CIE Standard Sky classification by accessible climatic indices. (December 2017)

• Record Type: Journal Article
• Authors: Lou, Siwei; Li, Danny H.W.; Lam, Joseph C.
• Is Part Of: Renewable energy. Volume 113(2017)
• Page Start: 347
• Page End: 356
• Publication Date: 2017-12
• Subjects: Diffuse sky model -- CIE Standard Skies -- Machine learning -- Classification Tree; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.renene.2017.06.013
• Languages: English
• ISSNs: 0960-1481

Abstract

Abstract: Solar irradiance and daylight illuminance are essential for solar energy and daylighting designs. Recently, the International Commission of Illuminance (CIE) adopted 15 Standard Skies to represent the possible sky-diffuse luminance and radiance distributions. Such distributions would improve the solar irradiance and daylight illuminance estimations for the building envelope and photovoltaic panels in any directions. The important issue is whether the sky conditions could be correctly identified by the available variables. Previously, many climatic parameters including sky luminance distributions, vertical diffuse irradiance and illuminance were proposed for identifying sky conditions. However, such data may not always be available from the routine measurements of a weather station. This paper proposes an approach to interpreting the sky conditions using the variables that are readily accessible from meteorological stations for many years. The approach appropriately identified 83.2% of the 3 typical overcast, partly cloudy and clear skies, and further 62.7% of the 15 individual CIE Standard Skies for Hong Kong. The %RMSE of the vertical solar irradiance and daylight illuminance estimated by the approach was found less than 23%. The results show that the proposed approach would be reliable for sky classification. Highlights: We built a white box approach by machine learning to classify CIE Standard Skies. The model estimates sky luminance and radiance distribution by accessible variables. The %RMSEs of vertical irradiance and illuminance by the model were less than 23%.