ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph
For building HVAC control, this work addresses the limitation of existing LLM-based controllers in reasoning about spatial and thermal interactions, offering a more effective approach for energy-efficient comfort management.
ThermoLLM introduces a thermodynamics-aware LLM controller for multi-zone HVAC control that uses a physics-informed spatial knowledge graph to capture zone coupling and thermal dynamics. In a five-zone EnergyPlus simulation, it achieves the best energy-comfort trade-off and lowest PMV violation among baselines.
Multi-zone HVAC control is a spatial decision problem in which indoor thermal evolution and control decisions depend not only on outdoor conditions and internal heat gains but also on zone layout, physical adjacency, and delayed thermal interactions across the building. Recent LLM-based HVAC controllers have shown that prompt-based control is feasible. However, these methods typically rely on task descriptions, observation values, short textual feedback, or unstructured retrieval, which limits their ability to reason about zone coupling, thermal response, and building dynamics. This paper presents a thermodynamics-aware LLM control framework for a five-zone EnergyPlus building simulation. The controller is grounded in a physics-informed spatial knowledge graph derived from Brick-style building semantics and linked with recent interaction history. At each control step, the model receives the current building state, graph-structured spatial context, and recent environment-controller history, enabling it to make decisions that reflect both building structure and short-term thermal evolution. We evaluate the framework against standard control baselines and several LLM-based alternatives. Results show that the proposed approach achieves the best overall energy-comfort trade-off and the lowest PMV violation while maintaining energy-efficient operation.