Q-learning-based hyper-heuristic evolutionary algorithm for the distributed assembly blocking flowshop scheduling problem

Abstract

Distributed shop scheduling problems (DSSPs) have attracted increasing interest in recent years due to the technical trends of smart manufacturing and Industry 4.0. The distributed assembly blocking flowshop scheduling problem (DABFSP) is a critical class of DSSPs with widespread applications in modern supply chains and manufacturing systems. In this paper, a Q-learning-based hyper-heuristic evolutionary algorithm (QLHHEA) is proposed to solve DABFSP with the objective of minimizing the makespan. Firstly, a mathematical model of DABFSP is formulated, and two insertion-based speedup strategies are devised to conserve the computational cost of evaluating solutions and to accelerate the search efficiency. Secondly, a problem-specific constructive heuristic is developed to produce high-quality initial solutions. Thirdly, twelve efficient heuristics are designed to construct low-level heuristics (LLHs). The Q-learning-based evolutionary algorithm is applied as a high-level strategy to manipulate the LLHs, which are then executed in order to search the solution space. Moreover, suitable solution encoding and decoding schemes are provided to produce feasible scheduling schedules. The design of experiments is implemented to investigate the impact of the parameters. Finally, a comprehensive comparison campaign is carried out based on a total of 1710 well-known instances to evaluate the efficacy of the proposed algorithm against several state-of-the-art algorithms. Experimental results and statistical analysis show that QLHHEA significantly outperforms the existing algorithms by a significant margin, demonstrating the effectiveness and efficiency of QLHHEA in solving DABFSP.