TY - GEN
T1 - Comparative analysis of model-free and model-based HVAC control for residential demand response
AU - Kurte, Kuldeep
AU - Amasyali, Kadir
AU - Munk, Jeffrey
AU - Zandi, Helia
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/11/17
Y1 - 2021/11/17
N2 - In this paper, we present a comparative analysis of model-free reinforcement learning (RL) and model predictive control (MPC) approaches for intelligent control of heating, ventilation, and air-conditioning (HVAC). Deep-Q-network (DQN) is used as a candidate for model-free RL algorithm. The two control strategies were developed for residential demand-response (DR) HVAC system. We considered MPC as our golden standard to compare DQN's performance. The question we tried to answer through this work was, What % of MPC's performance can be achieved by model-free RL approach for intelligent HVAC control?. Based on our test result, RL achieved an average of ≈ 62% daily cost saving of MPC. Considering the pure optimization and model-based nature of MPC methods, the RL showed very promising performance. We believe that the interpretations derived from this comparative analysis provide useful insights to choose from various DR approaches and further enhance the performance of the RL-based methods for building energy managements.
AB - In this paper, we present a comparative analysis of model-free reinforcement learning (RL) and model predictive control (MPC) approaches for intelligent control of heating, ventilation, and air-conditioning (HVAC). Deep-Q-network (DQN) is used as a candidate for model-free RL algorithm. The two control strategies were developed for residential demand-response (DR) HVAC system. We considered MPC as our golden standard to compare DQN's performance. The question we tried to answer through this work was, What % of MPC's performance can be achieved by model-free RL approach for intelligent HVAC control?. Based on our test result, RL achieved an average of ≈ 62% daily cost saving of MPC. Considering the pure optimization and model-based nature of MPC methods, the RL showed very promising performance. We believe that the interpretations derived from this comparative analysis provide useful insights to choose from various DR approaches and further enhance the performance of the RL-based methods for building energy managements.
KW - building energy
KW - deep reinforcement learning
KW - demand response
KW - intelligent HVAC control
KW - model predictive control
UR - http://www.scopus.com/inward/record.url?scp=85120995796&partnerID=8YFLogxK
U2 - 10.1145/3486611.3488727
DO - 10.1145/3486611.3488727
M3 - Conference contribution
AN - SCOPUS:85120995796
T3 - BuildSys 2021 - Proceedings of the 2021 ACM International Conference on Systems for Energy-Efficient Built Environments
SP - 309
EP - 313
BT - BuildSys 2021 - Proceedings of the 2021 ACM International Conference on Systems for Energy-Efficient Built Environments
PB - Association for Computing Machinery, Inc
T2 - 8th ACM International Conference on Systems for Energy-Efficient Built Environments, BuildSys 2021
Y2 - 17 November 2021 through 18 November 2021
ER -