Wave refrigeration control via deep reinforcement learning

Abstract Wave refrigerating technology is a new type of refrigerating technology that performs more efficiently and is more environmentally friendly. Nowadays, the commonly used control method is the PID control method. However, although the above control methods are simple in structure, they have the problems of difficult parameter tuning, large overshoot, and unstable and inaccurate output response. Therefore, to improve the above problems, we propose a framework of deep reinforcement learning-based wave refrigerating control system. An improved SAC algorithm is used to learn the control system. The evaluation method is established according to the working condition requirements as well as the safety requirements in the operation process. Experiments show that this method can effectively improve the control efficiency as well as the control quality, which can make the control system operate stably.