A Wind Speed Prediction Method Based on Improved Empirical Mode Decomposition and Support Vector Machine

Abstract

Abstract Based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and bat algorithm (BA) to optimize the support vector machine, this paper proposed a combined model for short-term wind speed forecasting to predict the wind speed more accurately. Firstly, CEEMDAN was used to decompose the original wind speed time series into a series of subsequences with different frequencies. Secondly, the decomposed subsequences were forecasted by combined model of BA-SVM. Finally, the wind speed forecasting results was achieved by superposing each predicted subsequence. The simulation results suggest that the model improves the prediction accuracy and reduces the error.