Large neural networks for electricity load forecasting: Are they overfitted?

Abstract Neural networks have apparently enjoyed considerable success in practice for predicting short-term daily electricity load profiles. Most of these applications have utilised very large neural network specifications, which raises the methodological question of over-fitting. This paper examines this issue by comparing several forecasting methods on a sample of hourly electricity demands, including both large neural networks and conventional regression-based methods. We find good performance for the large neural networks, and offer some analysis of why forecasting the 24 element vector of daily electricity demands may be particularly conducive to this approach.

[1]  C. Chatfield,et al.  Comparative Models for Electrical Load Forecasting. , 1986 .

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

[3]  Jae Hong Park,et al.  Composite modeling for adaptive short-term load forecasting , 1991 .

[4]  J. D. McDonald,et al.  A real-time implementation of short-term load forecasting for distribution power systems , 1994 .

[5]  David Infield,et al.  Optimal smoothing for trend removal in short term electricity demand forecasting , 1998 .

[6]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[7]  Terry R. Rakes,et al.  The effect of sample size and variability of data on the comparative performance of artificial neural networks and regression , 1998, Comput. Oper. Res..

[8]  Igor V. Tetko,et al.  Neural network studies, 1. Comparison of overfitting and overtraining , 1995, J. Chem. Inf. Comput. Sci..

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

[10]  C. Lee Giles,et al.  Overfitting and neural networks: conjugate gradient and backpropagation , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

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

[12]  O. Hyde,et al.  An adaptable automated procedure for short-term electricity load forecasting , 1997 .

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

[14]  Henrik Saxén,et al.  Nonlinear Time Series Analysis by Neural Networks: a Case Study , 1996, Int. J. Neural Syst..

[15]  D. P. Sen Gupta,et al.  Short-term load forecasting for demand side management , 1997 .

[16]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[17]  Fred Collopy,et al.  How effective are neural networks at forecasting and prediction? A review and evaluation , 1998 .

[18]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .