A study of grey theory used in prediction of annual wind power generation

With the coming mature of the wind energy technology, wind energy has become one of the most promising renewable energy. In order to conduct post appraisals and operation management to a large wind farm, accurate prediction of the annual wind power generation is necessary. In this paper, grey model GM(1,1) for predicting annual wind power generation is set up. Moreover, in order to improve the prediction accuracy, a effective method of processing the original wind power data series is proposed. The prediction result with the original data series processed is compared to the unprocessed one. We obtain that the normalized average absolute error of the prediction result with the original data series processed is 7.0315%, improved 0.7679% relative to that original data series unprocessed.