Volatility, intermittence and randomness of wind power cause longer time and bigger error in wind power prediction, therefore, in order to improve prediction accuracy and shorten prediction time, this paper uses particle swarm optimization to optimize the parameters for least square support vector machine (LS-SVM) algorithm, then sets up the optimization prediction model to conduct simulation, and the results show that the optimized model has higher prediction accuracy than RBF and LS-SVM.