Data-driven optimization design method and tool platform for green residential area layout

In early design stage of residential area layouts, sustainable design and performance optimization are crucial for minimizing environmental impact of buildings. This work integrates environmentally-friendly sustainable design with artificial intelligence technology to enhance residential area layouts. A parametric generative algorithm is developed to automatically generate design schemes for typical Chinese urban residential areas based on a sustainable, performance-oriented design flow. The workflow of architects is summarized into the following steps:1) Extraction of spatial form features from the residential area layout database;2) Automatic generation and sunlight duration simulation of new design schemes;3) Evaluation and screening of generated schemes. The generative algorithm is implemented using Rhino/Grasshopper, Python, and Matlab. In a case study involving residential area layouts in Beijing, the design scheme with the lowest values of DF, WinH, QuVue, SiteH, and UTCI among 42,691 automatically generated schemes was identified as the optimal scheme. This optimal scheme's total load is 40.7% lower than the original scheme. To validate the design flow, two additional case studies were conducted. The results demonstrate that the parametric generative design of residential area layouts facilitates passive sustainable design in the early design stage and enhances environmental effects without increasing construction costs.