跳到正文
arXiv cs.AI· Abbas Raza Ali, Muhammad Hamza Rehman, Xu Li, Muhammad Ajmal Siddiqui·· 2 小时前AI 评分39

从数据到阀门:面向可持续 HVAC 控制的自学习生产级边缘技术栈

From Data to Valves: A Self-Learning, Production-Grade Edge Stack for Sustainable HVAC Control

AI 导读

一套生产级 HVAC 控制技术栈在每栋建筑的一台 NVIDIA Jetson Orin 网关上运行三个持续自学习组件:transformer-encoder 预测器每 5 分钟一个梯度步学习。

正文 · 原文

View PDF HTML (experimental)

Abstract:Learned HVAC controllers rarely leave the simulator, and those that do are typically trained offline, frozen at deployment and retrained from the cloud. We present a production stack in which three learning components run on one NVIDIA Jetson Orin gateway per building, adapt continuously from the building's own data, and verify their own effect. (a) A compact transformer-encoder forecaster, one per equipment group with learned per-unit embeddings, predicts every air-side unit's next-cycle temperature and learns prequentially, one gradient step per five-minute cycle, behind five independent gates that bound the influence of any corrupt reading. (b) A distributional soft actor-critic agent, one shared policy across unit types, converts the measured state into a chilled-water valve position under a structural safety envelope that no learned component can soften; its second generation learns nightly on the device from recorded transitions alone, with a behaviour anchor and critic calibration terms, is scored by four model-free metrics and promoted by atomic hot-swap. (c) A change-point regression baseline held to ASHRAE Guideline 14 supplies the counterfactual against which savings are certified. On eighteen months of data from a hotel the forecaster converges from random weights within a week and reaches 0.37, 0.39 and 0.11 degree C MAE for air-handling, fresh-air and fan-coil units with no retraining event; on a different hotel the baseline reproduces a 46-day held-out period to within 0.07%. The RL agent has completed its in-simulator campaign and runs in shadow on 104 units; we report measured latency and memory of every service on a shared 15 GB device, the systems lessons of the campaign, and precisely what the evidence does and does not yet establish.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24052 [cs.LG]
  (or arXiv:2611.24052v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.24052

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Abbas Raza Ali [view email]
[v1] Wed, 18 Nov 2026 08:43:30 UTC (2,972 KB)

来源:arXiv cs.AI · arxiv.org