Next Article in Journal
Impact of Trade, FDI, and Urbanization on Female Employment System in SAARC: GMM and Quantile Regression Approach
Previous Article in Journal
AI-Based Environmental Color System in Achieving Sustainable Urban Development
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Multi-Agent Optimal Control for Central Chiller Plants Using Reinforcement Learning and Game Theory

1
School of Civil Engineering and Architecture, Zhejiang University of Science and Technology, Hangzhou 310023, China
2
School of Mechanical Engineering, Tongji University, Shanghai 200092, China
3
Department of Construction Management, Louisiana State University, Patrick F. Taylor Hall 3315-D, Baton Rouge, LA 70803, USA
4
School of Design and Fashion, Zhejiang University of Science and Technology, Hangzhou 310023, China
*
Author to whom correspondence should be addressed.
Systems 2023, 11(3), 136; https://doi.org/10.3390/systems11030136
Submission received: 2 February 2023 / Revised: 27 February 2023 / Accepted: 1 March 2023 / Published: 3 March 2023

Abstract

To conserve building energy, optimal operation of a building’s energy systems, especially heating, ventilation and air-conditioning (HVAC) systems, is important. This study focuses on the optimization of the central chiller plant, which accounts for a large portion of the HVAC system’s energy consumption. Classic optimal control methods for central chiller plants are mostly based on system performance models which takes much effort and cost to establish. In addition, inevitable model error could cause control risk to the applied system. To mitigate the model dependency of HVAC optimal control, reinforcement learning (RL) algorithms have been drawing attention in the HVAC control domain due to its model-free feature. Currently, the RL-based optimization of central chiller plants faces several challenges: (1) existing model-free control methods based on RL typically adopt single-agent scheme, which brings high training cost and long training period when optimizing multiple controllable variables for large-scaled systems; (2) multi-agent scheme could overcome the former problem, but it also requires a proper coordination mechanism to harmonize the potential conflicts among all involved RL agents; (3) previous agent coordination frameworks (identified by distributed control or decentralized control) are mainly designed for model-based control methods instead of model-free controllers. To tackle the problems above, this article proposes a multi-agent, model-free optimal control approach for central chiller plants. This approach utilizes game theory and the RL algorithm SARSA for agent coordination and learning, respectively. A data-driven system model is set up using measured field data of a real HVAC system for simulation. The simulation case study results suggest that the energy saving performance (both short- and long-term) of the proposed approach (over 10% in a cooling season compared to the rule-based baseline controller) is close to the classic multi-agent reinforcement learning (MARL) algorithm WoLF-PHC; moreover, the proposed approach’s nature of few pending parameters makes it more feasible and robust for engineering practices than the WoLF-PHC algorithm.
Keywords: central chiller plant; game theory; model-free control; multi-agent reinforcement learning; agent-based control; multi-agent system central chiller plant; game theory; model-free control; multi-agent reinforcement learning; agent-based control; multi-agent system

Share and Cite

MDPI and ACS Style

Qiu, S.; Li, Z.; Pang, Z.; Li, Z.; Tao, Y. Multi-Agent Optimal Control for Central Chiller Plants Using Reinforcement Learning and Game Theory. Systems 2023, 11, 136. https://doi.org/10.3390/systems11030136

AMA Style

Qiu S, Li Z, Pang Z, Li Z, Tao Y. Multi-Agent Optimal Control for Central Chiller Plants Using Reinforcement Learning and Game Theory. Systems. 2023; 11(3):136. https://doi.org/10.3390/systems11030136

Chicago/Turabian Style

Qiu, Shunian, Zhenhai Li, Zhihong Pang, Zhengwei Li, and Yinying Tao. 2023. "Multi-Agent Optimal Control for Central Chiller Plants Using Reinforcement Learning and Game Theory" Systems 11, no. 3: 136. https://doi.org/10.3390/systems11030136

APA Style

Qiu, S., Li, Z., Pang, Z., Li, Z., & Tao, Y. (2023). Multi-Agent Optimal Control for Central Chiller Plants Using Reinforcement Learning and Game Theory. Systems, 11(3), 136. https://doi.org/10.3390/systems11030136

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop