Environmental performance driven optimization of urban modular housing layout in Singapore

Abstract

ABSTRACT With the growing size of cities and the need to renew residential areas, architects are calling for more efficient use of already settled areas. This paper presents a performance-driven architectural design (PDAD) workflow for shape generation and genetic optimization based on environmental data, using public housing in the Singapore region as a case study. It integrates three-dimensional cellular automata, parametric performance simulation, genetic optimization algorithms, and hierarchical clustering algorithms. The results show that the average value of Useful Daylight Illuminance (UDI) is 85.19%, the average value of Energy Use Intensity (EUI) is 159.41 kWh/m2, and the average value of Predicted Mean Vote (PMV) is 0.64 for the optimal set of solutions produced after genetic optimization. The optimal solution set was further classified into 4 categories by a hierarchical clustering algorithm and was visualized for further evaluation and selection by the architect. The study helps architects to integrate data analysis results with human decision-making as a design research method in the early stages of design and leads to further discussion on bottom-up design approaches in the urban renewal process.