TY - GEN
T1 - Containerized framework for building control performance comparisons
T2 - 8th ACM International Conference on Systems for Energy-Efficient Built Environments, BuildSys 2021
AU - Fu, Yangyang
AU - Xu, Shichao
AU - Zhu, Qi
AU - O'Neill, Zheng
N1 - Funding Information:
The research reported in this paper was supported by the Building Technologies Office at the U.S. Department of Energy through the Emerging Technologies program under award number DE-EE0009150.
Publisher Copyright:
© 2021 ACM.
PY - 2021/11/17
Y1 - 2021/11/17
N2 - While both model predictive control (MPC) and deep reinforcement learning control (DRL) have shown significant energy cost savings for building systems, there is a lack of in-depth quantitative study on the comparison between the two. One major obstacle is the lack of a holistic evaluation environment for the building community and the control community to integrate their expertise in studying both model-based and learning-based control methods. To address this challenge, this paper presents a scalable containerized software framework for building control performance comparisons, with a special focus on enabling both optimal model-based control and deep learning-based control. The framework provides a standardized building environment for the control community to benchmark different advanced control strategies, and a flexible software architecture for the building community to standardize their own customized building environments. A preliminary performance comparison of MPC and DRL on a single zone building is performed in the case study. Both MPC and DRL can outperform the rule-based baseline controllers in terms of reducing energy cost and maintaining thermal discomfort. DRL can outperform MPC after a long training time with a predefined reward policy.
AB - While both model predictive control (MPC) and deep reinforcement learning control (DRL) have shown significant energy cost savings for building systems, there is a lack of in-depth quantitative study on the comparison between the two. One major obstacle is the lack of a holistic evaluation environment for the building community and the control community to integrate their expertise in studying both model-based and learning-based control methods. To address this challenge, this paper presents a scalable containerized software framework for building control performance comparisons, with a special focus on enabling both optimal model-based control and deep learning-based control. The framework provides a standardized building environment for the control community to benchmark different advanced control strategies, and a flexible software architecture for the building community to standardize their own customized building environments. A preliminary performance comparison of MPC and DRL on a single zone building is performed in the case study. Both MPC and DRL can outperform the rule-based baseline controllers in terms of reducing energy cost and maintaining thermal discomfort. DRL can outperform MPC after a long training time with a predefined reward policy.
KW - OpenAI-Gym
KW - building energy and control system
KW - deep reinforcement learning
KW - model predictive control
UR - http://www.scopus.com/inward/record.url?scp=85120959688&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85120959688&partnerID=8YFLogxK
U2 - 10.1145/3486611.3492412
DO - 10.1145/3486611.3492412
M3 - Conference contribution
AN - SCOPUS:85120959688
T3 - BuildSys 2021 - Proceedings of the 2021 ACM International Conference on Systems for Energy-Efficient Built Environments
SP - 276
EP - 280
BT - BuildSys 2021 - Proceedings of the 2021 ACM International Conference on Systems for Energy-Efficient Built Environments
PB - Association for Computing Machinery, Inc
Y2 - 17 November 2021 through 18 November 2021
ER -