Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)
This work addresses building energy optimization for scalable and robust real-world applications, but it is incremental as it builds on existing MPC and surrogate modeling techniques.
The paper tackles the problem of optimizing building HVAC systems by developing a data-driven modeling and control framework that uses differentiable surrogate models for Model Predictive Control (MPC), and it demonstrates this through extensive evaluation across various test cases in the BOPTEST framework.
We present a data-driven modeling and control framework for physics-based building emulators. Our approach consists of: (a) Offline training of differentiable surrogate models that accelerate model evaluations, provide cost-effective gradients, and maintain good predictive accuracy for the receding horizon in Model Predictive Control (MPC), and (b) Formulating and solving nonlinear building HVAC MPC problems. We extensively evaluate the modeling and control performance using multiple surrogate models and optimization frameworks across various test cases available in the Building Optimization Testing Framework (BOPTEST). Our framework is compatible with other modeling techniques and can be customized with different control formulations, making it adaptable and future-proof for test cases currently under development for BOPTEST. This modularity provides a path towards prototyping predictive controllers in large buildings, ensuring scalability and robustness in real-world applications.