Physics-constrained Deep Learning of Multi-zone Building Thermal Dynamics

TL;DR

This paper introduces a physics-constrained deep learning approach for modeling multi-zone building thermal dynamics, integrating physics priors and eigenvalue constraints to improve accuracy and interpretability with limited data.

Contribution

The method systematically encodes physics-based knowledge into a neural network architecture and employs eigenvalue constraints for stable, physically realistic predictions.

Findings

Achieved accurate thermal modeling with only 10 days of training data.

Demonstrated improved accuracy over existing methods on real-world data.

Ensured physical plausibility through eigenvalue and inequality constraints.

Abstract

We present a physics-constrained control-oriented deep learning method for modeling building thermal dynamics. The proposed method is based on the systematic encoding of physics-based prior knowledge into a structured recurrent neural architecture. Specifically, our method incorporates structural priors from traditional physics-based building modeling into the neural network thermal dynamics model structure. Further, we leverage penalty methods to provide inequality constraints, thereby bounding predictions within physically realistic and safe operating ranges. Observing that stable eigenvalues accurately characterize the dissipativeness of the system, we additionally use a constrained matrix parameterization based on the Perron-Frobenius theorem to bound the dominant eigenvalues of the building thermal model parameter matrices. We demonstrate the proposed data-driven modeling approach's effectiveness and physical interpretability on a dataset obtained from a real-world office building with 20 thermal zones. Using only 10 days' measurements for training, we demonstrate generalization over 20 consecutive days, significantly improving the accuracy compared to prior state-of-the-art results reported in the literature.