An error-revision-based method for very short-term wind speed prediction using wavelet transform and support vector machine

With the rapid growth of wind power connected to the power system, the problems caused by the volatile nature of wind speed have drawn more and more attention from system operator and researchers. The effective wind speed and power prediction of is the key to solve all these problems. This paper proposed a method based on prediction error revision, which use wavelet transform and Grid Search optimized SMO-SVM during data processing. The simulation indicate that the proposed method performs better than the traditional forecasting model on one and three step ahead prediction.