A combination method for short term load forecasting used in Iran electricity market by NeuroFuzzy, Bayesian and finding similar days methods

Short term load forecasting (STLF) plays an important role for the power system operational planners and also most of the participants in the nowadays electricity markets. With the importance of the STLF in power system operation and electricity markets, many methods for arriving careful results, are represented. In this paper, a combination approach for STLF is proposed. The proposed approach is based on the weighted method for STLF results from Bayesian neural network, neurofuzzy and finding similar days methods. According to the obtained research, these 3 mentioned methods have the best results for the STLF of Iran national power system. Because Iran calendar is a combination of two solar and lunar calendars, so the special conditions, such as: solar and lunar holidays, days after or between holidays have the variable results with these 3 methods. For arriving STLF careful results, the least square method is used for combining these 3 methods. By using this technique, the effect of improper results is ignored. The results for Iran power system, shows that the idea can improve the performance of the STLF.

[1]  Ah Vahabie,et al.  A New Approach for Short Term Load Forecasting Based on Finding Similar Days , 2008 .

[2]  Dominic Maratukulam,et al.  ANNSTLF-a neural-network-based electric load forecasting system , 1997, IEEE Trans. Neural Networks.

[3]  Radford M. Neal.  Bayesian training of backpropagation networks by the hybrid Monte-Carlo method , 1992 .

[4]  S. Barghinia,et al.  Short-Term Load Forecasting for Special Days Using Bayesian Neural Networks , 2006, 2006 IEEE PES Power Systems Conference and Exposition.

[5]  S. Barghinia,et al.  Short term load forecasting of Iran national power system using artificial neural network , 2001, 2001 IEEE Porto Power Tech Proceedings (Cat. No.01EX502).

[6]  Babak Nadjar Araabi,et al.  Mutual Information Based Input Selection in Neuro-Fuzzy Modeling for Short Term Load Forecasting of Iran National Power System , 2007, 2007 IEEE International Conference on Control and Automation.

[7]  Shyh-Jier Huang,et al.  Short-term load forecasting via ARMA model identification including non-Gaussian process considerations , 2003 .

[8]  P. Ansarimehr,et al.  Short term load forecasting for Iran national power system using artificial neural network and fuzzy expert system , 2002, Proceedings. International Conference on Power System Technology.

[9]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[10]  Alireza Khotanzad,et al.  A Neuro-Fuzzy Approach to Short-Term Load Forecasting in a Price-Sensitive Environment , 2002, IEEE Power Engineering Review.

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