Short-Term Prediction of Wind Power Considering the Fusion of Multiple Spatial and Temporal Correlation Features

Abstract

As the wind power penetration increases, the short-term prediction accuracy of wind power is of great importance for the safe and cost-effective operation of the power grid in which the wind power is integrated. Traditional wind farm power prediction uses numerical weather prediction (NWP) information as an important input but does not consider the correlation characteristics of NWP information from different wind farms. In this study, a convolutional neural network–long short-term memory based short-term prediction model for wind farm clusters is proposed. Additionally, a feature map is established for multiposition NWP information, the spatial correlation of NWP information from different wind farms is fully explored, and the feature map is trained using the spatiotemporal model to obtain the short-term prediction results of wind farm clusters. Finally, as a case study, the operational data of a wind farm cluster in China are analyzed, and the proposed model outperforms traditional short-term prediction methods in terms of prediction accuracy.