A Weighted Evolving Fuzzy Neural Network for Electricity Demand Forecasting

This research develops a weighted evolving fuzzy neural network for electricity demand forecasting in Taiwan. This study modifies the evolving fuzzy neural network framework (EFuNN framework) and adopts a weighted factor to calculate the importance of each factor among these different rules. In addition, an exponential transfer function (exp(-D)) is employed to transfer the distance of any two factors into the value of similarity among different rules, thus a different rule clustering method is developed accordingly. Seven explanatory factors identified by the Taiwan Power Company will affect the power consumption in Taiwan and these seven factors will be inputted into the WEFuNN to forecast the electricity demand in the future. The historical data will be applied to train the WEFuNN and then forecasts the future electricity demands. Finally, the model is compared with other approaches proposed in the literature. The experimental results reveal that the MAPE for WEFuNN model is 6.11% which outperforms the others. In summary, the WEFuNN model can be applied practically as an electricity demand forecasted tool in Taiwan.