AI Chiller: An Open IoT Cloud Based Machine Learning Framework for the Energy Saving of Building HVAC System via Big Data Analytics on the Fusion of BMS and Environmental Data
This work addresses energy saving in buildings for climate change mitigation, but it appears incremental as it builds on existing AI and big data applications in HVAC optimization.
The paper tackles optimizing chiller plant energy consumption in building HVAC systems by proposing a machine learning framework that addresses benchmarking, modeling approaches, and deployment strategies, with results from historical data analysis and live experiments.
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.