Forecasting price has now become an essential task in the operation of electrical power system. Power producers and customers use short term price forecasts to manage and plan for bidding approaches, and hence increase the utilitys profit and energy efficiency. This paper proposes a novel method of Least Square Support Vector Machine (LSSVM) with Bacterial Foraging Optimization Algorithm (BFOA) to predict daily electricity prices in Ontario. The selection of input data and LSSVM's parameters held by BFOA are proven to improve accuracy as well as efficiency of prediction. A comparative study of the proposed method with previous researches was conducted in term of forecast accuracy. The results indicate that (1) the LSSVM with BFOA outperforms other methods for same test data; (2) the optimization algorithm of BFOA gives better accuracy than other optimization techniques. In fact, the proposed approach is less complex compared to other methods presented in this paper.
|Number of pages||8|
|Journal||ARPN Journal of Engineering and Applied Sciences|
|Publication status||Published - 20 Apr 2016|
All Science Journal Classification (ASJC) codes