Neural Network Models for Electricity Market Forecasting

For increasingly deregulated electricity market, accurate forecasting of electricity demand and spot price has become crucial for the independent system operators, generators and consumers. However, the exclusive features of electricity present a number of challenges for this task. This paper describes the author’s continual effort in power system forecasting studies. By using various new techniques, such as wavelet, neural network and support vector machine, different models for electricity load and price forecast have been developed, which are able to forecast at one or more time steps ahead. Case studies, using actual data from Australian National Electricity Market, have been carried out and the results are presented. In addition, comparisons with other forecasting models have shown that the proposed new methods can provide more stable and reliable performance even under the chaotic market conditions.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..

[3]  T. Niimura,et al.  A day-ahead electricity price prediction based on a fuzzy-neuro autoregressive model in a deregulated electricity market , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[4]  M. A. Wincek.  Forecasting With Dynamic Regression Models , 1993 .

[5]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[6]  Amir B. Geva,et al.  ScaleNet-multiscale neural-network architecture for time series prediction , 1998, IEEE Trans. Neural Networks.

[7]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[8]  Pravin Varaiya,et al.  Coordinated multilateral trades for electric power networks: theory and implementation , 1999 .

[9]  F. Wolak.  Market Design and Price Behavior in Restructured Electricity Markets: An International Comparison , 2000 .

[10]  Z. Dong,et al.  A multi-resolution neural network model for electricity market place forecasting , 2002 .

[11]  E. Michael Azoff,et al.  Neural Network Time Series: Forecasting of Financial Markets , 1994 .

[12]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[13]  Ronald R. Coifman,et al.  Entropy-based algorithms for best basis selection , 1992, IEEE Trans. Inf. Theory.