EUVIMEDEUVIMED entdecken
Crossref

Multimodal Ensemble Photovoltaic Power Forecasting Incorporating Diffusion-Based Satellite Image Prediction

Kai Wang, Tao Wang, Shuo Shan, Weijing Dou, Jingxin Zhang, Haikun Wei, Kanjian Zhang

IEEE Transactions on Sustainable Energy · 2026-04 · 17 (2) · 1425-1436

DOI: 10.1109/tste.2025.3619938 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Sustainable Energy, 2026-04. Verfasst von Kai Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: State Grid Corporation Headquarters Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate ultra-short-term photovoltaic (PV) power forecasting is crucial for grid stability and energy management, but it is often challenged by the intermittent and unpredictable nature of cloud cover. Since satellite images provide large-scale cloud information, most studies incorporate them by predicting cloud evolution using deterministic models. However, these models often produce blurry forecasts, failing to capture rapid cloud changes and leading to unreliable power predictions. To address this limitation, CloudDiff, a novel diffusion-based satellite image prediction model, is proposed to generate ensemble satellite image forecasts, which could better account for PV power forecasting uncertainty caused by short-term cloud variations. Spatiotemporal cloud uncertainty is modeled recurrently by conditioning the diffusion process on encoded cloud motion features, while a neural stochastic differential equation captures temporal variability in cloud dynamics. These image forecasts, combined with historical PV power and numerical weather prediction data, are fed into a multimodal forecasting model to produce calibrated ensemble PV power forecasts. Extensive experiments across multiple sites and regions demonstrate that the proposed method outperforms existing approaches in probabilistic forecasting of both satellite imagery and PV power at a 180-minute horizon, exhibiting strong robustness under diverse cloud conditions.

Förderung

  • State Grid Corporation Headquarters Technology Project

Zitieren

APA

Wang, K., Wang, T., Shan, S., Dou, W., Zhang, J., Wei, H., & Zhang, K. (2026). Multimodal Ensemble Photovoltaic Power Forecasting Incorporating Diffusion-Based Satellite Image Prediction. IEEE Transactions on Sustainable Energy, 17(2), 1425-1436. https://doi.org/10.1109/tste.2025.3619938

Vancouver

Wang K, Wang T, Shan S, Dou W, Zhang J, Wei H, et al. Multimodal Ensemble Photovoltaic Power Forecasting Incorporating Diffusion-Based Satellite Image Prediction. IEEE Transactions on Sustainable Energy. 2026;17(2):1425-1436. doi:10.1109/tste.2025.3619938

BibTeX
@article{Wang2026,
  author = {Wang, Kai and Wang, Tao and Shan, Shuo and Dou, Weijing and Zhang, Jingxin and Wei, Haikun and Zhang, Kanjian},
  title = {Multimodal Ensemble Photovoltaic Power Forecasting Incorporating Diffusion-Based Satellite Image Prediction},
  journal = {IEEE Transactions on Sustainable Energy},
  year = {2026},
  volume = {17},
  number = {2},
  pages = {1425--1436},
  doi = {10.1109/tste.2025.3619938}
}
Kostenlos starten →