Answers are grounded in this paper and cite their sources.
Climate change is a problem that requires effective solutions. Much research on this subject is now being undertaken because of the recent rise in the energy consumption of lighting. Sustainable strategies serve as excellent examples of energy efficiency in the building sector. Daylight simulations are time-consuming and computationally expensive. Predictive lighting tools combined with predictive models built on machine learning algorithms (MLAs) can improve their output by using neural network algorithms to make decisions early in the design process, which takes a long time when simulation operations are based on evolutionary algorithms. The investigatory methodology employs an analytical framework in which machine learning algorithms are used to configure the geometric parameters of a light shelf. This configuration is then examined in terms of its influence on daylight metrics. This paper showed how combining artificial intelligence techniques with evolutionary algorithms can improve the design of light shelf parameters to meet daylighting requirements. The main results of the study reveal that most office buildings, specifically 54.5%, prefer using a light shelf. In addition, among the commonly experienced climate types, the Mediterranean climate is particularly prevalent, accounting for 36.4%. The evaluation of the simulation tools involved the use of a parametric program that incorporated all significant daylighting metrics as output parameters. Of these metrics, the Useful Daylight Index (UDI) stands out as the most notable, and it is expected to have a significant influence on shaping future light shelf designs using machine learning concepts .
No takes yet. Share an insight, caveat, or question.
Zekry et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: