Effective Wind Speed Forecasting in Annual Prediction of Output Power for Wind Farm

Wind power forecasting is very important to the utilization of wind energy. In order to forecast the yearly wind speed of the next year, the data of average wind speed per hour of the history is to be used in this paper. The wind speed can be decomposed into several different frequency bands based on wavelet decomposition, different recursive least square (RLS) models to forecast each band were built up, these forecasting results of high frequency bands and low frequency bands were combined to obtain the final forecasting results. The simulation experiment shows the average value of the mean absolute percentage error (MAPE) is 12.25% about wind speed forecasting and the prediction accuracy is improved considerably. Considering power characteristic of wind power generator, unit efficiency, operating conditions, the output power of the next year in wind farm can be obtained.