Affiliation:
1. National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, China
2. Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
3. School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China
4. Tianjin Key Laboratory for Control Theory & Applications in Complicated Industry Systems, Tianjin 300000, China
Abstract
The central air conditioning system accounts for 50% of the building energy consumption, and the cold source system accounts for more than 60% of the total energy consumption of the central air conditioning system. Therefore, it is crucial to solve the optimal control strategy of the cold source system according to the cooling load demand, and adjust the operating parameters in time to achieve low energy consumption and high efficiency. Due to the complex and changeable characteristics of the central air conditioning system, it is often difficult to achieve ideal results using traditional control methods. In order to solve this problem, this study first coupled the building cooling load simulation environment and the cold source system simulation environment to build a central air conditioning system simulation environment. Secondly, noise interference was introduced to reduce the gap between the simulated environment and the actual environment, and improve the robustness of the environment. Finally, combined with deep reinforcement learning, an optimal control strategy for the central air conditioning system is proposed. Aiming at the simulation environment of the central air conditioning system, a new model-free algorithm is proposed, called the dominant function upper confidence bound deep Q-network (AFUCB-DQN). The algorithm combines the advantages of an advantage function and an upper confidence bound algorithm to balance the relationship between exploration and exploitation, so as to achieve a better control strategy search. Compared with the traditional deep Q-network (DQN) algorithm, double deep Q-network (DDQN) algorithm, and the distributed double deep Q-network (D3QN) algorithm, the AFUCB-DQN algorithm has more stable convergence, faster convergence speed, and higher reward. In this study, significant energy savings of 21.5%, 21.4%, and 22.3% were obtained by conducting experiments at indoor thermal comfort levels of 24 °C, 25 °C, and 26 °C in the summer.
Funder
State Grid Tianjin Electric Power Company Science and Technology Project
Tianjin Postgraduate Scientific Research Innovation Project
Tianjin University of Technology 2022 School-Level Postgraduate Scientific Research Innovation Practice Project
Subject
Process Chemistry and Technology,Chemical Engineering (miscellaneous),Bioengineering