TY - GEN
T1 - Practical implementation and evaluation of deep reinforcement learning control for a radiant heating system
AU - Zhang, Zhiang
AU - Lam, Khee Poh
N1 - Publisher Copyright:
© 2018 Copyright held by the owner/author(s).
PY - 2018/11/7
Y1 - 2018/11/7
N2 - Deep reinforcement learning (DRL) has become a popular optimal control method in recent years. This is mainly because DRL has the potential to solve the optimal control problems with complex process dynamics, such as the optimal control for heating, ventilation, and air-conditioning (HVAC) systems. However, DRL control for HVAC systems has not been well studied. There is limited research on the real-life implementation and evaluation of this method. This study implements and deploys a DRL control method for a radiant heating system in a real-life office building for energy efficiency. A physics-based model for the heating system is first created and then calibrated using the measured building operation data. After that, the model is used as a simulator to train the DRL agent. The trained agent is then deployed in the actual heating system, and a smartphone App is used to let the occupants submit their thermal preferences to the DRL agent. It is found the DRL control method can save 16.6% to 18.2% heating demand compared to the old rule-based control logic over the three-month deployment period. However, several limitations of this study are found, such as the low participation rate of the App-based thermal preference feedback system, inefficient DRL training, and the requirement for a large amount of building data.
AB - Deep reinforcement learning (DRL) has become a popular optimal control method in recent years. This is mainly because DRL has the potential to solve the optimal control problems with complex process dynamics, such as the optimal control for heating, ventilation, and air-conditioning (HVAC) systems. However, DRL control for HVAC systems has not been well studied. There is limited research on the real-life implementation and evaluation of this method. This study implements and deploys a DRL control method for a radiant heating system in a real-life office building for energy efficiency. A physics-based model for the heating system is first created and then calibrated using the measured building operation data. After that, the model is used as a simulator to train the DRL agent. The trained agent is then deployed in the actual heating system, and a smartphone App is used to let the occupants submit their thermal preferences to the DRL agent. It is found the DRL control method can save 16.6% to 18.2% heating demand compared to the old rule-based control logic over the three-month deployment period. However, several limitations of this study are found, such as the low participation rate of the App-based thermal preference feedback system, inefficient DRL training, and the requirement for a large amount of building data.
KW - Deep reinforcement learning
KW - Energy efficiency
KW - HVAC control
UR - http://www.scopus.com/inward/record.url?scp=85058371120&partnerID=8YFLogxK
U2 - 10.1145/3276774.3276775
DO - 10.1145/3276774.3276775
M3 - Conference contribution
AN - SCOPUS:85058371120
T3 - BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments
SP - 148
EP - 157
BT - BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments
A2 - Ramachandran, Gowri Sankar
A2 - Batra, Nipun
PB - Association for Computing Machinery, Inc
T2 - 5th ACM International Conference on Systems for Built Environments, BuildSys 2018
Y2 - 7 November 2018 through 8 November 2018
ER -
