A Data-Driven Modeling and Control Framework for Physics-Based Building Emulators

01/31/2023

∙

We present a data-driven modeling and control framework for physics-based building emulators. Our approach comprises: (a) Offline training of differentiable surrogate models that speed up model evaluations, provide cheap gradients, and have good predictive accuracy for the receding horizon in Model Predictive Control (MPC) and (b) Formulating and solving nonlinear building HVAC MPC problems. We extensively verify the modeling and control performance using multiple surrogate models and optimization frameworks for different available test cases in the Building Optimization Testing Framework (BOPTEST). The framework is compatible with other modeling techniques and customizable with different control formulations. The modularity makes the approach future-proof for test cases currently in development for physics-based building emulators and provides a path toward prototyping predictive controllers in large buildings.

READ FULL TEXT

A Data-Driven Modeling and Control Framework for Physics-Based Building Emulators

NeurOpt: Neural network based optimization for building energy management and climate control

Deep Learning Explicit Differentiable Predictive Control Laws for Buildings

State space models for building control: how deep should you go?

Lessons Learned from Data-Driven Building Control Experiments: Contrasting Gaussian Process-based MPC, Bilevel DeePC, and Deep Reinforcement Learning

Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling

Physics-informed linear regression is a competitive approach compared to Machine Learning methods in building MPC

MFNets: Learning network representations for multifidelity surrogate modeling

A Data-Driven Modeling and Control Framework for Physics-Based Building Emulators

Related Research

NeurOpt: Neural network based optimization for building energy management and climate control

Deep Learning Explicit Differentiable Predictive Control Laws for Buildings

State space models for building control: how deep should you go?

Lessons Learned from Data-Driven Building Control Experiments: Contrasting Gaussian Process-based MPC, Bilevel DeePC, and Deep Reinforcement Learning

Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling

Physics-informed linear regression is a competitive approach compared to Machine Learning methods in building MPC

MFNets: Learning network representations for multifidelity surrogate modeling