LAUSR

Abstract Aiming at the local wind speed prediction of each turbine in the wind farm, a wind speed prediction method based on feature analysis of wind speed behavior coupling the time characteristics and spatial feature is proposed, and a three-dimensional convolutional neural network (3D-CNN) multi-output wind speed prediction model with behavioral feature learning is established. Though the overall depth learning of the spatiotemporal behavior of wind speed with the temporal and spatial characteristics information being uncoupled, the function of future wind velocity and history spatiotemporal behavior features of each turbine location was established and furthermore, realized the multi-step wind speed prediction of each turbine location of the whole wind farm. The feasibilities and effectiveness of the proposed model are verified by the obtained SCADA (Supervisory Control and Data Acquisition) data from a wind farm in Hebei Province, China. When the prediction step size is 7 days, comparison results showed that the mean absolute error (MAE) and root mean squared error (RMSE) of the proposed model are 7.51 % and 0.70 %, respectively, which can conduct the wind speed prediction use spatiotemporal feature information effectively. Meanwhile, performances of the proposed model and previous existing prediction models were also compared with its superior been illuminated.