Research on New Energy Generation Power Prediction Method Based on Sequence Decomposition and Reconstruction

With the increasing proportion of wind power in the energy structure, accurate prediction of wind power is of great significance for grid scheduling and operation. In this paper, a wind power prediction model based on complementary ensemble empirical modal decomposition (CEEMD) and gated recurrent unit (GRU) is proposed. The model firstly utilizes CEEMD to decompose the wind power sequences to reduce the volatility of the sequences; then, the time features are extracted by GRU to predict each decomposed sequence; finally, the prediction results of the decomposed sequences are superimposed to obtain the final wind power prediction results. The experimental results show that the model, compared with the traditional single LSTM and GRU model, is reduced in each error index and shows higher prediction accuracy. This study verifies the superiority of the CEEMD-GRU model in dealing with temporal features and extracting hidden features in wind power data, providing a new and efficient method for wind power prediction.