Abstract:The paper proposes a power short-term load forecasting method using simulated annealing and least square support vector machine.Because its prediction accuracy is dependent on the choice of its parameters, and it is very difficult to select the appropriate parameter values,therefore parameter selection is a key issue in LSSVM. In order to improve the quality and efficiency of parameter selection, the paper used the SA algorithm to optimize the parameters of LSSVM. The proposed model is applied to the short-term electrical power load forecasting using power load and meteorological data of a city in China from 2010-1-1 to 2011-1-7.The experimental results show that the proposed method has higher prediction accuracy.