Wind Power Forecasting Using Neural Network Ensembles With Feature Selection

摘要: In this paper, a novel ensemble method consisting of neural networks, wavelet transform, feature selection, and partial least-squares regression (PLSR) is proposed for the generation forecasting wind farm. Based on conditional mutual information, selection technique developed to choose compact set input features model. order overcome nonstationarity power series improve accuracy, new wavelet-based scheme integrated into The individual forecasters are featured with different mixtures mother number decomposition levels. outputs combined form forecast output using PLSR method. To confirm effectiveness, examined real-world datasets compared other methods.