Performance analysis of reinforcement learning algorithms on intelligent closed-loop control on fluid flow and convective heat transfer

• Published in: Physics of fluids (1994) Vol. 35; no. 7
• Main Author: Aubry, Nadine
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 01.07.2023
• Subjects: Algorithms; Closed loops; Convective heat transfer; Cooling; Deep learning; Feasibility studies; Feedback control; Fluid dynamics; Fluid flow; Heat; Machine learning; Optimization; Physics
• ISSN: 1070-6631; 1089-7666
• DOI: 10.1063/5.0158049

This paper investigates the performance of several most popular deep reinforcement learning (DRL) algorithms applied to fluid flow and convective heat transfer systems, providing credible guidance and evaluation on their characteristics and performance. The studied algorithms are selected by considering the popularity, category, and advancement for guaranteeing the significance of the current study. The effectiveness and feasibility of all DRL algorithms are first demonstrated by studying a two-dimensional multi-heat-source cooling problem. Compared with the best manually optimized control, all DRL algorithms can find better control strategies that realize a further temperature reduction of 3–7 K. For problems with complex control objectives and environments, PPO (proximal policy optimization) shows an outstanding performance that accurately and dynamically constrains the oscillation of the solid temperature within 0.5 K around the target value, which is far beyond the capability of the manually optimized control. With the presented performance and the supplemented generalization test, the characteristic and specialty of the DRL algorithms are analyzed. The value-based methods have better training efficiency on simple cooling tasks with linear reward, while the policy-based methods show remarkable convergence on demanding tasks with nonlinear reward. Among the algorithms studied, the single-step PPO and prioritized experience replay deep Q-networks should be highlighted: the former has the advantage of considering multiple control targets and the latter obtains the best result in all generalization testing tasks. In addition, randomly resetting the environment is confirmed to be indispensable for the trained agent executing long-term control, which is strongly recommended to be included in follow-up studies.