Improved Estimation of Electricity Demand Function by Integration of Fuzzy System and Data Mining Approach

This paper presents an integrated fuzzy system and data mining approach for estimation of electricity demand function in Iran. To construct fuzzy systems, a rule base is needed. Because a rule base is not available, for the case of demand function, look up table which is one of the extracting rule methods is used to extract the rule base. But the extraction by look up table in this case (demand function) operates poorly. Therefore, decision tree method which is a data mining approach is utilized to extract the rule base. It can be seen that this method provides better solution. The case study is based on the total electricity consumption in Iran from 1992 to 2004. The prescribed approach may be an ideal substitute for fuzzy regression. At last, relative results of the mentioned methods are compared with ARIMA (auto regressive integrated moving average) model, which is one of the most famous time series models.