Skip to main content

Research Repository

Advanced Search

Advanced multimodal fusion method for very short-term solar irradiance forecasting using sky images and meteorological data: A gate and transformer mechanism approach

Zhang, Liwenbo; Wilson, Robin; Sumner, Mark; Wu, Yupeng

Advanced multimodal fusion method for very short-term solar irradiance forecasting using sky images and meteorological data: A gate and transformer mechanism approach Thumbnail


Authors

MARK SUMNER MARK.SUMNER@NOTTINGHAM.AC.UK
Professor of Electrical Energy Systems

YUPENG WU yupeng.wu@nottingham.ac.uk
Professor of Building Physics



Abstract

Cloud dynamics are the main factor influencing the intermittent variability of short-term solar irradiance, and therefore affect the solar farm output. Sky images have been widely used for short-term solar irradiance prediction with encouraging results due to the spatial information they contain. At present, there is little discussion on the most promising deep learning methods to integrate images with quantitative measures of solar irradiation. To address this gap, we optimise the current mainstream framework using gate architecture and propose a new transformer-based framework in an attempt to achieve better prediction results. It was found that compared to the classical CNN model based on late feature-level fusion, the transformer framework model based on early feature-level prediction improves the balanced accuracy of ramp events by 9.43% and 3.91% on the 2-min and 6-min scales, respectively. However, based on the results, it can be concluded that for the single picture-digital bimodal model, the spatial information validity of a single picture is difficult to achieve beyond 10 min. This work has the potential to contribute to the interpretability and iterability of deep learning models based on sky images.

Citation

Zhang, L., Wilson, R., Sumner, M., & Wu, Y. (2023). Advanced multimodal fusion method for very short-term solar irradiance forecasting using sky images and meteorological data: A gate and transformer mechanism approach. Renewable Energy, 216, Article 118952. https://doi.org/10.1016/j.renene.2023.118952

Journal Article Type Article
Acceptance Date Jun 22, 2023
Online Publication Date Jun 28, 2023
Publication Date 2023-11
Deposit Date Jun 29, 2023
Publicly Available Date Jun 29, 2023
Journal Renewable Energy
Print ISSN 0960-1481
Electronic ISSN 1879-0682
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 216
Article Number 118952
DOI https://doi.org/10.1016/j.renene.2023.118952
Keywords Solar energy, Forecasting, Computer vision, Deep learning, Vision Transformer, Sky images
Public URL https://nottingham-repository.worktribe.com/output/22436361
Publisher URL https://www.sciencedirect.com/science/article/pii/S0960148123008583

Files





You might also like



Downloadable Citations