楼宇自动化系统生成丰富的传感器数据，但仍然缺乏洞察力，因为异构点命名, 缺少元数据, 和碎片化文档阻碍了其操作使用。这项系统审查对 2023 年至 2026 年 3 月期间发布的针对 HVAC 操作的大型语言模型 (LLMs) 的 66 项同行评审研究进行了分析和编码。每项研究都分为五个应用程序系列和三个 LLM 方法系列，并评估了证据现实性, 部署准备情况, 以及 LLM 和物理 HVAC 决策之间的责任边界。语料库集中于建筑能源建模 (BEM, 66 篇论文中的 32),，而负荷预测对于子领域级别的结论来说仍然太稀疏。只有四项研究达到了试点级证据,，并且没有一项研究报告了持续的作战部署。没有研究被归类为可供行业采用的现成; 3 项是近期研究，63 项仅用于研究。尽管如此, 一些有限的, 人机交互使用值得近期试验, 包括点名称规范化, 基于文档的操作员支持, BEM 工作流程辅助, 和基于物理的控制器的咨询界面。传统机器学习(ML), 模型预测控制(MPC), 强化学习(RL) 和基于本体的工具仍然更多地用于高频控制, 短期数值预测, 和适定本体映射,，而自主代理操作和未经验证的占用者代理仍处于研究阶段。因此，目前的证据支持LLM主要作为语义和工作流程层，而不是自主的 HVAC 控制器。未来的工作应优先考虑具有有限延迟和可验证安全属性的操作约束下的现场验证基准,编排评估,和LLM-MPC/RL架构。
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.
科目: 人工智能 (cs.AI); 计算与语言 (cs.CL); 系统与控制 (eess.SY)
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Systems and Control (eess.SY)