EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSVMD-Informer: A Multi-Variate Multi-Scale Method to Wind Power Prediction

Zhijian Liu, Jikai Chen, Hang Dong, Zizhuo Wang

Energies · 21.03.2025 · 18 (7) · 1571

DOI: 10.3390/en18071571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 21.03.2025. Verfasst von Zhijian Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China key research and development program funding project, Key Basic Research Projects in Yunnan Province, Major Project of Basic Research Foundation of Yunnan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wind power prediction plays a crucial role in enhancing power grid stability and wind energy utilization efficiency. Existing prediction methods demonstrate insufficient integration of multi-variate features, such as wind speed, temperature, and humidity, along with inadequate extraction of correlations between variables. This paper proposes a novel multi-variate multi-scale wind power prediction method named multi-scale variational mode decomposition informer (MSVMD-Informer). First, a multi-scale modal decomposition module is designed to decompose univariate time-series features into multiple scales. Adaptive graph convolution is applied to extract correlations between scales, while self-attention mechanisms are utilized to capture temporal dependencies within the same scale. Subsequently, a multi-variate feature fusion module is proposed to better account for inter-variable correlations. Finally, the informer is reconstructed by integrating the aforementioned modules, enabling multi-variate multi-scale wind power forecasting. The proposed method was evaluated through comparative experiments and ablation studies against seven baselines using a public dataset and two private datasets. Experimental results demonstrate that our proposed method achieves optimal metric performance, with its lowest MAPE scores being 1.325%, 1.500% and 1.450%, respectively.

Förderung

  • China key research and development program funding project
  • Key Basic Research Projects in Yunnan Province
  • Major Project of Basic Research Foundation of Yunnan Province

Zitieren

APA

Liu, Z., Chen, J., Dong, H., & Wang, Z. (2025). MSVMD-Informer: A Multi-Variate Multi-Scale Method to Wind Power Prediction. Energies, 18(7), 1571. https://doi.org/10.3390/en18071571

Vancouver

Liu Z, Chen J, Dong H, Wang Z. MSVMD-Informer: A Multi-Variate Multi-Scale Method to Wind Power Prediction. Energies. 2025;18(7):1571. doi:10.3390/en18071571

BibTeX
@article{Liu2025,
  author = {Liu, Zhijian and Chen, Jikai and Dong, Hang and Wang, Zizhuo},
  title = {MSVMD-Informer: A Multi-Variate Multi-Scale Method to Wind Power Prediction},
  journal = {Energies},
  year = {2025},
  volume = {18},
  number = {7},
  pages = {1571},
  doi = {10.3390/en18071571}
}
Kostenlos starten →