Electricity price forecasting using generalized regression neural network based on principal components analysis

Abstract

A combined model based on principal components analysis (PCA) and generalized regression neural network (GRNN) was adopted to forecast electricity price in day-ahead electricity market. PCA was applied to mine the main influence on day-ahead price, avoiding the strong correlation between the input factors that might influence electricity price, such as the load of the forecasting hour, other history loads and prices, weather and temperature; then GRNN was employed to forecast electricity price according to the main information extracted by PCA. To prove the efficiency of the combined model, a case from PJM (Pennsylvania-New Jersey-Maryland) day-ahead electricity market was evaluated. Compared to back-propagation (BP) neural network and standard GRNN, the combined method reduces the mean absolute percentage error about 3%.

Keywords

electricity price forecasting / generalized regression neural network / principal components analysis

References

[1] LiX., YangS.-d., QiJ.-x.. A new support vector machine optimized by improved particle swarm optimization and its application [J]. Journal of Central South University of Technology, 2006, 13(5): 568-572

[2] AmjadyN.. Day-ahead price forecasting of electricity markets by a new fuzzy neural network [J]. IEEE Transactions on Power Systems, 2006, 21(2): 887-896

[3] GuoJ. J., LuhP. B.. Selecting input factors for clusters of Gaussian radial basis function networks to improve market clearing price prediction [J]. IEEE Transactions on Power Systems, 2003, 18(3): 665-672

[4] HongY.-y., LeeC.-fang.. A neuro-fuzzy price forecasting approach in deregulated electricity markets [J]. Electric Power Systems Research, 2005, 73(2): 151-157

[5] PaoH. T.. Forecasting electricity market pricing using artificial neural networks [J]. Energy Conversion and Management, 2007, 48(3): 907-912

[6] GaretaR., RomeoL. M., GilA.. Forecasting of electricity prices with neural networks [J]. Energy Conversion and Management, 2006, 47(13/14): 1770-1778

[7] ZhangL., LuhP. B.. Neural Network-based market clearing price prediction and confidence interval estimation with an improved extended Kalman Filter method [J]. IEEE Transactions on Power Systems, 2005, 20(1): 59-66

[8] SpechtD. F.. A general regression neural network [J]. IEEE Transactions on Neural Network, 1991, 6(2): 568-576

[9] RutkowskiL.. Generalized regression neural network in time-varying environment [J]. IEEE Transactions on Neural Network, 2004, 15(3): 576-596

[10] LiZ.-w., SunJ.-z., ZhangZ.-qiang.. Reconstruction of novel viewpoint image using GRNN [J]. Transactions of Tianjin University, 2003, 9(2): 136-139

[11] ZhaoJ.-h., GeS.-y., LiuZ.-fa.. Application of radical basis function network based on principal component analysis in load forecasting [J]. Power System Technology, 2004, 28(5): 35-40

[12] JOBSON J D. Applied multivariate data analysis [M]. Springer, 1992.

[13] Matlab Company. Available on line: www.mathworks.com