Wind speed forecasting model based on wavelet decomposition and support vector machine
Hua Zhang, Yu Yongjing, Feng Zhijun, Sun Ke · Journal of Hydroelectric Engineering · 2012
A wind speed prediction model(WD-SVM) that uses data mining techniques of wavelet analysis and support vector machine,was developed.In this model,a given wind speed time series are decomposed by wavelet analysis into various layers that are predicted with support vector machines,and then by reconstructing the predicted values of each layer a prediction of wind speed is obtained.The model was applied to a wind farm for a forecast of its 10-minute average wind speed four hours in advance,i.e.,a forecast 24 steps ahead.By dividing one day into 21 intervals for such a prediction,an average root-mean-square error of 11.71% was resulted.The accuracy of WD-SVM model is much higher than that of support vector machine model(SVM).