Enhanced XGBoost Model for Accurate Wind Power Forecast Considering Multiple Schedule Windows

Accurate wind power forecasts are crucial for the reliable operation of power systems. Data-driven methods have demonstrated significant effectiveness in this area. The extreme gradient boosting (XGBoost) model stands out as a powerful tool for prediction. This study utilizes SCADA data to implement an enhanced XGBoost model for predicting wind power generation. To improve the robustness of the prediction, we propose an improved empirical loss function within the model. Experimental results based on historical wind power data indicate that the proposed model outperforms other data-driven approaches, such as support vector regression (SVR) and kernel ridge regression (KRR), in wind power prediction.