EPC-Based Clustering Framework for Representative Building Selection and Scalable Energy Simulation
Identifying representative buildings is essential for scalable urban energy simulation and effective retrofit planning. However, continuous monitoring data are often unavailable, limiting data-driven classification approaches. This study presents a structured methodology for selecting representative buildings through clustering of Energy Performance Certificate (EPC) attributes. By grouping buildings based on certificate-based features and validating clusters against thermal performance indicators, the research establishes a generalizable framework for simulation targeting and policy support without reliance on long-term metering. Six-Phase Clustering Workflow and Internal Validation The proposed methodology follows a six-phase workflow, beginning with EPC attribute preparation and feature engineering. Three clustering techniques—K-Medoids, Agglomerative clustering, and Gaussian Mixture Model (GMM)—were implemented to group buildings based on similarity. Cluster quality was assessed...