Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness
作者: Alexander Neubauer, Tianzhen Hong, Han Li, Mengbo Yu, Amin Darbandi, Yannick Fürst, Martin Kriegel
分类: cs.AI, cs.CL, eess.SY
发布日期: 2026-09-04
备注: 38 pages, 9 figures, 16 tables. Submitted to Energy and Buildings
💡 一句话要点
系统评估大型语言模型在HVAC操作中的应用与部署准备
🎯 匹配领域: 支柱一：机器人控制 (Robot Control) 支柱二：RL算法与架构 (RL & Architecture) 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 建筑自动化 大型语言模型 HVAC系统 能效建模 负荷预测 人机协作 系统评审
📋 核心要点
- 现有建筑自动化系统在数据利用上存在障碍，主要由于数据命名不一致和文档缺失。
- 论文系统评审了66篇研究，分类并评估LLMs在HVAC操作中的应用及其准备情况。
- 研究发现，虽然LLMs在建筑能效建模中有潜力，但尚未达到行业应用的准备水平。
📝 摘要（中文）
建筑自动化系统生成丰富的传感器数据，但由于异构点命名、缺失元数据和文档碎片化，导致其操作使用缺乏洞察。本系统评审分析了2023年至2026年3月间发表的66篇关于大型语言模型（LLMs）在HVAC操作中的研究。每项研究根据五个应用类别和三个LLM方法类别进行分类，并评估其证据真实性、部署准备情况以及LLM与物理HVAC决策之间的责任边界。尽管当前证据主要支持LLMs作为语义和工作流层，而非自主HVAC控制器，但一些有界的人机协作应用值得进行近期试验。
🔬 方法详解
问题定义：本论文旨在解决建筑自动化系统中数据利用不足的问题，现有方法面临异构数据命名和文档缺失等挑战。
核心思路：通过系统评审和分类分析现有研究，识别LLMs在HVAC操作中的应用潜力和部署准备情况。
技术框架：研究首先对66篇相关文献进行分类，涵盖五个应用类别和三个方法类别，随后评估其证据的真实性和部署准备情况。
关键创新：论文的创新在于系统性地评估LLMs在HVAC领域的应用，明确了其作为语义和工作流层的角色，而非完全自主的控制器。
关键设计：研究中采用了分类和评估的方法，重点关注证据的真实性和实际应用的可行性，未设定具体的参数或模型结构。
🖼️ 关键图片
📊 实验亮点
研究发现，只有四项研究达到试点级别证据，且没有报告持续的操作部署。大多数研究被分类为仅限研究，显示出LLMs在HVAC领域的应用仍处于探索阶段。
🎯 应用场景
该研究的潜在应用领域包括建筑能效建模、负荷预测和操作支持系统。通过改进数据处理和决策支持，LLMs可以帮助提升HVAC系统的效率和可靠性，未来可能推动建筑自动化的智能化进程。
📄 摘要（原文）
Building automation systems generate rich sensor data yet remain insight-poor because heterogeneous point naming, missing metadata, and fragmented documentation obstruct their operational use. This systematic review analyses and codes 66 peer-reviewed studies on large language models (LLMs) for HVAC operations published between 2023 and March 2026. Each study is classified across five application families and three LLM method families and assessed for evidence realism, deployment readiness, and the responsibility boundary between the LLM and physical HVAC decisions. The corpus is concentrated in building energy modelling (BEM, 32 of 66 papers), while load forecasting remains too sparse for subfield-level conclusions. Only four studies reach pilot-level evidence, and none reports sustained operational deployment. No study was classified as ready-now for industry adoption; three were near-term and 63 research-only. Nevertheless, several bounded, human-in-the-loop uses merit near-term trials, including point-name normalisation, document-grounded operator support, BEM workflow assistance, and advisory interfaces around physics-based controllers. Conventional machine learning (ML), model predictive control (MPC), reinforcement learning (RL) and ontology-based tools remain more adopted for high-frequency control, short-horizon numerical forecasting, and well-posed ontology mapping, while autonomous agentic operation and unvalidated occupant proxies remain research-stage. Current evidence therefore supports LLMs primarily as semantic and workflow layers rather than autonomous HVAC controllers. Future work should prioritise field-validated benchmarks, orchestration evaluation under operational constraints, and LLM-MPC/RL architectures with bounded latency and verifiable safety properties.