2020/12/02 by Quentin Paletta, Paletta, Quentin, Joan Lasenby +1
Computer Science · Energy · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques #Machine Learning (cs.LG) #Photovoltaic System Optimization Techniques #Solar Radiation and Photovoltaics #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2012.01059
Accepted as a workshop paper at NeurIPS 2020
openalex publication_date 2020/12/02 · arxiv created 2022/10/25 · arxiv updated 2022/10/26 · openalex created_date 2022/11/01 · openalex updated_date 2026/07/28
Improving irradiance forecasting is critical to further increase the share of solar in the energy mix. On a short time scale, fish-eye cameras on the ground are used to capture cloud displacements causing the local variability of the electricity production. As most of the solar radiation comes directly from the Sun, current forecasting approaches use its position in the image as a reference to interpret the cloud cover dynamics. However, existing Sun tracking methods rely on external data and a calibration of the camera, which requires access to the device. To address these limitations, this study introduces an image-based Sun tracking algorithm to localise the Sun in the image when it is visible and interpolate its daily trajectory from past observations. We validate the method on a set of sky images collected over a year at SIRTA's lab. Experimental results show that the proposed method provides robust smooth Sun trajectories with a mean absolute error below 1% of the image size.