Physics Informed Neural Networks for Control Oriented Thermal Modeling of Buildings

TL;DR

This paper introduces physics informed neural networks for control-oriented thermal modeling of buildings, combining physics laws with data-driven methods to improve accuracy and data efficiency in predicting indoor temperature and energy use.

Contribution

The paper proposes two novel physics informed neural network architectures tailored for thermal building modeling, demonstrating their superior accuracy and data efficiency over traditional neural networks.

Findings

Physics informed neural networks require less training data.

The architectures achieve more accurate long-term predictions.

Models effectively capture thermal dynamics and energy consumption.

Abstract

This paper presents a data-driven modeling approach for developing control-oriented thermal models of buildings. These models are developed with the objective of reducing energy consumption costs while controlling the indoor temperature of the building within required comfort limits. To combine the interpretability of white/gray box physics models and the expressive power of neural networks, we propose a physics informed neural network approach for this modeling task. Along with measured data and building parameters, we encode the neural networks with the underlying physics that governs the thermal behavior of these buildings. Thus, realizing a model that is guided by physics, aids in modeling the temporal evolution of room temperature and power consumption as well as the hidden state, i.e., the temperature of building thermal mass for subsequent time steps. The main research contributions of this work are: (1) we propose two variants of physics informed neural network architectures for the task of control-oriented thermal modeling of buildings, (2) we show that training these architectures is data-efficient, requiring less training data compared to conventional, non-physics informed neural networks, and (3) we show that these architectures achieve more accurate predictions than conventional neural networks for longer prediction horizons. We test the prediction performance of the proposed architectures using simulated and real-word data to demonstrate (2) and (3) and show that the proposed physics informed neural network architectures can be used for this control-oriented modeling problem.