This paper aims to develop DGP predictive methods. Linear regression and machine learning based approaches were used to compare the performance of newly developed models and these models were compared with existing equations. The results show that developed models are more correct in predicting DGP than the existing equation. In addition, the second new finding by this research is that the combination of the azimuth (Az) and altitude (Aa) angle of the sun and time of day (T) along with vertical eye illuminance (Ev) supply a little better performance than Ev alone due to the consideration of the interaction effect between these factors. Therefore, the developed models can be used if linear model is preferred for simplification of computation. For a higher predictive performance, random forest models based on Ev, Az, Aa, and T is recommended due to its capability of dealing with nonlinear effects. The last contribution of this paper is that a classification model was developed for predicting DGP>0.4 by random forest algorithm considering Ev, Az, Aa, and T with adequate accuracy (90 %), which extends the ability of existing methods to the condition when the sun is in the field of view.
1. Yan D., Hong T., Li C., Zhang Q., An J., and Hu S. A thorough assessment of China’s standard for energy consumption of buildings // Energy Build, 2017, Vol. 143, pp. 114–128.
2. Yao J. Determining the energy performance of manually controlled solar shades: A stochastic model based co-simulation analysis // Appl. Energy, 2014, Vol. 127, pp. 64–80.
3. Lee H., Jeon G., Seo J., and Kim Y. Daylighting performance improvement of a light-shelf using diffused reflection // Indoor Built Environ., 2017, Vol. 26, # 5, pp. 717–726.
4. Shen H. and Tzempelikos A. Daylighting and energy analysis of private offices with automated interior roller shades // Sol. Energy, 2012, Vol. 86, # 2, pp. 681–704.
5. Skarning G.C. J., Hviid C.A., and Svendsen S. The effect of dynamic solar shading on energy, daylighting and thermal comfort in a nearly zero-energy loft room in Rome and Copenhagen // Energy Build., 2017, Vol. 135, pp. 302–311.
6. Yao J. An investigation into the impact of movable solar shades on energy, indoor thermal and visual comfort improvements // Build. Environ., 2014, Vol. 71, pp. 24–32.
7. Hirning M.B., Isoardi G.L., and Garcia-Hansen V.R. Prediction of discomfort glare from windows under tropical skies // Build. Environ., 2017, Vol. 113, pp. 107–120.
8. Konstantzos I. and Tzempelikos A. Daylight glare evaluation with the sun in the field of view through window shades // Build. Environ., 2017, Vol. 113, pp. 65–77.
9. Wienold J. Dynamic daylight glare evaluation // IBPSA 2009 – Int. Build. Perform. Simul. Assoc. 2009, pp. 944–951.
10. Wienold J. Dynamic simulation of blind control strategies for visual comfort and energy balance analysis // IBPSA 2007 – Int. Build. Perform. Simul. Assoc. 2007, pp. 1197–1204.
11. Wienold J. and Christoffersen J. Evaluation methods and development of a new glare prediction model for daylight environments with the use of CCD cameras // Energy Build., 2006, Vol. 38, #7, pp. 743–757.
12. Kunwar N. and Bhandari M. A comprehensive analysis of energy and daylighting impact of window shading systems and control strategies on commercial buildings in the United States // Energies, 2020, Vol. 13, # 9.
13. Konstantzos I., Tzempelikos A., and Chan Y.C. Experimental and simulation analysis of daylight glare probability inoffices with dynamic window shades // Build. Environ., 2015, Vol. 87, pp. 244–254.
14. Xiong J. and Tzempelikos A. Model-based shading and lighting controls considering visual comfort and energy use // Sol. Energy, 2016, Vol. 134, pp. 416–428.

• Previous article
• Next article

• daylight glare probability
• machine learning
• prediction
• hot summer and cold winter zone