Short-term wind speed prediction based on LS-SVM

Accurate short-term wind speed prediction is very important to improve the security and stability of power grid. The method of least squares support vector machine (LS-SVM) for short-term wind speed prediction is proposed in this paper. In order to avoid inaccuracy of parameter selection and improve the accuracy of prediction, genetic algorithm is used to optimize the parameters of LS-SVM. It is proved that the method put forward in this paper can quickly and effectively realize short-term wind speed prediction by simulation example.