Skip to content

Qiuzhuang/learning-building-control

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

69 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

From Model-Based to Model-Free: Learning Building Control for Demand Response

Description

This repository encompasses the source code and data to reproduce and extend results for a manuscript that compares demand responsive control schemes for multi-zone buildings. It includes examples of model predictive control (MPC and MPC-C), value function approximation via CVXPYLAYERS (MPC-CL), differentiable predictive control (DPC) and reinforcement learning control (RLC). The goal of the study is to evaluate state-of-the-art controllers and establish the efficacy (if any) of learning-based approaches that leverage deep neural networks in one way or another.

Please refer to our preprint on arXiv for more details.

Basic installation instructions

Env setup using platform-dependent yaml file:

conda env create -n <env-name> -f env-xxxx.yaml
pip install -e .

Citation

If citing this work, please use the following:

@article{biagioni2022lbc,
  title={From Model-Based to Model-Free: Learning Building Control for Demand Response},
  author={Biagioni, David and Zhang, Xiangyu and Adcock, Christiane and Sinner, Michael and Graf, Peter and King, Jennifer},
  journal={arXiv preprint arXiv:2210.10203},
  year={2022}
}

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 76.8%
  • Python 22.5%
  • Shell 0.7%