Dataset for Machine Learning: Explicit All-Sky Image Features to Enhancing Indirect Solar Photovoltaic Forecasting

This dataset contains a set of features explicitly extracted from all-sky images using image processing techniques. The features and global solar irradiance are provided for each all-sky image, with a temporal resolution of 1 minute, spanning three complete years (2014 to 2016). The dataset can be used as a benchmark and for studies on Artificial Intelligence methods applied to solar irradiance prediction and photovoltaic energy generation. The dataset descriptor is detailed in the study titled ‘Dataset for Machine Learning: Explicit All-Sky Image Features to Enhance Solar Irradiance Prediction’, DOI: https://doi.org/10.3390/data9100113.

This dataset uses data derived from: Pedro, H. T. C., Larson, D. P., & Coimbra, C. F. M. (2019). A comprehensive dataset for the accelerated development and benchmarking of solar forecasting methods. Journal of Renewable and Sustainable Energy, 11(3), 036102. https://doi.org/10.1063/1.5094494. The dataset is related with the paper Maciel, J.N.; Ledesma, J.J.G.; Ando Junior, O.H. Hybrid Prediction Method of Solar Irradiance Applied to Short-Term Photovoltaic Energy Generation. Renewable and Sustainable Energy Reviews 2024, 192, 114185, doi:10.1016/j.rser.2023.114185.