Energy saving and carbon emission reduction in buildings is one of the key measures in combating climate change. Heating, Ventilation, and Air Conditioning (HVAC) system account for the majority of the energy consumption in the built environment, and among which, the chiller plant constitutes the top portion. The optimization of chiller system power consumption had been extensively studied in the mechanical engineering and building service domains. Many works employ physical models from the domain knowledge. With the advance of big data and AI, the adoption of machine learning into the optimization problems becomes popular. Although many research works and projects turn to this direction for energy saving, the application into the optimization problem remains a challenging task. This work is targeted to outline a framework for such problems on how the energy saving should be benchmarked, if holistic or individually modeling should be used, how the optimization is to be conducted, why data pattern augmentation at the initial deployment is a must, why the gradually increasing changes strategy must be used. Results of analysis on historical data and empirical experiment on live data are presented.

中文翻译：

---

AI Chiller：一种基于开放物联网云的机器学习框架，通过融合 BMS 和环境数据的大数据分析实现建筑暖通空调系统的节能

建筑节能减排是应对气候变化的关键措施之一。供暖、通风和空调（HVAC）系统占建筑环境能耗的大部分，其中，冷水机组构成了最重要的部分。冷却器系统功耗的优化已在机械工程和建筑服务领域得到广泛研究。许多作品采用领域知识中的物理模型。随着大数据和人工智能的进步，将机器学习应用于优化问题变得流行起来。尽管许多研究工作和项目都转向了这个节能方向，但在优化问题中的应用仍然是一项具有挑战性的任务。这项工作旨在概述此类问题的框架，包括如何对节能进行基准测试，是否应使用整体或单独建模，如何进行优化，为什么必须在初始部署时增强数据模式，为什么必须使用逐渐增加的变化策略。介绍了历史数据分析和实时数据实证实验的结果。