We present a Bayesian optimization (BO) framework for tuning model predictive controllers (MPC) of central heating, ventilation, and air conditioning (HVAC) plants. This approach treats the functional relationship between the closedloop performance of MPC and its tuning parameters as a black-box. The approach is motivated by the observation that evaluating the closed-loop performance of MPC by trial-anderror is time-consuming (e.g., every closed-loop simulation can involve solving thousands of optimization problems). The proposed BO framework seeks to quickly identify the optimal tuning parameters by strategically exploring and exploiting the space of the tuning parameters. The effectiveness of the BO framework is demonstrated by using an MPC controller for a complex central HVAC plant using realistic data. Here, the BO framework tunes back-off terms for thermal storage tanks to minimize year-long closed-loop costs. Simulation results show that BO can find the optimal back-off terms by conducting 13 year-long simulations, which significantly reduces the computational burden of a naive grid search. We also find that the back-off terms obtained with BO reduce the closed-loop costs from a baseline value of 9.1 million USD to 6.92 million USD (a reduction of 24%).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.