A Self-Supervised Pre-Learning Method for Low Wind Power Forecasting
IEEE Transactions on Sustainable Energy · 2025-07 · 16 (3) · 1723-1736
DOI: 10.1109/tste.2025.3529199 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Sustainable Energy, 2025-07. Verfasst von Weiye Song und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Key R&D Program of China, State Grid Corporation of China Science and Technology Project, Multi-timescale Forecast Technology for Large-scale Wind/Photovoltaic Power Supply Capability.
Abstract (Originalsprache)
As wind power is becoming a major energy source of power systems, the risk of power shortages due to its intermittent low power output is growing. Accurate forecasting of low wind power is crucial for mitigating these impacts. However, conventional methods struggle with few-sample issues due to the infrequent occurrence of low wind power, limiting accuracy improvements. To address this, a self-supervised pre-learning method is proposed to forecast low wind power occurrence period and output, leveraging the similarities and differences among low output samples to enhance forecasting accuracy. Low wind power output is decomposed into low wind power events (LWPE), which represent the occurrence timeframe, and low wind power processes (LWPP), which represent the power sequences. For LWPE forecasting, a siamese residual shrinkage network based on contrastive learning is introduced. This network pre-learns LWPE features from sample pairs to mitigate the impact of imbalanced sample distribution. For LWPP forecasting, a pattern recognition-based embedded forecasting framework is proposed, embedding typical LWPP fluctuations into the prediction network to improve fit under limited sample conditions. A case study on 3 wind farm clusters shows that this method improves LWPP forecasting accuracy from 84.99%-86.6% to 89.97%, outperforming traditional methods without pre-learning.
Förderung
- National Key R&D Program of China
- State Grid Corporation of China Science and Technology Project
- Multi-timescale Forecast Technology for Large-scale Wind/Photovoltaic Power Supply Capability
Zitieren
APA
Song, W., Yan, J., Han, S., Zhang, N., Liu, S., Ge, C., & Liu, Y. (2025). A Self-Supervised Pre-Learning Method for Low Wind Power Forecasting. IEEE Transactions on Sustainable Energy, 16(3), 1723-1736. https://doi.org/10.1109/tste.2025.3529199
Vancouver
Song W, Yan J, Han S, Zhang N, Liu S, Ge C, et al. A Self-Supervised Pre-Learning Method for Low Wind Power Forecasting. IEEE Transactions on Sustainable Energy. 2025;16(3):1723-1736. doi:10.1109/tste.2025.3529199
BibTeX
@article{Song2025,
author = {Song, Weiye and Yan, Jie and Han, Shuang and Zhang, Ning and Liu, Shihua and Ge, Chang and Liu, Yongqian},
title = {A Self-Supervised Pre-Learning Method for Low Wind Power Forecasting},
journal = {IEEE Transactions on Sustainable Energy},
year = {2025},
volume = {16},
number = {3},
pages = {1723--1736},
doi = {10.1109/tste.2025.3529199}
}
EUVIMED