In this paper, a new ARMAX model based on evolutionary algorithm and particle swarm optimization for short-term load forecasting is proposed. Auto-regressive (AR) and moving average (MA) with exogenous variables (ARMAX) has been widely applied in the load forecasting area. Because of the nonlinear characteristics of the power system loads, the forecasting function has many local optimal points. The traditional method based on gradient searching may be trapped in local optimal points and lead to high error. While, the hybrid method based on evolutionary algorithm and particle swarm optimization can solve this problem more efficiently than the traditional ways. It takes advantage of evolutionary strategy to speed up the convergence of particle swarm optimization (PSO), and applies the crossover operation of genetic algorithm to enhance the global search ability. The new ARMAX model for short-term load forecasting has been tested based on the load data of Eastern China location market, and the results indicate that the proposed approach has achieved good accuracy.

Owing to the inherent nonlinear characteristics of the power system loads,solutions of the gradient search based technique may stall at the local optimal points,which lead to high forecasting error.A hybrid method based on evolutionary algorithm and particle swarm optimization(HPSO) to identify the auto-regressive and moving average with exogenous variables(ARMAX) is proposed.HPSO introduces evolutionary algorithm into particle swarm optimization(PSO),thus can get higher precision and faster convergence speed without changing the structure of PSO. The proposed method has been tested on the Shanghai power system,and the results show that the proposed approach can achieve great accuracy.

To correct the relatively big errors caused by climatic factors,human being intervention is often needed in the short-term load forecasting to improve forecasting results.By analyzing the co-relationships between climatic factors and electric loads,an experience based model correction method is proposed.Correction models and software corresponding to the humidity,rainfall,temperature,and air pressure conditions respectively are developed.Test results show that the proposed model has a high level precision due to the consideration of climate factors.