An Automated Space-Based Graph Generation Framework for Building Energy Consumption Estimation

The 3D information in Building Information Modeling (BIM) has received significant interest for smart city applications. Recently, employing Industry Foundation Classes (IFC) BIM data-driven methods Energy Consumption Estimation (BECE) gained momentum because of the enriched geometric and semantic information. However, despite extensive studies on applying IFC data BECE analysis, full potential remains poor due to its complex model incompatibility with algorithms. This paper proposes a framework extract accurate semantic, geometry, topology from room-level (space) schema by introducing new geo-computation algorithms deal these challenges. Additionally, we define topological weighted relationship between spaces different stories combining common geometry area energy resistance value. Eventually, proposed space-based graph will be constructed decrease original complexity model, it is compatible graph-based machine learning results are promising, more than 90% accuracy extracting convex non-convex polyhedron rooms 100% detecting vertical horizontal adjacent rooms. study confirms approach’s efficiency, accuracy, feasibility analysis.