Short-term wind power forecasting based on lifting wavelet transform and SVM

Short-term load forecasting is important for the safety and economic operation of the wind power system. In order to forecast the power load more accurately, the Support Vector Machines (SVM) combined with the lifting wavelet transform is proposed in this paper. The lifting wavelet transform is used to find out the characteristics of original signal while the SVM is utilized to improve the precision of forecasting. Finally, the data in September 2010 from a wind farm in North China are adopted. The result shows that wind power load forecasting based on method above is more effective than that of SVM only, thus proving the validity of the method above for power load forecasting.