Construction and Practice of Energy Efficiency Evaluation System for Green Building Environment Design Driven by Artificial Intelligence

Abstract

Green-building energy-efficiency evaluation requires dynamic integration of spatial topology, environmental sensing, and design-optimization feedback. This study constructs an artificial-intelligence-driven evaluation system that combines BIM, IoT monitoring data, graph neural networks, deep reinforcement learning, and interpretable analysis. Building spaces are modeled as graph nodes, while heat-transfer paths, ventilation channels, equipment zoning, and personnel movement are represented as graph edges. A temporal graph attention network extracts environment–space coupling features, and a soft actor-critic reinforcement-learning model dynamically generates multi-objective evaluation weights under energy-efficiency, thermal-comfort, daylighting, and carbon-emission constraints. An interpretable module integrating attention weights and Shapley values forms an assessment–diagnosis–optimization loop. Experiments on eight operational green-building projects show that the system achieves an RMSE of 2.91 kWh/m2·a, reduces prediction error by 66.3% compared with static indicators, and improves energy-efficiency optimization from 12.4% to 28.6%. The framework supports IoT-based environmental sensing, intelligent energy management, and design decision optimization.