Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning
The climate change crisis has resulted in the need to use sustainable methods in architectural design, including building form and orientation decisions that can save a significant amount of energy consumed by a building. Several previous studies have optimized building form and envelope for energy...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/11/10/192 |
| _version_ | 1827721327378694144 |
|---|---|
| author | Amany Khalil Anas M. Hosney Lila Nouran Ashraf |
| author_facet | Amany Khalil Anas M. Hosney Lila Nouran Ashraf |
| author_sort | Amany Khalil |
| collection | DOAJ |
| description | The climate change crisis has resulted in the need to use sustainable methods in architectural design, including building form and orientation decisions that can save a significant amount of energy consumed by a building. Several previous studies have optimized building form and envelope for energy performance, but the isolated effect of varieties of possible architectural forms for a specific climate has not been fully investigated. This paper proposes four novel office building form generation methods (the polygon that varies between pentagon and decagon; the pixels that are complex cubic forms; the letters including H, L, U, T; cross and complex cubic forms; and the round family including circular and oval forms) and evaluates their annual thermal energy use intensity (EUI) for Cairo (hot climate). Results demonstrated the applicability of the proposed methods in enhancing the energy performance of the new forms in comparison to the base case. The results of the optimizations are compared together, and the four families are discussed in reference to their different architectural aspects and performance. Scatterplots are developed for the round family (highest performance) to test the impact of each dynamic parameter on EUI. The round family optimization process takes a noticeably high calculation time in comparison to other families. Therefore, an Artificial Neural Network (ANN) prediction model is developed for the round family after simulating 1726 iterations. Training of 1200 configurations is used to predict annual EUI for the remaining 526 iterations. The ANN predicted values are compared against the trained to determine the time saved and accuracy. |
| first_indexed | 2024-03-10T21:21:00Z |
| format | Article |
| id | doaj.art-bf026c1539f240c680d07a9c5ac58d13 |
| institution | Directory Open Access Journal |
| issn | 2079-3197 |
| language | English |
| last_indexed | 2024-03-10T21:21:00Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computation |
| spelling | doaj.art-bf026c1539f240c680d07a9c5ac58d132023-11-19T16:07:36ZengMDPI AGComputation2079-31972023-10-01111019210.3390/computation11100192Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine LearningAmany Khalil0Anas M. Hosney Lila1Nouran Ashraf2Department of Architectural Engineering, Faculty of Engineering & Technology, Future University in Egypt, 90th St, New Cairo 11835, Cairo Governorate, EgyptSchool of Architecture & Environment, College of Arts, Technology & Environment (CATE), University of the West of England, Bristol BS16 1QY, UKDepartment of Architectural Engineering, Faculty of Engineering & Technology, Future University in Egypt, 90th St, New Cairo 11835, Cairo Governorate, EgyptThe climate change crisis has resulted in the need to use sustainable methods in architectural design, including building form and orientation decisions that can save a significant amount of energy consumed by a building. Several previous studies have optimized building form and envelope for energy performance, but the isolated effect of varieties of possible architectural forms for a specific climate has not been fully investigated. This paper proposes four novel office building form generation methods (the polygon that varies between pentagon and decagon; the pixels that are complex cubic forms; the letters including H, L, U, T; cross and complex cubic forms; and the round family including circular and oval forms) and evaluates their annual thermal energy use intensity (EUI) for Cairo (hot climate). Results demonstrated the applicability of the proposed methods in enhancing the energy performance of the new forms in comparison to the base case. The results of the optimizations are compared together, and the four families are discussed in reference to their different architectural aspects and performance. Scatterplots are developed for the round family (highest performance) to test the impact of each dynamic parameter on EUI. The round family optimization process takes a noticeably high calculation time in comparison to other families. Therefore, an Artificial Neural Network (ANN) prediction model is developed for the round family after simulating 1726 iterations. Training of 1200 configurations is used to predict annual EUI for the remaining 526 iterations. The ANN predicted values are compared against the trained to determine the time saved and accuracy.https://www.mdpi.com/2079-3197/11/10/192alternative building formsparametric modelingoptimizationmachine learningenergy performancegenetic algorithm |
| spellingShingle | Amany Khalil Anas M. Hosney Lila Nouran Ashraf Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning Computation alternative building forms parametric modeling optimization machine learning energy performance genetic algorithm |
| title | Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning |
| title_full | Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning |
| title_fullStr | Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning |
| title_full_unstemmed | Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning |
| title_short | Optimization and Prediction of Different Building Forms for Thermal Energy Performance in the Hot Climate of Cairo Using Genetic Algorithm and Machine Learning |
| title_sort | optimization and prediction of different building forms for thermal energy performance in the hot climate of cairo using genetic algorithm and machine learning |
| topic | alternative building forms parametric modeling optimization machine learning energy performance genetic algorithm |
| url | https://www.mdpi.com/2079-3197/11/10/192 |
| work_keys_str_mv | AT amanykhalil optimizationandpredictionofdifferentbuildingformsforthermalenergyperformanceinthehotclimateofcairousinggeneticalgorithmandmachinelearning AT anasmhosneylila optimizationandpredictionofdifferentbuildingformsforthermalenergyperformanceinthehotclimateofcairousinggeneticalgorithmandmachinelearning AT nouranashraf optimizationandpredictionofdifferentbuildingformsforthermalenergyperformanceinthehotclimateofcairousinggeneticalgorithmandmachinelearning |