Short-term wind power prediction based on genetic algorithm to optimize RBF neural network

Abstract

Wind power prediction technology is very important for scheduling of wind power farm. In order to improve the predictive accuracy of wind power, a short-term wind power prediction method based on genetic algorithm to optimize RBF neural network is proposed this paper. Genetic algorithm is used to optimize the weight, centers and widths of the hidden layer in RBF neural network. Relevant historical data is used to train the neural network on MATLAB platform. Simulation results show that the proposed method has higher prediction accuracy and less calculation time than RBF neural network. Therefore, the proposed method can be employed to predict short-term wind power.