Personalized Building Climate Control with Contextual Preferential Bayesian Optimization

TL;DR

This paper introduces a Bayesian optimization method that uses preference feedback and contextual data to efficiently personalize building climate controllers, improving occupant utility by up to 23% in simulations.

Contribution

It presents a novel contextual preferential Bayesian optimization algorithm for real-time, personalized building climate control tuning using preference feedback.

Findings

Outperforms baseline controllers in simulations.

Achieves up to 23% utility improvement.

Automatically adapts to individual occupant preferences.

Abstract

Efficient tuning of building climate controllers to optimize occupant utility is essential for ensuring overall comfort and satisfaction. However, this is a challenging task since the latent utility are difficult to measure directly. Time-varying contextual factors, such as outdoor temperature, further complicate the problem. To address these challenges, we propose a contextual preferential Bayesian optimization algorithm that leverages binary preference feedback together with contextual information to enable efficient real-time controller tuning. We validate the approach by tuning an economic MPC controller on BOPTEST, a high-fidelity building simulation platform. Over a two-month simulation period, our method outperforms the baseline controller and achieves an improvement of up to 23% in utility. Moreover, for different occupant types, we demonstrate that the algorithm automatically adapts to individual preferences, enabling personalized controller tuning.