Wind Power Prediction for Wind Farm Clusters Based on the Multi-feature Similarity Matching Method

Regional wind power forecasting is conducive to achieving scientific dispatch of the power system as well as improving its reliability. Data mining based on a large number of samples is an effective way to improve the accuracy of wind power forecasting. A new regional power forecasting method in the context of data mining is presented in this paper. First, a previously described regional wind power forecasting method, single feature similarity matching method, is analyzed and a new multi-feature similarity matching method is proposed. Second, the optimization and analysis processes of four key parameters in the multi-feature similarity matching method are proposed and the impact of each key parameter on prediction accuracy and the applicability of the method under different regional scales is analyzed. Finally, the new method and the optimization and analysis processes are verified by wind farm clusters, composed of 52 wind farms in a region of northeast China, and the new method is compared with the conventional statistical up-scaling method, additive method, and the single feature similarity matching method. The results show that the improved multi-feature similarity matching method is superior to the conventional prediction method, whereby the root mean square error of 0 to 2 h is reduced by 3.65% and the root mean square error of 0 to 4 h is reduced by 1.56%. The new method has been proved to be an effective power forecasting method for wind farm clusters and has potential industrial application prospects.