Support vector machines with PSO algorithm for short-term load forecasting

Accurate forecasting of short-term electricity load has been one of the most important issues in the electricity industry. Because of the remarkable nonlinear mapping capabilities of forecasting, artificial neural networks have played a crucial role in forecasting electricity load. Support vector machine (SVM) is a novel type of learning machine, which has been successfully employed to solve nonlinear regression and time series problems. This paper investigates the feasibility of using SVM to forecast electricity load. Moreover, the particle swarm optimization (PSO) algorithm is employed to determine the free parameters of SVM model automatically. Subsequently, examples of electricity load data from a practical power system were used to verify the proposed PSO-SVM model. The empirical results reveal that the proposed model outperforms the other two models. Consequently, the PSO-SVM model provides a promising alternative for forecasting electricity load.