Study of daily peak load forecasting by structured representation on genetic algorithms for function fitting

In recent years, electric power systems have become more and more complex and large-scale. Therefore, we thought that electric power demand forecasting is required. This paper presents a method of a daily peak load forecasting by STROGANOFF (structured representation on genetic algorithms for non-linear function fitting). The STROGANOFF is a hierarchical technique of multiple regression analysis method and GA-based search strategy. The proposed method is demonstrated by using the data of Chubu district in Japan.

[1]  Hiroyuki Mori,et al.  Short-term Load Forecasting with Fuzzy Optimal Regression Tree , 2001 .

[2]  K. Yukita,et al.  Study of daily peak load forecasting by structured representation on genetic algorithms for function fitting , 2004, 39th International Universities Power Engineering Conference, 2004. UPEC 2004..

[3]  Hiroyuki Mori,et al.  Optimal regression tree based rule discovery for short-term load forecasting , 2001, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[4]  Tatsuya Iizaka,et al.  Development of Electric Load Forecasting System using Neural Networks , 2000 .