Lessons Learned from Data-Driven Building Control Experiments: Contrasting Gaussian Process-based MPC, Bilevel DeePC, and Deep Reinforcement Learning
This work provides practical guidance for building control practitioners by experimentally evaluating modern data-driven techniques, though it is incremental as it focuses on comparative analysis rather than introducing new methods.
The paper compares three data-driven control techniques—Gaussian process-based MPC, bilevel DeePC, and deep reinforcement learning—in real-world building control experiments across diverse environments, highlighting their trade-offs in data needs, usability, computational load, and robustness to aid practitioners in selecting appropriate methods.
This manuscript offers the perspective of experimentalists on a number of modern data-driven techniques: model predictive control relying on Gaussian processes, adaptive data-driven control based on behavioral theory, and deep reinforcement learning. These techniques are compared in terms of data requirements, ease of use, computational burden, and robustness in the context of real-world applications. Our remarks and observations stem from a number of experimental investigations carried out in the field of building control in diverse environments, from lecture halls and apartment spaces to a hospital surgery center. The final goal is to support others in identifying what technique is best suited to tackle their own problems.