EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

State-aware adaptive multimodal fusion for ultra-short-term solar irradiance forecasting using sky cloud images

Houhang Zhao, Aiyi Song, Yu Jin iD, Haoxiang Yu

PLOS One · 03.11.2026 · 21 (11) · e0362193

DOI: 10.1371/journal.pone.0362193 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 03.11.2026. Verfasst von Houhang Zhao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Statistics, Dongbei University of Finance and Economics, Dalian, China. Hauptthemen laut MEDLINE: Solar Energy, Sunlight, Cloud Computing. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Program of National Fund of Philosophy and Social Science of China, Natural Science Foundation of Liaoning Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As renewable energy penetration continues to increase, accurate ultra-short-term solar irradiance forecasting is essential for improving energy utilization and supporting power system operation. However, irradiance variations are jointly influenced by historical trends and rapid cloud changes, making traditional single-modal methods insufficient for capturing complex dynamics under varying weather conditions. This paper proposes a multimodal solar irradiance forecasting framework based on the collaborative representation of sky cloud images and numerical sequences. The framework introduces a heterogeneous modal state encoding mechanism and a state-aware adaptive selective attention fusion mechanism to enhance interactions between visual weather information and historical physical patterns. Specifically, the numerical modality captures irradiance trends and temporal correlations through dependency modeling, while the image modality extracts cloud structures and evolution features through spatiotemporal representation. The proposed fusion mechanism dynamically adjusts modality contributions according to forecasting conditions, enabling effective integration of complementary information. Experimental results demonstrate that the proposed framework outperforms benchmark models in forecasting accuracy and robustness, validating the effectiveness of combining visual cloud information with numerical evolution patterns for ultra-short-term solar irradiance forecasting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Solar EnergySunlightCloud ComputingForecastingWeatherModels, Theoretical

Autor:innen und Institutionen

  • School of Statistics, Dongbei University of Finance and Economics, Dalian, China.
  • School of Health and Medical Technology, Dalian Neusoft University of Information, Dalian, China.
  • Academy for Educational Development and Innovation, The Education University of Hong Kong, Hong Kong, China.

ORCID-Profile: Yu Jin

Förderung

  • Major Program of National Fund of Philosophy and Social Science of China
  • Natural Science Foundation of Liaoning Province

Zitieren

APA

Zhao, H., Song, A., Jin, Y., & Yu, H. (2026). State-aware adaptive multimodal fusion for ultra-short-term solar irradiance forecasting using sky cloud images. PLOS One, 21(11), e0362193. https://doi.org/10.1371/journal.pone.0362193

Vancouver

Zhao H, Song A, Jin Y, Yu H. State-aware adaptive multimodal fusion for ultra-short-term solar irradiance forecasting using sky cloud images. PLOS One. 2026;21(11):e0362193. doi:10.1371/journal.pone.0362193

BibTeX
@article{Zhao2026,
  author = {Zhao, Houhang and Song, Aiyi and Jin, Yu and Yu, Haoxiang},
  title = {State-aware adaptive multimodal fusion for ultra-short-term solar irradiance forecasting using sky cloud images},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0362193},
  doi = {10.1371/journal.pone.0362193}
}
Kostenlos starten →