Estimation of sky luminance in the tropics using artificial neural networks: Modeling and performance comparison with the CIE model

• Published in: Applied energy Vol. 88; no. 3; pp. 840 - 847
• Main Authors: Janjai, Serm, Plaon, Piyanuch
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.03.2011; Elsevier
• Series: Applied Energy
• Subjects: algorithms; Artificial neural network; Artificial neural networks; Back propagation algorithms; CIE model; cloud cover; Daylight; Earth atmosphere; Earth, ocean, space; Estimating; Exact sciences and technology; External geophysics; Learning theory; lighting; Mathematical models; Meteorology; Modeling; Neural networks; Radiative transfer. Solar radiation; Sky; Sky luminance; Sky luminance Daylight Modeling Artificial neural network The tropics CIE model; Thailand; The tropics; Tropics; Thailand; Far East; Asia; The tropics; Sky luminance; Daylight; CIE model; Artificial neural network; Modeling; Backpropagation algorithm; Luminance; neural networks; tropical zone; Cloudiness; Forecast model
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2010.09.004

An artificial neural network (ANN) model for estimating sky luminance was developed. A 3-year period (2007–2009) of sky luminance data obtained from measurements at Nakhon Pathom (13.82°N, 100.04°E) and a 1-year period (2008) of the same type of data at Songkhla (7.20°N, 100.60°E), Thailand were used in this study. The ANN model was trained using a back propagation algorithm, based on 2 years data (2007–2008) at Nakhon Pathom for clear, partly cloudy and overcast skies. The trained ANN model was used to predict sky luminance at Nakhon Pathom for the year 2009 for the case of clear, partly cloudy and overcast skies. The results were compared with those of the CIE model. It was found that the ANN model performed better than CIE models for most cases. The ANN model trained with Nakhon Pathom data were also used to predict sky luminance at Songkhla and satisfactory results were obtained.