SHORT-TERM WIND SPEED PREDICTION BY COMBINING TWO-STEP DECOMPOSITION AND ARIMA-LSTM
To improve the accuracy of wind speed series prediction,a combined short-term wind speed prediction model based on two-step decomposition is proposed.The wind speed data are first decomposed into subseries of different frequencies using robust empirical modal decomposition(REMD),and then the high-frequency modal components obtain from REMD decomposition are decomposed in a second step using wavelet packet decomposition(WPD)to reduce the wind speed series instability and improve its predictability.Next,a long short-term memory neural network(LSTM)prediction model is built for the decomposed high-frequency subsequences,and a differential autoregressive moving average model(ARIMA)prediction model is built for the low-frequency subsequences.Finally,the wind speed prediction results are obtained by superimposing the subseries prediction results.The performance of the model is scientifically evaluated through experiments with two different wind speed datasets,and the mean absolute errors of the model predictions are 0.3026 and 0.1255.The root mean square errors are 0.498 and 0.1607,respectively.Compared with other comparative prediction models,it is proved that this model has certain advantages.
NETL
NSTL
万方数据
维普
