JOURNAL ARTICLE

Enhanced photovoltaic power prediction for dust weather: Integrating satellite cloud imagery, PM10 concentration, and numerical weather prediction.

  • Published In: Journal of Renewable & Sustainable Energy, 2025, v. 17, n. 2. P. 1 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Jiao, Meining; Song, Weiye; Han, Shuang; Liu, Yongqian; Yan, Jie; Ge, Chang 3 of 3

Abstract

This article focuses on improving photovoltaic (PV) power output prediction under dust storm conditions in northwestern China by integrating satellite cloud imagery and PM10 concentration data. It proposes a two-stage deep learning framework: a CNN-GRU model predicts PM10 concentrations using upstream air quality and satellite data, and a CNN-Attention-GRU model forecasts PV power output by combining PM10 predictions with numerical weather prediction (NWP) data. Case studies using data from a 300 MW PV power station demonstrate that this approach achieves higher accuracy than traditional models, reducing prediction errors by up to 4.95% in dusty weather. The study highlights the critical role of PM10 concentration information in enhancing PV power forecasting accuracy during dust storms, offering a valuable tool for grid management in dust-prone regions.

Additional Information

  • Source:Journal of Renewable & Sustainable Energy. 2025/03, Vol. 17, Issue 2, p1
  • Document Type:Article
  • Subject Area:Earth and Atmospheric Sciences
  • Publication Date:2025
  • ISSN:1941-7012
  • DOI:10.1063/5.0249579
  • Accession Number:184884749
  • Copyright Statement:Copyright of Journal of Renewable & Sustainable Energy is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.