Vision transformer models to measure solar irradiance using sky images in temperate climates

• Published in: Applied energy 2024-05, Vol.362, p.122967, Article 122967
• Main Authors: Mercier, Thomas M., Sabet, Amin, Rahman, Tasmiat
• Format: Article
• Language: English
• Subjects: Computer vision; Machine learning; Sky imaging; Solar irradiance
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2024.122967

Solar Irradiance measurements are critical for a broad range of energy systems, including evaluating performance ratios of photovoltaic systems, as well as forecasting power generation. Using sky images to evaluate solar irradiance, allows for a low-cost, low-maintenance, and easy integration into Internet-of-things network, with minimal data loss. This work demonstrates that a vision transformer-based machine learning model can produce accurate irradiance estimates based on sky-images without any auxiliary data being used. The training data utilizes 17 years of global horizontal, diffuse and direct data, based on a high precision pyranometer and pyrheliometer sun-tracked system; in-conjunction with sky images from a standard lens and a fish-eye camera. The vision transformer-based model learns to attend to relevant features of the sky-images and to produce highly accurate estimates for both global horizontal irradiance (RMSE =52 W/m2) and diffuse irradiance (RMSE = 31 W/m2). This work compares the model’s performance on wide field of view all-sky images as well as images from a standard camera and shows that the vision transformer model works best for all-sky images. For images from a normal camera both vision transformer and convolutional architectures perform similarly with the convolution-based architecture showing an advantage for direct irradiance with an RMSE of 155 W/m2. •Transformer models outperform convolution models for sky irradiance estimation.•Pyranometers can be replaced by all-sky images and DL models for wider deployment.•Even conventional cameras can serve as basis for useful estimates.•The model learns to focus on crucial features in sky images for irradiance estimation.