Evolutionary quantile regression gated recurrent unit network based on variational mode decomposition, improved whale optimization algorithm for probabilistic short-term wind speed prediction

Abstract

Wind energy, as clean energy, has attracted more and more attention. Wind power generation is easily threatened by the irregular fluctuation of wind speed, which interferes with the safety and stability of power system. In this study, a wind speed interval prediction method based on variational mode decomposition (VMD), phase space reconstruction (PSR), whale optimization algorithm (WOA), quantile regression (QR) and gated recurrent unit (GRU) is proposed. Firstly, the wind speed time series is decomposed into a variety of intrinsic mode functions (IMFs) through VMD to reduce the stochasticity. Secondly, all IMFs are then reconstructed using PSR to get the optimal input variables of the model. Then, the QRGRU model is optimized by the improved WOA to get the optimal QRGRU model parameters. Then, the wind speed interval prediction model of PSR-IWOA-QRGRU is established for each intrinsic mode function. Finally, the prediction results of each component are superimposed to realize the wind speed interval prediction. By checking on three different data sets, the effectiveness of the proposed method in wind speed interval prediction is proved.