Dataset for Machine Learning: Explicit All-Sky Image Features to Enhance Solar Irradiance Prediction

• Published in: Data (Basel) Vol. 9; no. 10; p. 113
• Main Authors: Maciel, Joylan Nunes, Ledesma, Jorge Javier Gimenez, Ando Junior, Oswaldo Hideo
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-10-2024
• Subjects: all-sky image features; Artificial intelligence; Clouds; Data processing; Datasets; Deep learning; Environmental aspects; Image enhancement; Image processing; Irradiance; Machine learning; Methods; photovoltaic energy forecasting; Photovoltaic power generation; Sky; Solar energy; solar irradiance prediction; Solar radiation; Sun; Workflow; Brazil; United States > US
• ISSN: 2306-5729; 2306-5729
• DOI: 10.3390/data9100113

Prediction of solar irradiance is crucial for photovoltaic energy generation, as it helps mitigate intermittencies caused by atmospheric fluctuations such as clouds, wind, and temperature. Numerous studies have applied machine learning and deep learning techniques from artificial intelligence to address this challenge. Based on the recently proposed Hybrid Prediction Method (HPM), this paper presents an original and comprehensive dataset with nine attributes extracted from all-sky images developed using image processing techniques. This dataset and analysis of its attributes offer new avenues for research into solar irradiance forecasting. To ensure reproducibility, the data processing workflow and the standardized dataset have been meticulously detailed and made available to the scientific community to promote further research into prediction methods for photovoltaic energy generation.