.png){kind=icon}
.png){kind=icon}
Return
Generative design and multi-objective optimization for enhanced building thermal performance
.png){kind=icon}
OA
AI
DOI：10.1016/j.csite.2025.106621.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This research proposes a framework that generates multiple building design alternatives for residential urban typologies, aiming to optimize thermal performance parameters by focusing on decreasing Incident Radiation (IR) while increasing the Shadow Area of the building, Vegetation Area (VA), and carbon dioxide (CO2) Reduction rate. The proposed framework consists of three modules: 1) Generative Scripting module, 2) Multi-objective Optimization module, and 3) Decision-Making module. Rhinoceros 3D's Visual programming environment, known as Grasshopper, and its components, packages, and plugins, such as Ladybug, Honeybee, and Wallacei X, are used to generate multiple simulated design scenarios for efficient building design. Furthermore, decision-making utilizes Data Envelopment Analysis (DEA), a linear programming methodology that quantifies the relative thermal performance parameters efficiency based on design parameters. Moreover, a case study of an urban plot comprising six residential buildings located in Al-Shorouk City, Egypt, is examined using the proposed framework to illustrate its key features.
Keywords:
Generative design
Multi-objective optimization
Genetic algorithm
Data envelopment analysis
Buildings thermal performance
Journal
IF:
6.4
Papers:
8.0K
Citations:
2.6W