Logistics-involved QoS-aware service composition in cloud manufacturing with deep reinforcement learning

Cloud manufacturing is a new manufacturing model that aims to provide on-demand manufacturing services to consumers over the Internet. Service composition is an essential issue as well as an important technique in cloud manufacturing (CMfg) that supports construction of larger-granularity, value-added services by combining a number of smaller-granularity services to satisfy consumers' complex requirements. Meta-heuristics algorithms such as genetic algorithm, particle swarm optimization, and ant colony algorithm are frequently employed for addressing service composition issues in cloud manufacturing. These algorithms, however, require complex design flows and painstaking parameter tuning, and lack adaptability to dynamic environment. Deep re-inforcement learning (DRL) provides an alternative approach for solving cloud manufacturing service compo-sition (CMfg-SC) issues. DRL as model-free artificial intelligent methods enables a system to learn optimal service composition solutions through training, which can therefore circumvent the aforementioned problems with meta-heuristics algorithms. This paper is dedicated to exploring possible applications of DRL in CMfg-SC. A logistics-involved QoS-aware DRL-based CMfg-SC is proposed. A dueling Deep Q-Network (DQN) with prior-itized replay named PD-DQN is designed as the DRL algorithm. Effectiveness, robustness, adaptability, and scalability of PD-DQN are investigated, and compared with that of the basic DQN and Q-learning. Experimental results indicate that PD-DQN is able to effectively address the CMfg-SC problem.

Automated summary

Cloud manufacturing is a new manufacturing model that provides on-demand manufacturing services, with service composition being a crucial issue. Deep reinforcement learning (DRL) offers a promising alternative for addressing service composition problems in cloud manufacturing. The effectiveness of PD-DQN algorithm in solving CMfg-SC issues is demonstrated through experimental results.