Artificial neural networks for short-term energy forecasting: Accuracy and economic value

Abstract Sixteen electric utilities surveyed state that use of ANNs significantly reduced errors in daily electric load forecasts, while only three found otherwise. Data for five gas utilities reinforces this result: the mean absolute percentage error (MAPE) for ANN daily gas demand forecasts was 6.4%, a 1.9% improvement over previous methods. Yet ANNs were not always best, implying opportunities for further improvement. The economic value of error reduction for electric utilities was assessed by examining operating decisions. For 19 utilities surveyed, an average of $800 000/year per utility is estimated to be saved from use of ANN-based forecasts. Most benefits resulted from improved generating unit scheduling; the utilities estimated such benefits to be up to $143 annually per peak MW of demand for each 1% improvement in MAPE. This estimated worth of accuracy improvement (roughly 0.1% of annual generation O&M costs) is confirmed by solving generation scheduling and dispatch models under various levels of forecast accuracy.

[1]  Michael T. Manry,et al.  Comparison of very short-term load forecasting techniques , 1996 .

[2]  R. Campo,et al.  Adaptive Weather-Sensitive Short-Term Load Forecast , 1987, IEEE Power Engineering Review.

[3]  G. Karady,et al.  Economic impact analysis of load forecasting , 1997 .

[4]  Ross Baldick,et al.  The generalized unit commitment problem , 1995 .

[5]  R. Ramanathan,et al.  Short-run forecasts of electricity loads and peaks , 1997 .

[6]  J. Rice.  Mathematical Statistics and Data Analysis , 1988 .

[7]  Ronald H. Brown,et al.  Development of artificial neural network models to predict daily gas consumption , 1995, Proceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics.

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

[9]  Rey-Chue Hwang,et al.  An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities , 1995 .

[10]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[11]  A. Comrie.  Comparing Neural Networks and Regression Models for Ozone Forecasting , 1997 .

[12]  T. Hesterberg,et al.  A regression-based approach to short-term system load forecasting , 1989, Conference Papers Power Industry Computer Application Conference.

[13]  B. Hobbs,et al.  Analysis of the value for unit commitment of improved load forecasts , 1999 .

[14]  Saifur Rahman,et al.  An expert system based algorithm for short term load forecast , 1988 .

[15]  Jonathan F. Bard,et al.  Short-Term Scheduling of Thermal-Electric Generators Using Lagrangian Relaxation , 1988, Oper. Res..

[16]  William Remus,et al.  Neural Network Models for Time Series Forecasts , 1996 .

[17]  Chuen-Sheng Cheng,et al.  Identification of seasonal short-term load forecasting models using statistical decision functions , 1990 .

[18]  Dejan J. Sobajic,et al.  Artificial Neural-Net Based Dynamic Security Assessment for Electric Power Systems , 1989, IEEE Power Engineering Review.

[19]  G. G. Karady,et al.  An adaptive neural network approach to one-week ahead load forecasting , 1993 .

[20]  Shangyou Hao,et al.  An implementation of a neural network based load forecasting model for the EMS , 1994 .