content over this region that differ from observations. An analysis of the large-scale temperature budget shows that this is the result of a model bias, implying that realistic simulation of the climatological fields is crucial for skillful decadal forecasts.

  18. Decadal prediction skill in the GEOS-5 forecast system

    Science.gov (United States)

    Ham, Yoo-Geun; Rienecker, Michele M.; Suarez, Max J.; Vikhliaev, Yury; Zhao, Bin; Marshak, Jelena; Vernieres, Guillaume; Schubert, Siegfried D.

    2014-01-01

    A suite of decadal predictions has been conducted with the NASA Global Modeling and Assimilation Office's (GMAO's) GEOS-5 Atmosphere-Ocean general circulation model. The hind casts are initialized every December 1st from 1959 to 2010, following the CMIP5 experimental protocol for decadal predictions. The initial conditions are from a multi-variate ensemble optimal interpolation ocean and sea-ice reanalysis, and from GMAO's atmospheric reanalysis, the modern-era retrospective analysis for research and applications. The mean forecast skill of a three-member-ensemble is compared to that of an experiment without initialization but also forced with observed greenhouse gases. The results show that initialization increases the forecast skill of North Atlantic sea surface temperature compared to the uninitialized runs, with the increase in skill maintained for almost a decade over the subtropical and mid-latitude Atlantic. On the other hand, the initialization reduces the skill in predicting the warming trend over some regions outside the Atlantic. The annual-mean atlantic meridional overturning circulation index, which is defined here as the maximum of the zonally-integrated overturning stream function at mid-latitude, is predictable up to a 4-year lead time, consistent with the predictable signal in upper ocean heat content over the North Atlantic. While the 6- to 9-year forecast skill measured by mean squared skill score shows 50 % improvement in the upper ocean heat content over the subtropical and mid-latitude Atlantic, prediction skill is relatively low in the subpolar gyre. This low skill is due in part to features in the spatial pattern of the dominant simulated decadal mode in upper ocean heat content over this region that differ from observations. An analysis of the large-scale temperature budget shows that this is the result of a model bias, implying that realistic simulation of the climatological fields is crucial for skillful decadal forecasts.

  19. Flood forecasting model based on geographical information system

    OpenAIRE

    Dong, A.; Zhi-Jia, L.; Yong-Tuo, W.; Cheng, Y.; D. Yi-Heng

    2015-01-01

    In this paper, the Antecedent Precipitation Index Model (API) combined with Nash’s Instantaneous Unit Curve Method is adopted for flood forecasting. The parameters n and k of Nash’s Method is obtained by setting up the mathematic relation between these two parameters and topographic characteristics. Based on the DEM information, ArcGIS software is used to get the topographic characteristics and the topographic parameters. The Tunxi basin in the humid region was taken as an example for analysi...

  20. Forecasting the Acquisition of University Spin-Outs: An RBF Neural Network Approach

    Directory of Open Access Journals (Sweden)

    Weiwei Liu

    2017-01-01

    Full Text Available University spin-outs (USOs, creating businesses from university intellectual property, are a relatively common phenomena. As a knowledge transfer channel, the spin-out business model is attracting extensive attention. In this paper, the impacts of six equities on the acquisition of USOs, including founders, university, banks, business angels, venture capitals, and other equity, are comprehensively analyzed based on theoretical and empirical studies. Firstly, the average distribution of spin-out equity at formation is calculated based on the sample data of 350 UK USOs. According to this distribution, a radial basis function (RBF neural network (NN model is employed to forecast the effects of each equity on the acquisition. To improve the classification accuracy, the novel set-membership method is adopted in the training process of the RBF NN. Furthermore, a simulation test is carried out to measure the effects of six equities on the acquisition of USOs. The simulation results show that the increase of university’s equity has a negative effect on the acquisition of USOs, whereas the increase of remaining five equities has positive effects. Finally, three suggestions are provided to promote the development and growth of USOs.

  1. Artificial neural network and SARIMA based models for power load forecasting in Turkish electricity market.

    Science.gov (United States)

    Bozkurt, Ömer Özgür; Biricik, Göksel; Tayşi, Ziya Cihan

    2017-01-01

    Load information plays an important role in deregulated electricity markets, since it is the primary factor to make critical decisions on production planning, day-to-day operations, unit commitment and economic dispatch. Being able to predict the load for a short term, which covers one hour to a few days, equips power generation facilities and traders with an advantage. With the deregulation of electricity markets, a variety of short term load forecasting models are developed. Deregulation in Turkish Electricity Market has started in 2001 and liberalization is still in progress with rules being effective in its predefined schedule. However, there is a very limited number of studies for Turkish Market. In this study, we introduce two different models for current Turkish Market using Seasonal Autoregressive Integrated Moving Average (SARIMA) and Artificial Neural Network (ANN) and present their comparative performances. Building models that cope with the dynamic nature of deregulated market and are able to run in real-time is the main contribution of this study. We also use our ANN based model to evaluate the effect of several factors, which are claimed to have effect on electrical load.

  2. Synthesis of Ultra High Molecular Weight HPAM and Viscosity Forecast by BP Neural Network

    Directory of Open Access Journals (Sweden)

    Guohao CHEN

    2015-11-01

    Full Text Available Hydrolyzed polyacrylamide (HPAM is widely used to increase the sweep efficiency of water phase in oil reservoirs. It is very important to select proper polymer for the reservoirs. In this study, a series of ultra high molecular weight HPAMs were synthesized and characterized by FT-IR analysis. Their physical properties were tested under reservoir condition. BP neural network (BPNN was employed to forecast the viscosity of high molecular weight HPAM in produced water. The input indices including molecular weight, solid content, degree of hydrolysis, water-insoluble residue, polymer concentration, temperature of reservoir and salinity of produced water. The results show that all physical properties fulfill the requirements of Q/SY DQ1059-2005. This BPNN can predict the viscosity of ultra high molecular weight HPAM accurately. It is proposed that this BPNN can be used to screen proper polymers for enhance oil recovery.DOI: http://dx.doi.org/10.5755/j01.ms.21.4.9698

  3. Development of a system for accurate forecasting of solar activity

    Science.gov (United States)

    Sofia, Sabatino

    1994-10-01

    The objectives were to study the solar activity cycle both to understand its physical nature and to forecast the timing and magnitude of future maxima with as much anticipation as possible. Because solar activity affects so many processes on Earth, from the reliability of solid state components on satellites, to electric power grids, to the orbital lifetime of low Earth orbit satellites, etc., such information is important to the DoD in general, and to the USAF in particular. The specific components of this study were three different tasks. The first consisted in developing an empirical forecasting scheme based on general but sound physical principles whose only objective was to provide the timing and magnitude of the following activity maximum both half-a-cycle and, hopefully, one-and-a-half cycle in advance. The second task involved a realistic modeling of the magnetized flow in the solar convective envelope with the ultimate objective of producing a dynamo model sufficiently solid to allow detailed forecasting of the behavior of future cycles. The third task involved partial support for the development of the Solar Disk Sextant, a spaceborne experiment which measures variations of the size and shape of the Sun with milli-arcsec accuracy.

  4. THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES

    Directory of Open Access Journals (Sweden)

    Subanar Subanar

    2006-01-01

    Full Text Available Recently, one of the central topics for the neural networks (NN community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series with both trend and seasonal patterns. Limited empirical studies on seasonal time series forecasting with neural networks show that some find neural networks are able to model seasonality directly and prior deseasonalization is not necessary, and others conclude just the opposite. In this research, we study particularly on the effectiveness of data preprocessing, including detrending and deseasonalization by applying Decomposition method on NN modeling and forecasting performance. We use two kinds of data, simulation and real data. Simulation data are examined on multiplicative of trend and seasonality patterns. The results are compared to those obtained from the classical time series model. Our result shows that a combination of detrending and deseasonalization by applying Decomposition method is the effective data preprocessing on the use of NN for forecasting trend and seasonal time series.

  5. A search for model parsimony in a real time flood forecasting system

    Science.gov (United States)

    Grossi, G.; Balistrocchi, M.

    2009-04-01

    As regards the hydrological simulation of flood events, a physically based distributed approach is the most appealing one, especially in those areas where the spatial variability of the soil hydraulic properties as well as of the meteorological forcing cannot be left apart, such as in mountainous regions. On the other hand, dealing with real time flood forecasting systems, less detailed models requiring a minor number of parameters may be more convenient, reducing both the computational costs and the calibration uncertainty. In fact in this case a precise quantification of the entire hydrograph pattern is not necessary, while the expected output of a real time flood forecasting system is just an estimate of the peak discharge, the time to peak and in some cases the flood volume. In this perspective a parsimonious model has to be found in order to increase the efficiency of the system. A suitable case study was identified in the northern Apennines: the Taro river is a right tributary to the Po river and drains about 2000 km2 of mountains, hills and floodplain, equally distributed . The hydrometeorological monitoring of this medium sized watershed is managed by ARPA Emilia Romagna through a dense network of uptodate gauges (about 30 rain gauges and 10 hydrometers). Detailed maps of the surface elevation, land use and soil texture characteristics are also available. Five flood events were recorded by the new monitoring network in the years 2003-2007: during these events the peak discharge was higher than 1000 m3/s, which is actually quite a high value when compared to the mean discharge rate of about 30 m3/s. The rainfall spatial patterns of such storms were analyzed in previous works by means of geostatistical tools and a typical semivariogram was defined, with the aim of establishing a typical storm structure leading to flood events in the Taro river. The available information was implemented into a distributed flood event model with a spatial resolution of 90m

  6. Determining the bounds of skilful forecast range for probabilistic prediction of system-wide wind power generation

    Science.gov (United States)

    Cannon, Dirk; Brayshaw, David; Methven, John; Drew, Daniel

    2017-04-01

    State-of-the-art wind power forecasts beyond a few hours ahead rely on global numerical weather prediction models to forecast the future large-scale atmospheric state. Often they provide initial and boundary conditions for nested high resolution simulations. In this work, both upper and lower bounds on forecast range are identified within which global ensemble forecasts provide skilful information for system-wide wind power applications. An upper bound on forecast range is associated with the limit of predictability, beyond which forecasts have no more skill than predictions based on climatological statistics. A lower bound is defined at the lead time beyond which the resolved uncertainty associated with estimating the future large-scale atmospheric state is larger than the unresolved uncertainty associated with estimating the system-wide wind power response to a given large-scale state. The bounds of skillful ensemble forecast range are quantified for three leading global forecast systems. The power system of Great Britain (GB) is used as an example because independent verifying data is available from National Grid. The upper bound defined by forecasts of GB-total wind power generation at a specific point in time is found to be 6-8 days. The lower bound is found to be 1.4-2.4 days. Both bounds depend on the global forecast system and vary seasonally. In addition, forecasts of the probability of an extreme power ramp event were found to possess a shorter limit of predictability (4.5-5.5 days). The upper bound on this forecast range can only be extended by improving the global forecast system (outside the control of most users) or by changing the metric used in the probability forecast. Improved downscaling and microscale modelling of the wind farm response may act to decrease the lower bound. The potential gain from such improvements have diminishing returns beyond the short-range (out to around 2 days).

  7. NETWORK TRAFFIC FORCASTING IN INFORMATION-TELECOMMUNICATION SYSTEM OF PRYDNIPROVSK RAILWAYS BASED ON NEURO-FUZZY NETWORK

    Directory of Open Access Journals (Sweden)

    V. M. Pakhomovа

    2016-12-01

    Full Text Available Purpose. Continuous increase in network traffic in the information-telecommunication system (ITS of Prydniprovsk Railways leads to the need to determine the real-time network congestion and to control the data flows. One of the possible solutions is a method of forecasting the volume of network traffic (inbound and outbound using neural network technology that will prevent from server overload and improve the quality of services. Methodology. Analysis of current network traffic in ITS of Prydniprovsk Railways and preparation of sets: learning, test and validation ones was conducted as well as creation of neuro-fuzzy network (hybrid system in Matlab program and organization of the following phases on the appropriate sets: learning, testing, forecast adequacy analysis. Findings. For the fragment (Dnipropetrovsk – Kyiv in ITS of Prydniprovsk Railways we made a forecast (day ahead for volume of network traffic based on the hybrid system created in Matlab program; MAPE values are as follows: 6.9% for volume of inbound traffic; 7.7% for volume of outbound traffic. It was found that the average learning error of the hybrid system decreases in case of increase in: the number of inputs (from 2 to 4; the number of terms (from 2 to 5 of the input variable; learning sample power (from 20 to 100. A significant impact on the average learning error of the hybrid system is caused by the number of terms of its input variable. It was determined that the lowest value of the average learning error is provided by 4-input hybrid system, it ensures more accurate learning of the neuro-fuzzy network by the hybrid method. Originality. The work resulted in the dependences for the average hybrid system error of the network traffic volume forecasting for the fragment (Dnipropetrovsk-Kyiv in ITS Prydniprovsk Railways on: the number of its inputs, the number of input variable terms, the learning sample power for different learning methods. Practical value. Forecasting of

  8. A seamless global hydrological monitoring and forecasting system for water resources assessment and hydrological hazard early warning

    Science.gov (United States)

    Sheffield, Justin; He, Xiaogang; Wood, Eric; Pan, Ming; Wanders, Niko; Zhan, Wang; Peng, Liqing

    2017-04-01

    Sustainable management of water resources and mitigation of the impacts of hydrological hazards are becoming ever more important at large scales because of inter-basin, inter-country and inter-continental connections in water dependent sectors. These include water resources management, food production, and energy production, whose needs must be weighed against the water needs of ecosystems and preservation of water resources for future generations. The strains on these connections are likely to increase with climate change and increasing demand from burgeoning populations and rapid development, with potential for conflict over water. At the same time, network connections may provide opportunities to alleviate pressures on water availability through more efficient use of resources such as trade in water dependent goods. A key constraint on understanding, monitoring and identifying solutions to increasing competition for water resources and hazard risk is the availability of hydrological data for monitoring and forecasting water resources and hazards. We present a global online system that provides continuous and consistent water products across time scales, from the historic instrumental period, to real-time monitoring, short-term and seasonal forecasts, and climate change projections. The system is intended to provide data and tools for analysis of historic hydrological variability and trends, water resources assessment, monitoring of evolving hazards and forecasts for early warning, and climate change scale projections of changes in water availability and extreme events. The system is particular useful for scientists and stakeholders interested in regions with less available in-situ data, and where forecasts have the potential to help decision making. The system is built on a database of high-resolution climate data from 1950 to present that merges available observational records with bias-corrected reanalysis and satellite data, which then drives a coupled land

  9. Using Adaptive Neural-Fuzzy Inference Systems (ANFIS for Demand Forecasting and an Application

    Directory of Open Access Journals (Sweden)

    Onur Doğan

    2016-06-01

    Full Text Available Due to the rapid increase in global competition among organizations and companies, rational approaches in decision making have become indispensable for organizations in today’s world. Establishing a safe and robust path through uncertainties and risks depends on the decision units’ ability of using scientific methods as well as technology. Demand forecasting is known to be one of the most critical problems in organizations.  A company which supports its demand forecasting mechanism with scientific methodologies could increase its productivity and efficiency in all other functions. New methods, such as fuzzy logic and artificial neural networks are frequently being used as a decision-making mechanism in organizations and companies recently.  In this study, it is aimed to solve a critical demand forecasting problem with ANFIS. In the first phase of the study, the factors which impact demand forecasting are determined, and then a database of the model is established using these factors. It has been shown that ANFIS could be used for demand forecasting.

  10. Evaluation of a wildfire smoke forecasting system as a tool for public health protection.

    Science.gov (United States)

    Yao, Jiayun; Brauer, Michael; Henderson, Sarah B

    2013-10-01

    Exposure to wildfire smoke has been associated with cardiopulmonary health impacts. Climate change will increase the severity and frequency of smoke events, suggesting a need for enhanced public health protection. Forecasts of smoke exposure can facilitate public health responses. We evaluated the utility of a wildfire smoke forecasting system (BlueSky) for public health protection by comparing its forecasts with observations and assessing their associations with population-level indicators of respiratory health in British Columbia, Canada. We compared BlueSky PM2.5 forecasts with PM2.5 measurements from air quality monitors, and BlueSky smoke plume forecasts with plume tracings from National Oceanic and Atmospheric Administration Hazard Mapping System remote sensing data. Daily counts of the asthma drug salbutamol sulfate dispensations and asthma-related physician visits were aggregated for each geographic local health area (LHA). Daily continuous measures of PM2.5 and binary measures of smoke plume presence, either forecasted or observed, were assigned to each LHA. Poisson regression was used to estimate the association between exposure measures and health indicators. We found modest agreement between forecasts and observations, which was improved during intense fire periods. A 30-μg/m3 increase in BlueSky PM2.5 was associated with an 8% increase in salbutamol dispensations and a 5% increase in asthma-related physician visits. BlueSky plume coverage was associated with 5% and 6% increases in the two health indicators, respectively. The effects were similar for observed smoke, and generally stronger in very smoky areas. BlueSky forecasts showed modest agreement with retrospective measures of smoke and were predictive of respiratory health indicators, suggesting they can provide useful information for public health protection.

  11. Rain gauge network design for flood forecasting using multi-criteria decision analysis and clustering techniques in lower Mahanadi river basin, India

    Directory of Open Access Journals (Sweden)

    Anil Kumar Kar

    2015-09-01

    New hydrological insights for the region: This study establishes different possible key RG networks using Hall’s method, analytical hierarchical process (AHP, self organization map (SOM and hierarchical clustering (HC using the characteristics of each rain gauge occupied Thiessen polygon area. Efficiency of the key networks is tested by artificial neural network (ANN, Fuzzy and NAM rainfall-runoff models. Furthermore, flood forecasting has been carried out using the three most effective RG networks which uses only 7 RGs instead of 14 gauges established in the Kantamal sub-catchment, Mahanadi basin. The Fuzzy logic applied on the key RG network derived using AHP has shown the best result for flood forecasting with efficiency of 82.74% for 1-day lead period. This study demonstrates the design procedure of key RG network for effective flood forecasting particularly when there is difficulty in gathering the information from all RGs.

  12. RECOMMENDER SYSTEMS IN SOCIAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Cleomar Valois Batista Jr

    2011-12-01

    Full Text Available The continued and diversified growth of social networks has changed the way in which users interact with them. With these changes, what once was limited to social contact is now used for exchanging ideas and opinions, creating the need for new features. Users have so much information at their fingertips that they are unable to process it by themselves; hence, the need to develop new tools. Recommender systems were developed to address this need and many techniques were used for different approaches to the problem. To make relevant recommendations, these systems use large sets of data, not taking the social network of the user into consideration. Developing a recommender system that takes into account the social network of the user is another way of tackling the problem. The purpose of this project is to use the theory of six degrees of separation (Watts 2003 amongst users of a social network to enhance existing recommender systems.

  13. Analysis of the surface temperature and wind forecast errors of the NCAR-AirDat operational CONUS 4-km WRF forecasting system

    Science.gov (United States)

    Wyszogrodzki, Andrzej A.; Liu, Yubao; Jacobs, Neil; Childs, Peter; Zhang, Yongxin; Roux, Gregory; Warner, Thomas T.

    2013-11-01

    Investigating the characteristics of model-forecast errors using various statistical and object-oriented methods is necessary for providing useful guidance to end-users and model developers as well. To this end, the random and systematic errors (i.e., biases) of the 2-m temperature and 10-m wind predictions of the NCAR-AirDat weather research and forecasting (WRF)-based real-time four-dimensional data assimilation (RTFDDA) and forecasting system are analyzed. This system has been running operationally over a contiguous United States (CONUS) domain at a 4-km grid spacing with four forecast cycles daily from June 2009 to September 2010. In the result an exceptionally useful forecast dataset was generated and used for studying the error properties of the model forecasts, in terms of both a longer time period and a broader coverage of geographic regions than previously studied. Spatiotemporal characteristics of the errors are investigated based on the 24-h forecasts between June 2009 and April 2010, and the 72-h forecasts between May and September 2010. It was found that the biases of both wind and temperature forecasts vary greatly seasonally and diurnally, with dependency on the forecast length, station elevation, geographical location, and meteorological conditions. The temperature showed systematic cold biases during the daytime at all station elevations and warm biases during the nighttime above 1,000 m above sea level (ASL), while below 600 m ASL cold biases occurred during the nighttime. The forecasts of surface wind speed exhibited strong positive biases during the nighttime, while the negative biases were observed in the spring and summer afternoons. The surface wind speed was mostly over-predicted except for the stations located between 1,000 and 2,100 m ASL, for which negative biases were identified for most forecast cycles. The highest wind-speed errors were found over the high terrain and near sea-level stations. The wind-direction errors were relatively

  14. Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems

    Energy Technology Data Exchange (ETDEWEB)

    Chaabene, Maher; Ben Ammar, Mohsen [The High Institute of Technological Studies (ISET), Sfax (Tunisia); Unite de commande de machines et energies renouvelables CMER, ENIS (Tunisia)

    2008-07-15

    This paper introduces a dynamic forecasting of irradiance and ambient temperature. The medium term forecasting (MTF) gives a daily meteorological behaviour. It consists of a neuro-fuzzy estimator based on meteorological parameters' behaviours during the days before, and on time distribution models. As for the short term forecasting (STF), it estimates, for a 5 min time step ahead, the meteorological parameters evolution. It is ensured by the Auto-Regressive Moving Average (ARMA) model of the MTF associated to a Kalman filter. STF uses instantaneous measured data, delivered by a data acquisition system, so as to accomplish the forecast. Herein we describe our method and we present forecasting results. Validation is based on measurements taken at the Energy and Thermal Research Centre (CRTEn) in the north of Tunisia. Since our work delivers accurate meteorological parameters forecasting, the obtained results can be easily adapted to forecast any solar conversion system output. (author)

  15. ENSO Prediction in the NASA GMAO GEOS-5 Seasonal Forecasting System

    Science.gov (United States)

    Kovach, R. M.; Borovikov, A.; Marshak, J.; Pawson, S.; Vernieres, G.

    2016-12-01

    Seasonal-to-Interannual coupled forecasts are conducted in near-real time with the Goddard Earth Observing System (GEOS) Atmosphere-Ocean General Circulation Model (AOGCM). A 30-year suite of 9-month hindcasts is available, initialized with the MERRA-Ocean, MERRA-Land, and MERRA atmospheric fields. These forecasts are used to predict the timing and magnitude of ENSO and other short-term climate variability. The 2015 El Niño peaked in November 2015 and was considered a "very strong" event with the Equatorial Pacific Ocean sea-surface-temperature (SST) anomalies higher than 2.0 °C. These very strong temperature anomalies began in Sep/Oct/Nov (SON) of 2015 and persisted through Dec/Jan/Feb (DJF) of 2016. The other two very strong El Niño events recently recorded occurred in 1981/82 and 1997/98. The GEOS-5 system began predicting a very strong El Niño for SON starting with the March 2015 forecast. At this time, the GMAO forecast was an outlier in both the NMME and IRI multi-model ensemble prediction plumes. The GMAO May 2015 forecast for the November 2015 peak in temperature anomaly in the Niño3.4 region was in excellent agreement with the real event, but in May this forecast was still one of the outliers in the multi-model forecasts. The GEOS-5 May 2015 forecast also correctly predicted the weakening of the Eastern Pacific (Niño1+2) anomalies for SON. We will present a summary of the NASA GMAO GEOS-5 Seasonal Forecast System skills based on historic hindcasts. Initial conditions, prediction of ocean surface and subsurface evolution for the 2015/16 El Niño will be compared to the 1998/97 event. GEOS-5 capability to predict the precipitation, i.e. to model the teleconnection patterns associated with El Niño will also be shown. To conclude, we will highlight some new developments in the GEOS forecasting system.

  16. Forecasts for the Canadian Lynx time series using method that bombine neural networks, wavelet shrinkage and decomposition

    Directory of Open Access Journals (Sweden)

    Levi Lopes Teixeira

    2015-12-01

    Full Text Available Time series forecasting is widely used in various areas of human knowledge, especially in the planning and strategic direction of companies. The success of this task depends on the forecasting techniques applied. In this paper, a hybrid approach to project time series is suggested. To validate the methodology, a time series already modeled by other authors was chosen, allowing the comparison of results. The proposed methodology includes the following techniques: wavelet shrinkage, wavelet decomposition at level r, and artificial neural networks (ANN. Firstly, a time series to be forecasted is submitted to the proposed wavelet filtering method, which decomposes it to components of trend and linear residue. Then, both are decomposed via level r wavelet decomposition, generating r + 1 Wavelet Components (WCs for each one; and then each WC is individually modeled by an ANN. Finally, the predictions for all WCs are linearly combined, producing forecasts to the underlying time series. For evaluating purposes, the time series of Canadian Lynx has been used, and all results achieved by the proposed method were better than others in existing literature.

  17. The european flood alert system EFAS – Part 2: Statistical skill assessment of probabilistic and deterministic operational forecasts

    Directory of Open Access Journals (Sweden)

    J. C. Bartholmes

    2009-02-01

    Full Text Available Since 2005 the European Flood Alert System (EFAS has been producing probabilistic hydrological forecasts in pre-operational mode at the Joint Research Centre (JRC of the European Commission. EFAS aims at increasing preparedness for floods in trans-national European river basins by providing medium-range deterministic and probabilistic flood forecasting information, from 3 to 10 days in advance, to national hydro-meteorological services.

    This paper is Part 2 of a study presenting the development and skill assessment of EFAS. In Part 1, the scientific approach adopted in the development of the system has been presented, as well as its basic principles and forecast products. In the present article, two years of existing operational EFAS forecasts are statistically assessed and the skill of EFAS forecasts is analysed with several skill scores. The analysis is based on the comparison of threshold exceedances between proxy-observed and forecasted discharges. Skill is assessed both with and without taking into account the persistence of the forecasted signal during consecutive forecasts.

    Skill assessment approaches are mostly adopted from meteorology and the analysis also compares probabilistic and deterministic aspects of EFAS. Furthermore, the utility of different skill scores is discussed and their strengths and shortcomings illustrated. The analysis shows the benefit of incorporating past forecasts in the probability analysis, for medium-range forecasts, which effectively increases the skill of the forecasts.

  18. Multilevel Complex Networks and Systems

    Science.gov (United States)

    Caldarelli, Guido

    2014-03-01

    Network theory has been a powerful tool to model isolated complex systems. However, the classical approach does not take into account the interactions often present among different systems. Hence, the scientific community is nowadays concentrating the efforts on the foundations of new mathematical tools for understanding what happens when multiple networks interact. The case of economic and financial networks represents a paramount example of multilevel networks. In the case of trade, trade among countries the different levels can be described by the different granularity of the trading relations. Indeed, we have now data from the scale of consumers to that of the country level. In the case of financial institutions, we have a variety of levels at the same scale. For example one bank can appear in the interbank networks, ownership network and cds networks in which the same institution can take place. In both cases the systemically important vertices need to be determined by different procedures of centrality definition and community detection. In this talk I will present some specific cases of study related to these topics and present the regularities found. Acknowledged support from EU FET Project ``Multiplex'' 317532.

  19. Effects of the uncertainty of energy price and water availability forecasts on the operation of Alpine hydropower reservoir systems

    Science.gov (United States)

    Anghileri, D.; Castelletti, A.; Burlando, P.

    2016-12-01

    European energy markets have experienced dramatic changes in the last years because of the massive introduction of Variable Renewable Sources (VRSs), such as wind and solar power sources, in the generation portfolios in many countries. VRSs i) are intermittent, i.e., their production is highly variable and only partially predictable, ii) are characterized by no correlation between production and demand, iii) have negligible costs of production, and iv) have been largely subsidized. These features result in lower energy prices, but, at the same time, in increased price volatility, and in network stability issues, which pose a threat to traditional power sources because of smaller incomes and higher maintenance costs associated to a more flexible operation of power systems. Storage hydropower systems play an important role in compensating production peaks, both in term of excess and shortage of energy. Traditionally, most of the research effort in hydropower reservoir operation has focused on modeling and forecasting reservoir inflow as well as designing reservoir operation accordingly. Nowadays, price variability may be the largest source of uncertainty in the context of hydropower systems, especially when considering medium-to-large reservoirs, whose storage can easily buffer small inflow fluctuations. In this work, we compare the effects of uncertain inflow and energy price forecasts on hydropower production and profitability. By adding noise to historic inflow and price trajectories, we build a set of synthetic forecasts corresponding to different levels of predictability and assess their impact on reservoir operating policies and performances. The study is conducted on different hydropower systems, including storage systems and pumped-storage systems, with different characteristics, e.g., different inflow-capacity ratios. The analysis focuses on Alpine hydropower systems where the hydrological regime ranges from purely ice and snow-melt dominated to mixed snow

  20. Data assimilation of dust aerosol observations for the CUACE/dust forecasting system

    Directory of Open Access Journals (Sweden)

    T. Niu

    2008-07-01

    Full Text Available A data assimilation system (DAS was developed for the Chinese Unified Atmospheric Chemistry Environment – Dust (CUACE/Dust forecast system and applied in the operational forecasts of sand and dust storm (SDS in spring 2006. The system is based on a three dimensional variational method (3D-Var and uses extensively the measurements of surface visibility (phenomena and dust loading retrieval from the Chinese geostationary satellite FY-2C. By a number of case studies, the DAS was found to provide corrections to both under- and over-estimates of SDS, presenting a major improvement to the forecasting capability of CUACE/Dust in the short-term variability in the spatial distribution and intensity of dust concentrations in both source regions and downwind areas. The seasonal mean Threat Score (TS over the East Asia in spring 2006 increased from 0.22 to 0.31 by using the data assimilation system, a 41% enhancement. The forecast results with DAS usually agree with the dust loading retrieved from FY-2C and visibility distribution from surface meteorological stations, which indicates that the 3D-Var method is very powerful by the unification of observation and numerical model to improve the performance of forecast model.

  1. A Self-Adapting Approach for Forecast-Less Scheduling of Electrical Energy Storage Systems in a Liberalized Energy Market

    Directory of Open Access Journals (Sweden)

    Ninh Nguyen Quang

    2013-11-01

    Full Text Available In this paper, an original scheduling approach for optimal dispatch of electrical Energy Storage Systems (ESS in modern distribution networks is proposed. The control system is based on fuzzy rules and does not use forecasts since it repairs the past history according to the real time data on the electrical energy cost, renewable energy production and load. When the system detects a worsening of performances, the fuzzy logic rule-based control system self-adapts its membership functions using an economic indicator. The common use, in the relevant literature, of forecasted values in such systems can lead to large errors and economic losses. Moreover the speed of calculation guaranteed by the fuzzy control system allows the execution of new calculations even with high frequency. After the Introduction section, where the state of the art on the topic is outlined, the problem formulation is presented and an interesting application of the considered approach to the control on a medium size battery with real world data is proposed.

  2. Forecasting skills of the ensemble hydro-meteorological system for the Po river floods

    Science.gov (United States)

    Ricciardi, Giuseppe; Montani, Andrea; Paccagnella, Tiziana; Pecora, Silvano; Tonelli, Fabrizio

    2013-04-01

    The Po basin is the largest and most economically important river-basin in Italy. Extreme hydrological events, including floods, flash floods and droughts, are expected to become more severe in the next future due to climate change, and related ground effects are linked both with environmental and social resilience. A Warning Operational Center (WOC) for hydrological event management was created in Emilia Romagna region. In the last years, the WOC faced challenges in legislation, organization, technology and economics, achieving improvements in forecasting skill and information dissemination. Since 2005, an operational forecasting and modelling system for flood modelling and forecasting has been implemented, aimed at supporting and coordinating flood control and emergency management on the whole Po basin. This system, referred to as FEWSPo, has also taken care of environmental aspects of flood forecast. The FEWSPo system has reached a very high level of complexity, due to the combination of three different hydrological-hydraulic chains (HEC-HMS/RAS - MIKE11 NAM/HD, Topkapi/Sobek), with several meteorological inputs (forecasted - COSMOI2, COSMOI7, COSMO-LEPS among others - and observed). In this hydrological and meteorological ensemble the management of the relative predictive uncertainties, which have to be established and communicated to decision makers, is a debated scientific and social challenge. Real time activities face professional, modelling and technological aspects but are also strongly interrelated with organization and human aspects. The authors will report a case study using the operational flood forecast hydro-meteorological ensemble, provided by the MIKE11 chain fed by COSMO_LEPS EQPF. The basic aim of the proposed approach is to analyse limits and opportunities of the long term forecast (with a lead time ranging from 3 to 5 days), for the implementation of low cost actions, also looking for a well informed decision making and the improvement of

  3. The Santos Basin Ocean Observing System: From R&D to Operational Regional Forecasts

    Science.gov (United States)

    Da Rocha Fragoso, M.; Moore, A. M.; dos Santos, F. A.; Marques Da Cruz, L.; Carvalho, G. V.; Soares, F.

    2016-02-01

    Santos Basin is located on the Southwestern Brazilian Ocean Basin and comprises the main offshore oil reserves of Brazil. The exploration and production activities on its ocean are growing in accelerated pace, which means that oil spill contingency and search & rescue operations are likely to be more frequent. Therefore, ocean current reliable nowcasts and forecasts has become even more important for this region. The Santos Basin Ocean Observing System was designed as an R&D project and its main objective was to establish and maintain a systematic oceanographic data collection for this region in order to study its ocean dynamics and improve regional ocean forecast through data assimilation. In the first three years of the project surface drifters, profiling floats and gliders were deployed to measure and monitor mainly the Brazil Current Western Boundary System, a highly unstable baroclinic current system, that present several meanders and mesoscale eddies activities. Throughout the development of the project, the team involved was able to learn how to operate the equipment, treat the collected data and use it to assimilate on the Regional Ocean Modeling System (ROMS). After performing a one-year 4DVAR assimilation cycle (Fragoso et al., 2015) in which the forecasting skill was assessed, the system was considered mature enough to start producing ocean circulation forecasts for Santos Basin. It is the first time in Brazil that a regional ocean model using a 4DVAR data assimilation scheme was used to produce high resolution operational ocean current forecasts. This paper describes all the components of this forecasting system, its main results and discoveries with special focus on the Brazil Current System Transport and mesocale eddies dynamics and statistics.

  4. Reduction of the dimension of neural network models in problems of pattern recognition and forecasting

    Science.gov (United States)

    Nasertdinova, A. D.; Bochkarev, V. V.

    2017-11-01

    Deep neural networks with a large number of parameters are a powerful tool for solving problems of pattern recognition, prediction and classification. Nevertheless, overfitting remains a serious problem in the use of such networks. A method of solving the problem of overfitting is proposed in this article. This method is based on reducing the number of independent parameters of a neural network model using the principal component analysis, and can be implemented using existing libraries of neural computing. The algorithm was tested on the problem of recognition of handwritten symbols from the MNIST database, as well as on the task of predicting time series (rows of the average monthly number of sunspots and series of the Lorentz system were used). It is shown that the application of the principal component analysis enables reducing the number of parameters of the neural network model when the results are good. The average error rate for the recognition of handwritten figures from the MNIST database was 1.12% (which is comparable to the results obtained using the "Deep training" methods), while the number of parameters of the neural network can be reduced to 130 times.

  5. Spatial-temporal reproducibility assessment of global seasonal forecasting system version 5 model for Dam Inflow forecasting

    Science.gov (United States)

    Moon, S.; Suh, A. S.; Soohee, H.

    2016-12-01

    The GloSea5(Global Seasonal forecasting system version 5) is provided and operated by the KMA(Korea Meteorological Administration). GloSea5 provides Forecast(FCST) and Hindcast(HCST) data and its horizontal resolution is about 60km (0.83° x 0.56°) in the mid-latitudes. In order to use this data in watershed-scale water management, GloSea5 needs spatial-temporal downscaling. As such, statistical downscaling was used to correct for systematic biases of variables and to improve data reliability. HCST data is provided in ensemble format, and the highest statistical correlation(R2 = 0.60, RMSE = 88.92, NSE = 0.57) of ensemble precipitation was reported for the Yongdam Dam watershed on the #6 grid. Additionally, the original GloSea5(600.1mm) showed the greatest difference(-26.5%) compared to observations(816.1mm) during the summer flood season. However, downscaled GloSea5 was shown to have only a ?3.1% error rate. Most of the underestimated results corresponded to precipitation levels during the flood season and the downscaled GloSea5 showed important results of restoration in precipitation levels. Per the analysis results of spatial autocorrelation using seasonal Moran's I, the spatial distribution was shown to be statistically significant. These results can improve the uncertainty of original GloSea5 and substantiate its spatial-temporal accuracy and validity. The spatial-temporal reproducibility assessment will play a very important role as basic data for watershed-scale water management.

  6. Multi-scale quantitative precipitation forecasting using nonlinear and nonstationary teleconnection signals and artificial neural network models

    Science.gov (United States)

    Chang, Ni-Bin; Yang, Y. Jeffrey; Imen, Sanaz; Mullon, Lee

    2017-05-01

    Global sea surface temperature (SST) anomalies are observed to have a significant effect on terrestrial precipitation patterns throughout the United States. SST variations have been correlated with terrestrial precipitation via ocean-atmospheric interactions known as climate teleconnections. This study demonstrates how the scale effect could affect the forecasting accuracy with or without the inclusion of those newly discovered unknown teleconnection signals between Adirondack precipitation and SST anomaly in the Atlantic and Pacific oceans. Unique SST regions of both known and unknown telecommunication signals were extracted from the wavelet analysis and used as input variables in an artificial neural network (ANN) forecasting model. Monthly and seasonal scales were considered with respect to a host of long-term (30-year) nonlinear and nonstationary teleconnection signals detected locally at the study site of Adirondack. Similar intra-annual time-lag effects of SST on precipitation variability are salient at both time scales. Sensitivity analysis of four scenarios reveals that more improvements of the forecasting accuracy of the ANN model can be observed by including both known and unknown teleconnection patterns at both time scales, although such improvements are not salient. Research findings also highlight the importance of choosing the forecasting model at the seasonal scale to predict more accurate peak values and global trends of terrestrial precipitation in response to teleconnection signals. The scale shift from monthly to seasonal may improve results by 17% and 17 mm/day in terms of R squared and root of mean square error values, respectively, if both known and unknown SST regions are considered for forecasting.

  7. Solar Forecasting in a Challenging Insular Context

    Directory of Open Access Journals (Sweden)

    Philippe Lauret

    2016-01-01

    Full Text Available This paper aims at assessing the accuracy of different solar forecasting methods in the case of an insular context. Two sites of La Réunion Island, Le Tampon and Saint-Pierre, are chosen to do the benchmarking exercise. Réunion Island is a tropical island with a complex orography where cloud processes are mainly governed by local dynamics. As a consequence, Réunion Island exhibits numerous micro-climates. The two aforementioned sites are quite representative of the challenging character of solar forecasting in the case of a tropical island with complex orography. Hence, although distant from only 10 km, these two sites exhibit very different sky conditions. This work focuses on day-ahead and intra-day solar forecasting. Day-ahead solar forecasts are provided by the European Center for Medium-Range Weather Forecast (ECMWF. This organization maintains and runs the Numerical Weather Prediction (NWP model named Integrated Forecast System (IFS. In this work, post-processing techniques are applied to refine the output of the IFS model for day-ahead forecasting. Statistical models like a recursive linear model or a nonlinear model such as an artificial neural network are used to produce the intra-day solar forecasts. It is shown that a combination of the IFS model and the neural network model further improves the accuracy of the forecasts.

  8. Using NCAR Yellowstone for PhotoVoltaic Power Forecasts with Artificial Neural Networks and an Analog Ensemble

    Science.gov (United States)

    Cervone, G.; Clemente-Harding, L.; Alessandrini, S.; Delle Monache, L.

    2016-12-01

    A methodology based on Artificial Neural Networks (ANN) and an Analog Ensemble (AnEn) is presented to generate 72-hour deterministic and probabilistic forecasts of power generated by photovoltaic (PV) power plants using input from a numerical weather prediction model and computed astronomical variables. ANN and AnEn are used individually and in combination to generate forecasts for three solar power plant located in Italy. The computational scalability of the proposed solution is tested using synthetic data simulating 4,450 PV power stations. The NCAR Yellowstone supercomputer is employed to test the parallel implementation of the proposed solution, ranging from 1 node (32 cores) to 4,450 nodes (141,140 cores). Results show that a combined AnEn + ANN solution yields best results, and that the proposed solution is well suited for massive scale computation.

  9. Application of Artificial Neural Network Forecasts to Predict Fog at Canberra International Airport

    National Research Council Canada - National Science Library

    Fabbian, Dustin; de Dear, Richard; Lellyett, Stephen

    2007-01-01

    ... obtained from the Australian Bureau of Meteorology was used to develop, train, test, and validate ANNs designed to predict log occurrence. Fog forecasting aids were developed for 3-, 6-, 12-, a...

  10. Addressing model error through atmospheric stochastic physical parametrizations: impact on the coupled ECMWF seasonal forecasting system

    Science.gov (United States)

    Weisheimer, Antje; Corti, Susanna; Palmer, Tim; Vitart, Frederic

    2014-01-01

    The finite resolution of general circulation models of the coupled atmosphere–ocean system and the effects of sub-grid-scale variability present a major source of uncertainty in model simulations on all time scales. The European Centre for Medium-Range Weather Forecasts has been at the forefront of developing new approaches to account for these uncertainties. In particular, the stochastically perturbed physical tendency scheme and the stochastically perturbed backscatter algorithm for the atmosphere are now used routinely for global numerical weather prediction. The European Centre also performs long-range predictions of the coupled atmosphere–ocean climate system in operational forecast mode, and the latest seasonal forecasting system—System 4—has the stochastically perturbed tendency and backscatter schemes implemented in a similar way to that for the medium-range weather forecasts. Here, we present results of the impact of these schemes in System 4 by contrasting the operational performance on seasonal time scales during the retrospective forecast period 1981–2010 with comparable simulations that do not account for the representation of model uncertainty. We find that the stochastic tendency perturbation schemes helped to reduce excessively strong convective activity especially over the Maritime Continent and the tropical Western Pacific, leading to reduced biases of the outgoing longwave radiation (OLR), cloud cover, precipitation and near-surface winds. Positive impact was also found for the statistics of the Madden–Julian oscillation (MJO), showing an increase in the frequencies and amplitudes of MJO events. Further, the errors of El Niño southern oscillation forecasts become smaller, whereas increases in ensemble spread lead to a better calibrated system if the stochastic tendency is activated. The backscatter scheme has overall neutral impact. Finally, evidence for noise-activated regime transitions has been found in a cluster analysis of mid

  11. Analyzing the evolutionary mechanisms of the Air Transportation System-of-Systems using network theory and machine learning algorithms

    Science.gov (United States)

    Kotegawa, Tatsuya

    Complexity in the Air Transportation System (ATS) arises from the intermingling of many independent physical resources, operational paradigms, and stakeholder interests, as well as the dynamic variation of these interactions over time. Currently, trade-offs and cost benefit analyses of new ATS concepts are carried out on system-wide evaluation simulations driven by air traffic forecasts that assume fixed airline routes. However, this does not well reflect reality as airlines regularly add and remove routes. A airline service route network evolution model that projects route addition and removal was created and combined with state-of-the-art air traffic forecast methods to better reflect the dynamic properties of the ATS in system-wide simulations. Guided by a system-of-systems framework, network theory metrics and machine learning algorithms were applied to develop the route network evolution models based on patterns extracted from historical data. Constructing the route addition section of the model posed the greatest challenge due to the large pool of new link candidates compared to the actual number of routes historically added to the network. Of the models explored, algorithms based on logistic regression, random forests, and support vector machines showed best route addition and removal forecast accuracies at approximately 20% and 40%, respectively, when validated with historical data. The combination of network evolution models and a system-wide evaluation tool quantified the impact of airline route network evolution on air traffic delay. The expected delay minutes when considering network evolution increased approximately 5% for a forecasted schedule on 3/19/2020. Performance trade-off studies between several airline route network topologies from the perspectives of passenger travel efficiency, fuel burn, and robustness were also conducted to provide bounds that could serve as targets for ATS transformation efforts. The series of analysis revealed that high

  12. Promoting Social Network Awareness: A Social Network Monitoring System

    Science.gov (United States)

    Cadima, Rita; Ferreira, Carlos; Monguet, Josep; Ojeda, Jordi; Fernandez, Joaquin

    2010-01-01

    To increase communication and collaboration opportunities, members of a community must be aware of the social networks that exist within that community. This paper describes a social network monitoring system--the KIWI system--that enables users to register their interactions and visualize their social networks. The system was implemented in a…

  13. Demand forecasting for automotive sector in Malaysia by system dynamics approach

    Energy Technology Data Exchange (ETDEWEB)

    Zulkepli, Jafri, E-mail: zhjafri@uum.edu.my; Abidin, Norhaslinda Zainal, E-mail: nhaslinda@uum.edu.my [School of Quantitative Sciences, Universiti Utara Malaysia, Sintok, Kedah (Malaysia); Fong, Chan Hwa, E-mail: hfchan7623@yahoo.com [SWM Environment Sdn. Bhd.Level 17, Menara LGB, Taman Tun Dr. Ismail Kuala Lumpur (Malaysia)

    2015-12-11

    In general, Proton as an automotive company needs to forecast future demand of the car to assist in decision making related to capacity expansion planning. One of the forecasting approaches that based on judgemental or subjective factors is normally used to forecast the demand. As a result, demand could be overstock that eventually will increase the operation cost; or the company will face understock, which resulted losing their customers. Due to automotive industry is very challenging process because of high level of complexity and uncertainty involved in the system, an accurate tool to forecast the future of automotive demand from the modelling perspective is required. Hence, the main objective of this paper is to forecast the demand of automotive Proton car industry in Malaysia using system dynamics approach. Two types of intervention namely optimistic and pessimistic experiments scenarios have been tested to determine the capacity expansion that can prevent the company from overstocking. Finding from this study highlighted that the management needs to expand their production for optimistic scenario, whilst pessimistic give results that would otherwise. Finally, this study could help Proton Edar Sdn. Bhd (PESB) to manage the long-term capacity planning in order to meet the future demand of the Proton cars.

  14. Technology forecast and applications for autonomous, intelligent systems. [for space station, shuttle, and interplanetary missions

    Science.gov (United States)

    Lum, Henry, Jr.; Heer, Ewald

    1988-01-01

    Significant research products which have emerged from the core program of NASA's Office of Aeronautics and Space Technology (OAST) are discussed. The Space Station Thermal Control System, the Space Shuttle Integrated Communications Officer Station, the Launch Processing System, the Expert Scheduling System for Pioneer Venus Spacecraft, a Bayesian classification system, and a spaceborne multiprocessor system are included. The technology trends which led to these results are discussed and future developments in technology are forecasted.

  15. Forecasting drought risks for a water supply storage system using bootstrap position analysis

    Science.gov (United States)

    Tasker, Gary; Dunne, Paul

    1997-01-01

    Forecasting the likelihood of drought conditions is an integral part of managing a water supply storage and delivery system. Position analysis uses a large number of possible flow sequences as inputs to a simulation of a water supply storage and delivery system. For a given set of operating rules and water use requirements, water managers can use such a model to forecast the likelihood of specified outcomes such as reservoir levels falling below a specified level or streamflows falling below statutory passing flows a few months ahead conditioned on the current reservoir levels and streamflows. The large number of possible flow sequences are generated using a stochastic streamflow model with a random resampling of innovations. The advantages of this resampling scheme, called bootstrap position analysis, are that it does not rely on the unverifiable assumption of normality and it allows incorporation of long-range weather forecasts into the analysis.

  16. Post-processing of a low-flow forecasting system in the Thur basin (Switzerland)

    Science.gov (United States)

    Bogner, Konrad; Joerg-Hess, Stefanie; Bernhard, Luzi; Zappa, Massimiliano

    2015-04-01

    Low-flows and droughts are natural hazards with potentially severe impacts and economic loss or damage in a number of environmental and socio-economic sectors. As droughts develop slowly there is time to prepare and pre-empt some of these impacts. Real-time information and forecasting of a drought situation can therefore be an effective component of drought management. Although Switzerland has traditionally been more concerned with problems related to floods, in recent years some unprecedented low-flow situations have been experienced. Driven by the climate change debate a drought information platform has been developed to guide water resources management during situations where water resources drop below critical low-flow levels characterised by the indices duration (time between onset and offset), severity (cumulative water deficit) and magnitude (severity/duration). However to gain maximum benefit from such an information system it is essential to remove the bias from the meteorological forecast, to derive optimal estimates of the initial conditions, and to post-process the stream-flow forecasts. Quantile mapping methods for pre-processing the meteorological forecasts and improved data assimilation methods of snow measurements, which accounts for much of the seasonal stream-flow predictability for the majority of the basins in Switzerland, have been tested previously. The objective of this study is the testing of post-processing methods in order to remove bias and dispersion errors and to derive the predictive uncertainty of a calibrated low-flow forecast system. Therefore various stream-flow error correction methods with different degrees of complexity have been applied and combined with the Hydrological Uncertainty Processor (HUP) in order to minimise the differences between the observations and model predictions and to derive posterior probabilities. The complexity of the analysed error correction methods ranges from simple AR(1) models to methods including

  17. Ocean Model, Analysis and Prediction System version 3: operational global ocean forecasting

    Science.gov (United States)

    Brassington, Gary; Sandery, Paul; Sakov, Pavel; Freeman, Justin; Divakaran, Prasanth; Beckett, Duan

    2017-04-01

    The Ocean Model, Analysis and Prediction System version 3 (OceanMAPSv3) is a near-global (75S-75N; no sea-ice), uniform horizontal resolution (0.1°x0.1°), 51 vertical level ocean forecast system producing daily analyses and 7 day forecasts. This system was declared operational at the Bureau of Meteorology in April 2016 and subsequently upgraded to include ACCESS-G APS2 in June 2016 and finally ported to the Bureau's new supercomputer in Sep 2016. This system realises the original vision of the BLUElink projects (2003-2015) to provide global forecasts of the ocean geostrophic turbulence (eddies and fronts) in support of Naval operations as well as other national services. The analysis system has retained an ensemble-based optimal interpolation method with 144 stationary ensemble members derived from a multi