A Review on Light Shelf Design by Machine Learning Concept to Predict Daylighting Requirements

Omnya Saleh Zekry, Ahmed Ahmed Fekry, Reham El desouky Hamed

Abstract


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.


Keywords


Daylighting;Light Shelf;Machine Learning;Artificial Neural Network

Full Text:

PDF

References


H. Lee, S. Gim, J. Seo, and Y. Kim, “Study on movable light-shelf system with location-awareness technology for lighting energy saving,” Indoor and Built Environment, vol. 26, no. 6, pp. 796–812, 2017, DOI: 10.1177/1420326X16659691.

M. Moazzeni and Z. Ghiabaklou, “Investigating the influence of light shelf geometry parameters on daylight performance and visual comfort, a case study of educational space in Tehran, Iran,” Buildings, vol. 6, no. 3, pp. 1–16, 2016, DOI: 10.3390/buildings6030026.

H. Lee, S. Park, and J. Seo, “Development and performance evaluation of light shelves using width-adjustable reflectors,” Advances in Civil Engineering, vol. 2018, pp. 1–10, 2018, DOI: 10.1155/2018/2028065.

A. Meresi, “Evaluating daylight performance of light shelves combined with external blinds in south-facing classrooms in Athens, Greece,” Energy and Buildings, vol. 116, pp. 190–205, 2016, DOI: 10.1016/j.enbuild.2016.01.009.

G. Warrier and B. Raphael, “Performance evaluation of light shelves,” Energy and Buildings, vol. 140, pp. 19–27, 2017, DOI: 10.1016/j.enbuild.2017.01.068.

M. Essa, A. El-Shafeey, A. Omar, A. Fathi, A. S. El Maref, J. Lotfy, and M. El-Sayed, “Reliable integration of neural network and Internet of Things for forecasting, controlling, and monitoring of experimental building management system,” Sustainability, vol. 15, no. 3, p. 2168, 2023, DOI: 10.3390/su15032168.

C. Lorenz and W. Jabi, “Predicting daylight autonomy metrics using machine learning,” Proceedings of the International Conference for Sustainable Design of the Built Environment (SDBE), pp. 1–14, 2017.

S. Hosseini, N. Masoumi, M. Modarressi, and N. Karimian, “Daylight adaptive smart indoor lighting control method using artificial neural networks,” Journal of Building Engineering, vol. 29, p. 101141, 2020, DOI: 10.1016/j.jobe.2019.101141.

M. Beccali, M. Bonomolo, G. Ciulla, and V. Lo Brano, “Assessment of indoor illuminance and study on best photosensors’ position for design and commissioning of daylight linked control systems: A new method based on artificial neural networks,” Energy, vol. 154, pp. 466–476, 2018, DOI: 10.1016/j.energy.2018.04.106.

B. Mohapatra, M. Kumar, and S. Mandal, “Positioning of light shelves to enhance daylight illuminance in office rooms,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 15, no. 1, pp. 168–177, 2019, DOI: 10.11591/ijeecs.v15.i1.pp168-177.

P. Zazzini, A. Romano, A. Di Lorenzo, V. Portaluri, and A. Di Crescenzo, “Experimental analysis of the performance of light shelves in different geometrical configurations through the scale model approach,” Journal of Daylighting, vol. 7, no. 1, pp. 37–56, 2020, DOI: 10.15627/jd.2020.4.

A. Bahdad, S. Fadzil, H. O. Onubi, and S. A. BenLasod, “Multi-dimensions optimization for optimum modifications of light-shelves parameters for daylighting and energy efficiency,” International Journal of Environmental Science and Technology, vol. 19, no. 4, pp. 2659–2676, 2022, DOI: 10.1007/s13762-021-03328-9.

A. Freewan, L. Shao, and S. Riffat, “Optimizing performance of the lightshelf by modifying ceiling geometry in highly luminous climates,” Solar Energy, vol. 82, no. 4, pp. 343–353, 2008, DOI: 10.1016/j.solener.2007.08.003.

P. Littlefair, “Light shelves: Computer assessment of daylighting performance,” Lighting Research & Technology, vol. 27, no. 2, pp. 79–91, 1995, DOI: 10.1177/14771535950270020201.

A. Kontadakis, A. Tsangrassoulis, L. Doulos, and S. Zerefos, “A review of light shelf designs for daylit environments,” Sustainability, vol. 10, no. 1, 2017, DOI: 10.3390/su10010071.

S. Noshin, H. Kanwal, and A. Ahmad, “A comparative study on daylight performance assessment of light shelves based on inclination,” Mehran University Research Journal of Engineering and Technology, vol. 39, no. 4, pp. 800–805, 2020, DOI: 10.22581/muet1982.2004.12.

F. Häse, L. Roch, P. Friederich, and A. Aspuru-Guzik, “Designing and understanding light-harvesting devices with machine learning,” Nature Communications, vol. 11, no. 1, pp. 1–11, 2020, DOI: 10.1038/s41467-020-17995-8.

H. Liu, X. Wang, Y. Chen, D. Kong, and P. Xia, “Optimization lighting layout based on gene density improved genetic algorithm for indoor visible light communications,” Optics Communications, vol. 390, pp. 76–81, 2017, DOI: 10.1016/j.optcom.2016.12.065.

E. Horvitz and D. Mulligan, “Machine learning: Trends, perspectives, and prospects,” Science, vol. 349, no. 6245, pp. 253–255, 2015.

I. Chatzikonstantinou and S. Sariyildiz, “Approximation of simulation-derived visual comfort indicators in office spaces: A comparative study in machine learning,” Architectural Science Review, vol. 59, no. 4, pp. 307–322, 2016, DOI: 10.1080/00038628.2015.1072705.

Y. Liu, A. Colburn, and M. Inanici, “Computing long-term daylighting simulations from high dynamic range imagery using deep neural networks,” ASHRAE and IBPSA-USA Building Simulation Conference, pp. 119–126, 2018.

H. Nourkojouri, N. S. Shafavi, M. Tahsildoost, and Z. S. Zomorodian, “Development of a machine-learning framework for overall daylight and visual comfort assessment in early design stages,” Journal of Daylighting, vol. 8, no. 2, pp. 270–283, 2021, DOI: 10.15627/jd.2021.21.

S. Zhou and D. Liu, “Prediction of daylighting and energy performance using artificial neural network and support vector machine,” American Journal of Civil Engineering and Architecture, vol. 3, no. 3A, pp. 1–8, 2015.

A. Ahmed, S. Bahdad, S. Fairuz, S. Fadzil, and N. Taib, “Optimization of daylight performance based on controllable light-shelf parameters using genetic algorithms in the tropical climate of Malaysia,” Journal of Daylighting, vol. 7, pp. 122–136, 2020, DOI: 10.15627/jd.2020.10.

J. Ngarambe, A. Irakoze, G. Y. Yun, and G. Kim, “Comparative performance of machine learning algorithms in the prediction of indoor daylight illuminances,” Sustainability, vol. 12, no. 11, pp. 1–22, 2020, DOI: 10.3390/su12114471.

R. Labib, “Machine learning-based framework to predict single and multiple daylighting simulation outputs using neural networks,” Proceedings of the 17th IBPSA Conference, Bruges, Belgium, pp. 1334–1340, 1–3 Sept. 2021.

A. Soler and P. Oteiza, “Dependence on solar elevation of the performance of a light shelf as a potential daylighting device,” Renewable Energy, vol. 8, no. 1–4, pp. 198–201, 1996, DOI: 10.1016/0960-1481(96)88845-8.

A. Soler and P. Oteiza, “Light shelf performance in Madrid, Spain,” Building and Environment, vol. 32, no. 2, pp. 87–93, 1997, DOI: 10.1016/S0360-1323(96)00047-9.

S. Claros and A. Soler, “Indoor daylight climate comparison between light shelves and overhang performances in Madrid,” Solar Energy, vol. 71, no. 4, pp. 233–239, 2001, DOI: 10.1016/S0038-092X(01)00046-9.

S. Claros and A. Soler, “Indoor daylight climate: Influence of light shelf and model reflectance on performance in Madrid,” Building and Environment, vol. 37, no. 6, pp. 587–598, 2002, DOI: 10.1016/S0360-1323(01)00074-9.

B. Raphael, “Active control of daylighting features in buildings,” Computer-Aided Civil and Infrastructure Engineering, vol. 26, no. 5, pp. 393–405, 2011, DOI: 10.1111/j.1467-8667.2010.00692.x.

Y. Lim and M. H. Ahmad, “The effects of direct sunlight on light shelf performance under tropical sky,” Indoor and Built Environment, vol. 24, no. 6, pp. 788–802, 2015, DOI: 10.1177/1420326X14536066.

Y. Lim and C. Y. S. Heng, “Dynamic internal light shelf for tropical daylighting in high-rise office buildings,” Building and Environment, vol. 106, pp. 155–166, 2016, DOI: 10.1016/j.buildenv.2016.06.030.

H. Lee, K. Kim, J. Seo, and Y. Kim, “Effectiveness of a perforated light shelf for energy saving,” Energy and Buildings, vol. 144, pp. 144–151, 2017, DOI: 10.1016/j.enbuild.2017.03.008.

W. Youssef, M. Ahmed, and O. Zekry, “Improved window design in buildings light shelf system under overcast condition in Sinai,” Port-Said Engineering Research Journal, vol. 21, no. 2, pp. 9–18, 2017, DOI: 10.21608/pserj.2017.33228.

U. Berardi and H. Anaraki, “The benefits of light shelves over the daylight illuminance in office buildings in Toronto,” Indoor and Built Environment, vol. 27, no. 2, pp. 244–262, 2018, DOI: 10.1177/1420326X16673413.

R. Mangkuto, F. Feradi, R. Eka, R. T. Atmodipoero, and F. Favero, “Optimisation of daylight admission based on modifications of light shelf design parameters,” Journal of Building Engineering, vol. 18, pp. 195–209, 2018, DOI: 10.1016/j.jobe.2018.03.007.

H. Lee, “Performance evaluation of a light shelf with a solar module based on the solar module attachment area,” Building and Environment, vol. 159, p. 106161, 2019, DOI: 10.1016/j.buildenv.2019.106161.

H. Lee, S. Han, and J. Seo, “Light shelf development using folding technology and photovoltaic modules to increase energy efficiency in building,” Buildings, vol. 12, no. 1, 2022, DOI: 10.3390/buildings12010081.

H. Lee, J. Seo, and C. H. Choi, “Preliminary study on the performance evaluation of a light shelf based on reflector curvature,” Energies, vol. 12, no. 22, 2019, DOI: 10.3390/en12224295.

M. Ayoub, “A review on machine learning algorithms to predict daylighting inside buildings,” Solar Energy, vol. 202, pp. 249–275, 2020, DOI: 10.1016/j.solener.2020.03.104.

K. Radziszewski and M. Waczy?ska, “Machine learning algorithm-based tool and digital framework for substituting daylight simulations in early-stage architectural design evaluation,” Simulation Series, vol. 50, no. 7, pp. 1–7, 2018, DOI: 10.22360/simaud.2018.simaud.001.

N. Aste, M. Manfren, and G. Marenzi, “Building automation and control systems and performance optimization: A framework for analysis,” Renewable and Sustainable Energy Reviews, vol. 75, pp. 313–330, 2017, DOI: 10.1016/j.rser.2016.10.072.

I. Petrinska and D. Ivanov, “Comparison of experimental and simulation data for daylighting,” in 2018 Seventh Balkan Conference on Lighting (BalkanLight), pp. 1–4, 2018.

R. R. Verderber, O. C. Morse, and J. Jewell, “Building design: Impact on the lighting control system for a daylighting strategy,” IEEE Transactions on Industry Applications, vol. 25, no. 2, pp. 198–202, 1989, DOI: 10.1109/28.25531.

A. S. Garcia, “Illuminated shelf to charge devices through a solar panel,” International Conference on New Concepts in Smart Cities: Fostering Public and Private Alliances (SmartMILE), pp. 1–2, 2013.

R. M. Abhishek Dhankar and N. Gupta, “A systematic review of techniques, tools and applications of machine learning,” Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), pp. 764–768, 2021.

C. Lorenz, M. Packianather, A. B. Spaeth, and C. De Souza, “Artificial neural network-based modelling for daylight evaluations,” Simulation Series, vol. 50, no. 7, pp. 8–15, 2018, DOI: 10.22360/simaud.2018.simaud.002.

T. Sato, S. Shimada, H. Murakami, H. Watanabe, and H. Hashizume, “ALiSA: A visible-light positioning system using the ambient light sensor assembly in a smartphone,” IEEE Sensors Journal, 2021, DOI: 10.1109/JSEN.2021.3074580.




DOI (PDF): https://doi.org/10.20508/ijrer.v16i1.14998.g9150

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is indexed in EI Compendex, SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics)and CrossRef.

IJRER has been indexed in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4