Short-Term Wind Power Load Forecasting Based on VMD-SVM
GBP Proceedings Series · 16.05.2026 · 28 · 63-72
DOI: 10.70088/yvm55r92 ↗Kurz gefasst
Fachartikel in der Zeitschrift GBP Proceedings Series, online erschienen am 16.05.2026. Verfasst von Jieya Zhang.
Abstract (Originalsprache)
With the continuous global expansion of renewable wind power capacity, the accurate short-term forecasting of wind power load plays an increasingly crucial role in ensuring efficient power system dispatching, grid stability, and overall operational safety. However, due to the inherent non-stationarity, multi-scale fluctuations, and severe noise interference commonly found in real-world load time series data, traditional forecasting methods frequently fall short in terms of both predictive accuracy and systemic robustness. To effectively address this critical issue, this paper proposes a novel short-term forecasting approach based on the synergistic integration of Variational Mode Decomposition (VMD) and Support Vector Machine (SVM) algorithms. The proposed method first employs the VMD technique to systematically decompose the original complex load time series, successfully extracting essential underlying features across different frequency bands. Subsequently, dedicated SVM regression models are established for each independently decomposed mode to generate precise localized predictions. The final comprehensive load values are then obtained by carefully reconstructing the predicted modal components. Extensive experimental results based on the 2026 Kaggle Hourly Energy Consumption dataset indicate that the proposed VMD-SVM model achieves a Mean Absolute Error (MAE) of 101.43, a Root Mean Square Error (RMSE) of 126.26, and an impressive R2 of 0.9961 on the testing set. These metrics demonstrate that the hybrid approach significantly outperforms standalone SVM, Random Forest, and XGBoost models. Ultimately, this study proves that the proposed methodology substantially enhances model robustness against non-stationary load fluctuations, providing highly reliable technical support for practical operational applications in modern wind farms.
Zitieren
APA
Zhang, J. (2026). Short-Term Wind Power Load Forecasting Based on VMD-SVM. GBP Proceedings Series, 28, 63-72. https://doi.org/10.70088/yvm55r92
Vancouver
Zhang J. Short-Term Wind Power Load Forecasting Based on VMD-SVM. GBP Proceedings Series. 2026;28:63-72. doi:10.70088/yvm55r92
BibTeX
@article{Zhang2026,
author = {Zhang, Jieya},
title = {Short-Term Wind Power Load Forecasting Based on VMD-SVM},
journal = {GBP Proceedings Series},
year = {2026},
volume = {28},
pages = {63--72},
doi = {10.70088/yvm55r92}
}
EUVIMED