Evaluating advanced HVAC control benefits in operational buildings using historic data — A case study

Convincing building owners to retrofit advanced controls is a challenge due to the perceived complexity and unclear lack of benefits for a given building system. This paper describes an approach developed to demonstrate the benefits of Model Predictive Control (MPC) in an operating commercial building with access to historic data. A surrogate model of a building cooling delivery system and distributed energy resources, solar thermal fields, and thermal storage, has been developed to benchmark the building's Business As Usual (BAU) operations. A combination of white, gray, and black box modeling techniques have been used to capture and validate the operation of the building system with operational data. To analyze costs and operational benefits of the MPC retrofit, we employ machine learning techniques to identify representative day profiles in the dataset that capture the typical behavior of the system across a range of weather conditions. We then compare the performance of the MPC algorithm with a baseline case in these representative day profiles. The results demonstrate that the predictive controller surpasses the BAU baseline performance by strategically shifting the operation cost to off-peak hours through optimal utilization of thermal storage and the chiller plant. These results satisfied the building manager to favorably consider implementing MPC in the building.