Multi-step ahead forecasts for electricity prices using NARX: A new approach, a critical analysis of one-step ahead forecasts

Abstract The prediction of electricity prices is very important to participants of deregulated markets. Among many properties, a successful prediction tool should be able to capture long-term dependencies in market’s historical data. A nonlinear autoregressive model with exogenous inputs (NARX) has proven to enjoy a superior performance to capture such dependencies than other learning machines. However, it is not examined for electricity price forecasting so far. In this paper, we have employed a NARX network for forecasting electricity prices. Our prediction model is then compared with two currently used methods, namely the multivariate adaptive regression splines (MARS) and wavelet neural network. All the models are built on the reconstructed state space of market’s historical data, which either improves the results or decreases the complexity of learning algorithms. Here, we also criticize the one-step ahead forecasts for electricity price that may suffer a one-term delay and we explain why the mean square error criterion does not guarantee a functional prediction result in this case. To tackle the problem, we pursue multi-step ahead predictions. Results for the Ontario electricity market are presented.

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

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

[3]  Bernard Delyon,et al.  Wavelets in identification , 1994, Fuzzy logic and expert systems applications.

[4]  Hsiao-Tien Pao,et al.  Forecasting electricity market pricing using artificial neural networks , 2007 .

[5]  K. Bhattacharya,et al.  Forecasting the hourly Ontario energy price by multivariate adaptive regression splines , 2006, 2006 IEEE Power Engineering Society General Meeting.

[6]  Ajith Abraham,et al.  Is Neural Network a Reliable Forecaster on Earth? A MARS Query! , 2001, IWANN.

[7]  J. Contreras,et al.  ARIMA models to predict next-day electricity prices , 2002 .

[8]  A. Fraser.  Reconstructing attractors from scalar time series: A comparison of singular system and redundancy criteria , 1989 .

[9]  T. Dillon,et al.  Electricity price short-term forecasting using artificial neural networks , 1999 .

[10]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[11]  Edwin J C G van den Oord,et al.  Multivariate adaptive regression splines: a powerful method for detecting disease–risk relationship differences among subgroups , 2006, Statistics in medicine.

[12]  Hongming Yang,et al.  Chaotic characteristics of electricity price and its forecasting model , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[13]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[14]  Takahide Niimura,et al.  Deregulated electricity market data representation by fuzzy regression models , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[15]  Qinghua Zhang,et al.  Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[16]  J. Contreras,et al.  Forecasting next-day electricity prices by time series models , 2002 .

[17]  G. Bierman.  Factorization methods for discrete sequential estimation , 1977 .

[18]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[19]  H. Abarbanel,et al.  Determining embedding dimension for phase-space reconstruction using a geometrical construction. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[20]  Michael C. Mozer,et al.  Induction of Multiscale Temporal Structure , 1991, NIPS.

[21]  Jerome H. Friedman.  Multivariate adaptive regression splines (with discussion) , 1991 .

[22]  Marco van Akkeren,et al.  A GARCH forecasting model to predict day-ahead electricity prices , 2005, IEEE Transactions on Power Systems.

[23]  J. Contreras,et al.  Forecasting electricity prices for a day-ahead pool-based electric energy market , 2005 .

[24]  P. Luh,et al.  Improving market clearing price prediction by using a committee machine of neural networks , 2004, IEEE Transactions on Power Systems.

[25]  Ajith Abraham,et al.  MARS: Still an Alien Planet in Soft Computing? , 2001, International Conference on Computational Science.

[26]  T. Senjyu,et al.  Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market , 2006 .

[27]  A.M. Gonzalez,et al.  Modeling and forecasting electricity prices with input/output hidden Markov models , 2005, IEEE Transactions on Power Systems.

[28]  Ali Azadeh,et al.  Forecasting electrical consumption by integration of Neural Network, time series and ANOVA , 2007, Appl. Math. Comput..

[29]  J. R. Trapero,et al.  Electricity prices forecasting by automatic dynamic harmonic regression models , 2007 .

[30]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[31]  Lefteri H. Tsoukalas,et al.  Journal of Intelligent and Robotic Systems 31: 149--157, 2001. , 2022 .

[32]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[33]  T. Funabashi,et al.  Neural network models to predict short-term electricity prices and loads , 2005, 2005 IEEE International Conference on Industrial Technology.

[34]  H. Akaike.  Statistical predictor identification , 1970 .

[35]  Hong-Tzer Yang,et al.  Evolving wavelet-based networks for short-term load forecasting , 2001 .

[36]  C. Rodriguez,et al.  Energy price forecasting in the Ontario competitive power system market , 2004, IEEE Transactions on Power Systems.

[37]  A.J. Conejo,et al.  Day-ahead electricity price forecasting using the wavelet transform and ARIMA models , 2005, IEEE Transactions on Power Systems.

[38]  Floris Takens,et al.  On the numerical determination of the dimension of an attractor , 1985 .

[39]  P.B. Luh,et al.  Neural network-based market clearing price prediction and confidence interval estimation with an improved extended Kalman filter method , 2005, IEEE Transactions on Power Systems.

[40]  V. Mendes,et al.  Short-term electricity prices forecasting in a competitive market: A neural network approach , 2007 .

[41]  Lee A. Feldkamp,et al.  Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.