A New Combination Model for Offshore Wind Power Prediction Considering the Number of Climbing Features
摘要
The accurate identification of offshore wind power ramp events has great effects on wind power forecast. In order to improve the prediction accuracy of offshore wind power, this paper proposes an XGBoost-GRU combined forecasting model considering the number of climbing features. Firstly, the adaptive revolving door algorithm is used to identify the wind power climbing event, as well as data compression and feature extraction. Then, the XGBoost decision tree and gating loop unit are used to make preliminary power prediction. In case studies, the results are weighted and combined in detail. It is proved that the proposed model has a terrific performance on the offshore wind power prediction.