Abstract
In order to improve the accuracy of short-term load forecasting, a hybrid forecasting model based on variational mode decomposition (VMD), fuzzy logic and gated recurrent unit (GRU) is proposed. Firstly, the original load sequence is decomposed into several modal components by VMD algorithm, then the decomposed modal components are combined with the fuzzy processed meteorological information, and then the combined data are inputted into the GRU model for prediction, and finally the prediction results of each modal component are superimposed to obtain the final load prediction results. Through simulation experiments and comparison with other models (SVR, LSTM, GRU, VMD-FGRU), the hybrid model proposed in this paper has better prediction accuracy.