Saved in:
Bibliographic Details
Main Authors: Mostafavi, Saman, Song, Chihyeon, Sharma, Aayushman, Goyal, Raman, Brito, Alejandro
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2301.13447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909156335681536
author Mostafavi, Saman
Song, Chihyeon
Sharma, Aayushman
Goyal, Raman
Brito, Alejandro
author_facet Mostafavi, Saman
Song, Chihyeon
Sharma, Aayushman
Goyal, Raman
Brito, Alejandro
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2301_13447
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)
Mostafavi, Saman
Song, Chihyeon
Sharma, Aayushman
Goyal, Raman
Brito, Alejandro
Systems and Control
Artificial Intelligence
Machine Learning
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.
title Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)
topic Systems and Control
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2301.13447