Next Article in Journal
Can International Trade Help Africa’s Least Developed Countries Achieve SDG-1?
Next Article in Special Issue
Optimization of Daylighting Pattern of Museum Sculpture Exhibition Hall
Previous Article in Journal
Risk Index Method–A Tool for Sustainable, Holistic Building Fire Strategies
Article

Comparative Performance of Machine Learning Algorithms in the Prediction of Indoor Daylight Illuminances

1
Department of Architectural Engineering, Kyung Hee University, Yongin 17104, Korea
2
Department of Architectural Engineering, University of Ulsan, Ulsan 44610, Korea
*
Author to whom correspondence should be addressed.
Sustainability 2020, 12(11), 4471; https://doi.org/10.3390/su12114471
Received: 2 May 2020 / Revised: 28 May 2020 / Accepted: 29 May 2020 / Published: 1 June 2020
(This article belongs to the Special Issue Design of Architectural Sustainable Lighting)
The performance of machine learning (ML) algorithms depends on the nature of the problem at hand. ML-based modeling, therefore, should employ suitable algorithms where optimum results are desired. The purpose of the current study was to explore the potential applications of ML algorithms in modeling daylight in indoor spaces and ultimately identify the optimum algorithm. We thus developed and compared the performance of four common ML algorithms: generalized linear models, deep neural networks, random forest, and gradient boosting models in predicting the distribution of indoor daylight illuminances. We found that deep neural networks, which showed a determination of coefficient (R2) of 0.99, outperformed the other algorithms. Additionally, we explored the use of long short-term memory to forecast the distribution of daylight at a particular future time. Our results show that long short-term memory is accurate and reliable (R2 = 0.92). Our findings provide a basis for discussions on ML algorithms’ use in modeling daylight in indoor spaces, which may ultimately result in efficient tools for estimating daylight performance in the primary stages of building design and daylight control schemes for energy efficiency. View Full-Text
Keywords: machine learning; daylighting performance; daylighting control; deep learning; decision trees; daylight forecasting; predictive modeling; time-series machine learning; daylighting performance; daylighting control; deep learning; decision trees; daylight forecasting; predictive modeling; time-series
Show Figures

Figure 1

MDPI and ACS Style

Ngarambe, J.; Irakoze, A.; Yun, G.Y.; Kim, G. Comparative Performance of Machine Learning Algorithms in the Prediction of Indoor Daylight Illuminances. Sustainability 2020, 12, 4471. https://doi.org/10.3390/su12114471

AMA Style

Ngarambe J, Irakoze A, Yun GY, Kim G. Comparative Performance of Machine Learning Algorithms in the Prediction of Indoor Daylight Illuminances. Sustainability. 2020; 12(11):4471. https://doi.org/10.3390/su12114471

Chicago/Turabian Style

Ngarambe, Jack, Amina Irakoze, Geun Y. Yun, and Gon Kim. 2020. "Comparative Performance of Machine Learning Algorithms in the Prediction of Indoor Daylight Illuminances" Sustainability 12, no. 11: 4471. https://doi.org/10.3390/su12114471

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop