Bayesian Model Averaging of Load Demand Forecasts from Neural Network Models

Creating a set of a number of neural network (NN) models in an ensemble and accumulating them can achieve better overview capability as compared to single neural network. Neural network ensembles are designed to provide solutions to particular problems. Many researchers and academicians have adopted this NN ensemble technique, especially in machine learning, and has been applied in various fields of engineering, medicine and information technology. This paper present a robust aggregation methodology for load demand forecasting based on Bayesian Model Averaging of a set of neural network models in an ensemble. This paper estimate a vector of coefficient for individual NN models' forecasts using validation data-set. These coefficients, also known as weights, are equal to posterior probabilities of the models generating the forecasts. These BMA weights are then used in combining forecasts generated from NN models with test data-set. By comparing the Bayesian results with the Simple Averaging method, it was observed that benefits are obtained by utilizing an advanced method like BMA for forecast combinations.

[1]  Jing Shi,et al.  Bayesian adaptive combination of short-term wind speed forecasts from neural network models , 2011 .

[2]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[3]  C. Chatfield.  Model uncertainty, data mining and statistical inference , 1995 .

[4]  D. Srinivasan,et al.  Interval Type-2 Fuzzy Logic Systems for Load Forecasting: A Comparative Study , 2012, IEEE Transactions on Power Systems.

[5]  Wei-Chiang Hong,et al.  SVR with Hybrid Chaotic Immune Algorithm for Seasonal Load Demand Forecasting , 2011 .

[6]  A. Raftery,et al.  Using Bayesian Model Averaging to Calibrate Forecast Ensembles , 2005 .

[7]  Kuriakose Athappilly,et al.  A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models , 2005, Expert Syst. Appl..

[8]  Xuesong Zhang,et al.  Bayesian Neural Networks for Uncertainty Analysis of Hydrologic Modeling: A Comparison of Two Schemes , 2012, Water Resources Management.

[9]  R. Barzamini,et al.  Short term load forecasting for Iran National Power System and its regions using multi layer perceptron and fuzzy inference systems , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[10]  P. McSharry,et al.  Short-Term Load Forecasting Methods: An Evaluation Based on European Data , 2007, IEEE Transactions on Power Systems.

[11]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[12]  Saeid Nahavandi,et al.  Quantifying uncertainties of neural network-based electricity price forecasts , 2013 .

[13]  Chongqing Kang,et al.  Novel approach considering load-relative factors in short-term load forecasting , 2004 .

[14]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[15]  Saeid Nahavandi,et al.  Load Forecasting and Neural Networks: A Prediction Interval-Based Perspective , 2010 .

[16]  Joaquín Torres-Sospedra.  Ensembles of Artificial Neural Networks: Analysis and Development of Design Methods , 2011 .

[17]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[18]  J. Gooijer,et al.  Some recent developments in non-linear time series modelling, testing, and forecasting☆ , 1992 .

[19]  S. Nahavandi,et al.  Prediction Intervals for Short-Term Wind Farm Power Generation Forecasts , 2013, IEEE Transactions on Sustainable Energy.

[20]  Yongli Wang,et al.  Short-term power load forecasting based on IVL-BP neural network technology , 2012 .

[21]  Jan R. Magnus,et al.  A comparison of two model averaging techniques with an application to growth empirics , 2010 .

[22]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  A. Timmermann.  Chapter 4 Forecast Combinations , 2006 .

[24]  Chusak Limsakul,et al.  Mid-Term Load Forecasting: Level Suitably of Wavelet and Neural Network based on Factor Selection , 2012 .

[25]  Charles A. Ingene,et al.  Specification Searches: Ad Hoc Inference with Nonexperimental Data , 1980 .

[26]  Guoqiang Peter Zhang,et al.  A neural network ensemble method with jittered training data for time series forecasting , 2007, Inf. Sci..

[27]  Rob J Hyndman,et al.  Short-Term Load Forecasting Based on a Semi-Parametric Additive Model , 2012, IEEE Transactions on Power Systems.

[28]  R. Weron.  Modeling and Forecasting Electricity Loads and Prices , 2006 .

[29]  M. Steel,et al.  Benchmark Priors for Bayesian Model Averaging , 2001 .

[30]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[31]  Saeid Nahavandi,et al.  Construction of Optimal Prediction Intervals for Load Forecasting Problems , 2010, IEEE Transactions on Power Systems.

[32]  Z. Baharudin,et al.  Electricity forecasting for small scale power system using artificial neural network , 2011, 2011 5th International Power Engineering and Optimization Conference.

[33]  M. Steel,et al.  Benchmark Priors for Bayesian Model Averaging , 2001 .

[34]  Abbas Khosravi,et al.  Load Forecasting Accuracy through Combination of Trimmed Forecasts , 2012, ICONIP.

[35]  Wei-Chiang Hong,et al.  Chaotic particle swarm optimization algorithm in a support vector regression electric load forecasting model , 2009 .

[36]  Saeid Nahavandi,et al.  Combined Nonparametric Prediction Intervals for Wind Power Generation , 2013, IEEE Transactions on Sustainable Energy.