Chaotic characterization of electric load demand time series load forecasting by using GA trained artificial neural network

摘要

Non linear time series modeling and forecasting has fundamental importance to various practical domains and a lot of active research work is going on in this area during past several years. In this work, an artificial neural network based model is used for load forecasting. Further, its performance is improved by using a canonical genetic algorithm. The method is supported by giving the forecasting result via simulation for real non linear time series of the electric load demand of Delhi region. To evaluate forecasting accuracy as well as to compare different models, three performance measures, viz. RMSE (Root mean square Error), MAPE (Mean Absolute Percentage Error) and REP (Relative Error Percentage) have been used. In this paper, all the simulations are carried out in MATLAB 7.10.0 environment using core i5 Intel processor.