Wind speed prediction based on the Elman recursion neural networks

This paper introduces an efficient method for wind speed prediction, namely the Elman recursion neural network. The prediction model is proposed for one step ahead wind speed prediction based on the Elman recursion neural networks. The obtained results from the prediction model are shown when using different numbers of neurons to the different tested input data. The prediction model based on the Elman recursion neural networks is applied to a case study about a Chinese wind farm history data. Then, prediction error following Weibull distribution is confirmed compared with Gaussian distribution. The case shows that the prediction model is effective for one step ahead average ten-minute wind speed prediction.