Knowledge-enhanced XGBoost for Wind Power Forecasting under Extreme Meteorological Events
Proceedings of the Bulgarian Academy of Sciences · 27.07.2026 · 79 (7)
DOI: 10.7546/crabs.2026.07.05 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Bulgarian Academy of Sciences, online erschienen am 27.07.2026. Verfasst von Jin Ma und 3 weiteren Autor:innen.
Abstract (Originalsprache)
To address deteriorated generalization of conventional data-driven wind power forecasting under extreme meteorological conditions, this study develops a knowledge-enhanced XGBoost prediction framework. Physical thresholds are used to divide meteorological and turbine control variables into state labels for wind speed, temperature, yaw angle, and pitch angle. The labels are compressed into two-dimensional numerical features and combined with sliding window temporal features for model training. Experiments based on the SDWPF dataset verify that embedded physical prior information mitigates out-of-distribution prediction drift. Compared with vanilla XGBoost, the proposed method reduces 1-hour MAE by 23.77% with statistical significance and achieves evident accuracy improvement across diverse extreme weather subsets.
Zitieren
APA
Ma, J., Xu, M., Du, W., & Qiao, Z. (2026). Knowledge-enhanced XGBoost for Wind Power Forecasting under Extreme Meteorological Events. Proceedings of the Bulgarian Academy of Sciences, 79(7). https://doi.org/10.7546/crabs.2026.07.05
Vancouver
Ma J, Xu M, Du W, Qiao Z. Knowledge-enhanced XGBoost for Wind Power Forecasting under Extreme Meteorological Events. Proceedings of the Bulgarian Academy of Sciences. 2026;79(7). doi:10.7546/crabs.2026.07.05
BibTeX
@article{Ma2026,
author = {Ma, Jin and Xu, Ming and Du, Wei and Qiao, Zhongzhi},
title = {Knowledge-enhanced XGBoost for Wind Power Forecasting under Extreme Meteorological Events},
journal = {Proceedings of the Bulgarian Academy of Sciences},
year = {2026},
volume = {79},
number = {7},
doi = {10.7546/crabs.2026.07.05}
}
EUVIMED