Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)

TL;DR

This paper introduces a data-driven, modular framework for building emulation and control using surrogate models to enhance Model Predictive Control performance, tested within the BOPTEST environment.

Contribution

It develops a flexible, scalable approach combining offline surrogate modeling with nonlinear MPC for building HVAC systems, adaptable to various test cases.

Findings

Surrogate models significantly speed up MPC evaluations.

Framework achieves accurate control in diverse building scenarios.

Compatible with multiple modeling and optimization techniques.

Abstract

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.