Short-term Wind Speed Forecasting by Combination of Empirical Mode Decomposition and Extreme Learning Machine

According to the demand of accurate prediction of the short-term wind speed sequence, this paper proposes the short-term combination forecasting model of wind speed sequence by means of empirical mode decomposition (EMD) and extreme learning machine (ELM). First of all, because of the non-stationary characteristics of the wind speed sequence, the wind speed sequence is decomposed into several components with different frequency bands by the EMD to reduce the non-stationary characteristics. Secondly, to avert the randomness of input dimensionality selection of the extreme learning machine, the author reconstructs the phase space of each component. Thirdly, the ELM model of each component is established to predict the wind speed sequence. Finally, the predicted results of each component are superimposed to get the final result. The simulation result shows that the combination forecasting method presented in this paper has high prediction accuracy.