Neural Network Ensemble for 24-Hour Load Pattern Prediction in Power System

The paper is concerned with the problem of accurate prediction of the 24-hour ahead load pattern in the power system. We propose the solution relying on the application of many different neural predictors combined in an ensemble. Each neural network is responsible for the same job - predicting the 24-hour load pattern for the next day. The series containing 24 values of the load pattern forecasted by each predictor are combined together using principal component analysis, which extracts the most important information and reduces the size of vector used in the final stage of prediction. The final predictor has the form of another neural network. The developed system of prediction was tested on the real data of the Polish Power System. The results have been compared to the appropriate values generated by other methods.

[1]  Robert I. Egbert,et al.  Short term electric load forecasting via fuzzy neural collaboration , 2000 .

[2]  Krzysztof Siwek,et al.  Ensemble Neural Network Approach for Accurate Load Forecasting in a Power System , 2009, Int. J. Appl. Math. Comput. Sci..

[3]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[4]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[5]  Francisco Sandoval,et al.  From Natural to Artificial Neural Computation , 1995 .

[6]  Ioannis B. Theocharis,et al.  A load curve based fuzzy modeling technique for short-term load forecasting , 2003, Fuzzy Sets Syst..

[7]  Krzysztof Siwek,et al.  Two-Stage Neural Network Approach to Precise 24-Hour Load Pattern Prediction , 2009, HAIS.

[8]  Alireza Khotanzad,et al.  ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three , 1998 .

[9]  J.A.P. Lopes,et al.  Load forecasting performance enhancement when facing anomalous events , 2005, IEEE Transactions on Power Systems.

[10]  Wei-Chiang Hong,et al.  Hybrid evolutionary algorithms in a SVR-based electric load forecasting model , 2009 .

[11]  Hong-Tzer Yang,et al.  A new short-term load forecasting approach using self-organizing fuzzy ARMAX models , 1998 .

[12]  T. Yalcinoz,et al.  Short term and medium term power distribution load forecasting by neural networks , 2005 .

[13]  Tomonobu Senjyu,et al.  A neural network based several-hour-ahead electric load forecasting using similar days approach , 2006 .

[14]  Xiao-Jun Zeng,et al.  Short-Term and Midterm Load Forecasting Using a Bilevel Optimization Model , 2009, IEEE Transactions on Power Systems.

[15]  Michel Verleysen,et al.  Prediction of electric load using Kohonen maps - Application to the Polish electricity consumption , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[16]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[17]  Amaury Lendasse,et al.  Methodology for long-term prediction of time series , 2007, Neurocomputing.

[18]  P. Subbaraj,et al.  Evolutionary Techniques Based Combined Artificial Neural Networks for Peak Load Forecasting , 2008 .

[19]  Z.A. Bashir,et al.  Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks , 2009, IEEE Transactions on Power Systems.

[20]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[21]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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

[23]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[24]  E. Gonzalez-Romera,et al.  Monthly Electric Energy Demand Forecasting Based on Trend Extraction , 2006, IEEE Transactions on Power Systems.

[25]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[26]  Patrick Rousset,et al.  Daily Electrical Power Curves: Classification and Forecasting Using a Kohonen Map , 1995, IWANN.

[27]  Ming-Wei Chang,et al.  Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001 , 2004, IEEE Transactions on Power Systems.

[28]  G.T. Heydt,et al.  Estimation of unscheduled flows and contribution factors based on L/sub p/ norms , 2004, IEEE Transactions on Power Systems.

[29]  Krzysztof Siwek,et al.  Regularization of neural networks for improved load forecasting in power system , 2001, ICECS 2001. 8th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.01EX483).

[30]  Maarouf Saad,et al.  An efficient approach for short term load forecasting using artificial neural networks , 2006 .