论文信息 - Sequential GMDH approach to short term load forecasting

Sequential GMDH approach to short term load forecasting

Abstract This paper presents a methodology for forecasting the hourly load demand of the power provider enterprise using a sequential group method of data handing (SGMDH) approach. The SGMDH method not only simplifies the model of the forecasting systems and thus drastically reduces the computational efforts, but improves the forecasting accuracy by the nonlinear characteristics of higher-order polynomials. In this paper, the SGMDH approach is used to test on a practice power provider enterprise (Taiwan power network) 24-hour load forecasting model, to indicate its potential and practical values.

Chen-Sung Chang

[1] Nima Amjady,et al. Short-term hourly load forecasting using time-series modeling with peak load estimation capability , 2001 .

[2] Osama A. Mohammed,et al. Practical experiences with an adaptive neural network short-term load forecasting system , 1995 .

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

[4] A. G. Ivakhnenko,et al. Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[5] C.P. Lim,et al. Short Term Load Forecasting Using a Hybrid Neural Network , 2006, 2006 IEEE International Power and Energy Conference.

[6] G. Gross,et al. Short-term load forecasting , 1987, Proceedings of the IEEE.

[7] W. A. Pridmore,et al. Comparative Models for Electrical Load Forecasting , 1986 .

[8] W. R. Christiaanse. Short-Term Load Forecasting Using General Exponential Smoothing , 1971 .

[9] S. J. Kiartzis,et al. A neural network short term load forecasting model for the Greek power system , 1996 .

[10] G. Pask,et al. Heuristic Self-Organization in Problems of Engineering Cybernetics , 2003 .

[11] D. E. Brown,et al. A polynomial network for predicting temperature distributions , 1994, IEEE Trans. Neural Networks.