A Short-Term Wind Power Forecast Method via XGBoost Hyper-Parameters Optimization

The improvement of wind power prediction accuracy is beneficial to the effective utilization energy. An improved XGBoost algorithm via Bayesian hyperparameter optimization (BH-XGBoost method) was proposed in this article, which employed forecast short-term for farms. Compared XGBoost, SVM, KELM, and LSTM, results indicate that BH-XGBoost outperforms other methods all cases. method could yield a more minor estimated error than methods, especially cases ramp events caused by extreme weather conditions low speed range. comparison led recommendation an