Short-Term Wind Power Forecasting Using the Hybrid Method

An accurate forecasting method for power generation of wind energy conversion systems (WECS) is urgently required to address issues associated with the increased integration of wind power into the electricity system. This paper proposes a hybrid method that combines a radial basis function (RBF) neural network and enhanced particle swarm optimization (EPSO) algorithm for short-term wind power forecasting. With a RBF neural network structure, the EPSO algorithm is used to tune the parameters of the RBF neural network, including the centers and widths of the RBF and the connection weights. The trained RBF neural network is then used to forecast the power generation of a WECS. In order to demonstrate the effectiveness of the proposed hybrid forecasting method, the hybrid method is tested using historical power production data from WECS. The numerical results show that the proposed method outperforms the other methods.