Short-Term Wind Power Prediction for Wind Farm Clusters Based on SFFS Feature Selection and BLSTM Deep Learning

Wind power prediction (WPP) of wind farm clusters is important to the safe operation and economic dispatch system, but it faces two challenges: (1) The dimensions input parameters for WPP are very high so that contain irrelevant or redundant features; (2) difficult build a holistic model with high-dimensional clusters. To overcome these challenges, novel short-term clusters, based on sequential floating forward selection (SFFS) feature bidirectional long memory (BLSTM) deep learning, proposed in this paper. First, more than 300,000 features cluster constructed. Second, SFFS method applied sort analyze rule forecasting accuracy changes number obtain optimal sets. Finally, results selection, BLSTM combination learning. This case study shows an effective selecting core clusters; not only higher backpropagation neural network also outstanding performance terms reducing phase errors WPP.