Data-driven adaptive building thermal controller tuning with constraints: A primal–dual contextual Bayesian optimization approach

• Published in: Applied energy Vol. 358; p. 122493
• Main Authors: Xu, Wenjie, Svetozarevic, Bratislav, Di Natale, Loris, Heer, Philipp, Jones, Colin N.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.03.2024
• Subjects: algorithms; ambient temperature; Bayesian optimization; Bayesian theory; Building thermal control; case studies; Contextual model; Controller tuning; energy; Primal–dual method; system optimization; Building thermal control; Primal–dual method; Controller tuning; Bayesian optimization; Contextual model
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2023.122493

We study the problem of tuning the parameters of a room temperature controller to minimize its energy consumption, subject to the constraint that the daily cumulative thermal discomfort of the occupants is below a given threshold. We formulate it as an online constrained black-box optimization problem where, on each day, we observe some relevant environmental context and adaptively select the controller parameters. In this paper, we propose to use a data-driven Primal-Dual Contextual Bayesian Optimization (PDCBO) approach to solve this problem. In a simulation case study on a single room, we apply our algorithm to tune the parameters of a Proportional Integral (PI) heating controller and the pre-heating time. Our results show that PDCBO can save up to 4.7% energy consumption compared to other state-of-the-art Bayesian optimization-based methods while keeping the daily thermal discomfort below the given tolerable threshold on average. Additionally, PDCBO can automatically track time-varying tolerable thresholds while existing methods fail to do so. We then study an alternative constrained tuning problem where we aim to minimize the thermal discomfort with a given energy budget. With this formulation, PDCBO reduces the average discomfort by up to 63% compared to state-of-the-art safe optimization methods while keeping the average daily energy consumption below the required threshold. [Display omitted] •A primal–dual contextual Bayesian optimization framework to tune building controllers is proposed.•It asymptotically achieves the optimal performance while satisfying constraints on average.•It saves up to 4.7% energy compared to alternatives, satisfying thermal comfort constraints on average.•Alternatively, it can reduce the thermal discomfort by 63% within a given energy budget.