• Corpus ID: 244908748

Physically Consistent Neural Networks for building thermal modeling: theory and analysis

  title={Physically Consistent Neural Networks for building thermal modeling: theory and analysis},
  author={Loris Di Natale and Bratislav Svetozarevic and Philipp Heer and Colin Neil Jones},
Due to their high energy intensity, buildings play a major role in the current worldwide energy transition. Building models are ubiquitous since they are needed at each stage of the life of buildings, i.e. for design, retrofitting, and control operations. Classical white-box models, based on physical equations, are bound to follow the laws of physics but the specific design of their underlying structure might hinder their expressiveness and hence their accuracy. On the other hand, black-box… 
Physics Informed Neural Networks for Control Oriented Thermal Modeling of Buildings
Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control
Physically Consistent Neural Networks (PCNNs) are used as simulation environments, for which optimal control inputs are easy to compute, and results hint that DRL agents not only clearly outperform conventional rule-based controllers, they furthermore attain near-optimal performance.
Experimental Data-Driven Model Predictive Control of a Hospital HVAC System During Regular Use
A multi-zone, heating, ventilation and air-conditioning (HVAC) control case study of an industrial plant responsible for cooling a hospital surgery center is reported, based on a statistical non-parametric, non-linear regression technique named Gaussian processes.


Physics-constrained Deep Learning of Multi-zone Building Thermal Dynamics
Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling
A framework to learn dynamics models from trajectory data while incorporating a-priori system knowledge as inductive bias is developed and learns to predict the system dynamics two orders of magnitude more accurately than a baseline approach that does not include prior knowledge, given the same training dataset.
Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling
A novel framework, termed as physics-guided neural network (PGNN), leverages the output of physics-based model simulations along with observational features to generate predictions using a neural network architecture to ensure better generalizability as well as physical consistency of results.
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
The proposed DeLaN network can learn the equations of motion of a mechanical system with a deep network efficiently while ensuring physical plausibility and exhibits substantially improved and more robust extrapolation to novel trajectories and learns online in real-time.