Generating prototypical residential building geometry models using a new hybrid approach

Building prototyping has regularly been used in building performance analyses with statistically feasible models. The novelty of this research involves a new hybrid approach combining stratified sampling and k-means clustering to establish geometry prototypes. focuses on residential buildings Ningbo, China. Seventeen small districts (SRDs) containing 367 were systemically selected for survey data collection. construction year as the main parameter generate stratification. Floor numbers, shape coefficients, floor areas, window-to-wall ratios four observations clustering. Based approach, nine prototypes identified modelled. These representative provide geometrical information characteristic-based evaluations subsequent analysis.