An improved WNN for day-ahead electricity price forecasting

Abstract

Price forecasting has become essential tool in deregulated electricity market. It is used by utility operators for bidding in the competitive market to increase their profits and services. The models for electricity price forecasting can be mainly categorized into (i) Statistical models, (ii) Artificial Intelligence models & (iii) Hybrid models. AI based models, i.e., ANN have gained popularity in the recent years due to their black box nature and non-linear mapping capability, it is generally trained using back propagation algorithm, which has got some serious limitations like large training time, local minima etc. In this work, comparison of various training algorithms for ANN has been presented for accurate electricity price forecasting problem, the results obtained are contrasted with the generic ANN model trained using back propagation (BP) algorithm and other popular training algorithm. It is found that the generic ANN with Levenberg-Marquardt (LM) training method provides better result as compared to other models.