Walch, A; Castello, R; Mohajeri, N; Scartezzini, JL; (2020) A fast machine learning model for large-scale estimation of annual solar irradiation on rooftops. In: Proceedings of the ISES Solar World Congress 2019 and IEA SHC International Conference on Solar Heating and Cooling for Buildings and Industry 2019. (pp. pp. 2301-2310).

Preview

Text swc2019-proceeding - conference.pdf - Published Version Download (2MB) | Preview

Abstract

Rooftop-mounted solar photovoltaics have shown to be a promising technology to provide clean electricity in urban areas. Several large-scale studies have thus been conducted in different countries and cities worldwide to estimate their PV potential for the existing building stock using different methods. These methods, however, are time-consuming and computationally expensive. This paper provides a Machine Learning approach to estimate the annual solar irradiation on building roofs (in kWh/m2) for large areas in a fast and computationally efficient manner by learning from existing datasets. The estimation is based on rooftop characteristics, input features extracted from digital surface models and annual horizontal irradiation. Five ML models are compared, with Random Forests exhibiting the highest model accuracy. In the presented case study, the model is trained using data of the Swiss Romandie area and is then applied to estimate annual rooftop solar irradiation in remaining Switzerland with an accuracy of 92%.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item