Short-term wind speed prediction based on EEMD-LSTM

Abstract

Accurate wind speed prediction is of great significance for the smooth output of wind farms. To this end, this paper proposes a short-term wind speed prediction model based on the combination of ensemble empirical mode decomposition (EEMD) and long-term and short-term memory model (LSTM). Firstly, in order to reduce the nonlinearity and volatility of wind speed, the ensemble empirical mode decomposition technique is used to decompose the original wind speed time series into a plurality of different sub-sequences; then LSTM is used to predict each sub-sequence to obtain multiple prediction results. Finally, the prediction results of each LSTM model are superimposed to obtain the final wind speed prediction result of the combined model. The prediction model is verified by historical wind speed data of a wind farm in Hebei Province, and compared with ARIMA, GRNN and LSTM models. The simulation results show that the combined wind speed prediction model based on ensemble empirical mode decomposition and long-term and short-term memory model proposed in this paper has a higher prediction accuracy.