Short-term wind speed prediction based on combinatorial prediction model

Abstract

Improving the accuracy of wind speed forecast can increase wind power generation and better achieve wind energy grid connection. Therefore, a two-stage wind speed prediction model based on Ensemble Empirical Modal Decomposition (EEMD) and the combination prediction of Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), eXtreme Gradient Boosting (XGBOOST), Gate Recurrent Unit (GRU), Temporal Convolutional Network (TCN) is proposed. First, the original wind speed series is separated into Intrinsic Mode Functions (IMFs) using EEMD. Then, RNN, LSTM, XGBOOST, GRU, TCN multiple prediction models are established to learn features from each subsequence and superimpose the prediction results of subsequences. Finally, Particle Swarm Optimization (PSO) is applied to the results of multiple prediction models to assign weights, combined with weight superimposing sequences to achieve higher accuracy and more robust wind speed prediction. Simulation analysis using data from St. Thomas, Virgin Islands wind measurement station to validate the validity of the combined prediction model. The experimental simulation results show that the model proposed in this paper has a good result on increasing wind speed prediction accuracy.