Abstract: For the distributed flexible job shop scheduling problem considering sequence-dependent setup times, a mixed-integer linear programming model with the optimization objective of minimizing the makespan is proposed. Also, an improved genetic algorithm is developed. A load-balanced population initialization method is used to improve the quality of the initial population. Six local perturbation operators are constructed according to problem characteristics, and a multiple local perturbation strategy is designed to improve the local search capability of the algorithm. Test cases are generated by extending the flexible job shop scheduling benchmark, and the algorithm parameters are determined by orthogonal experiments. Experimental results show that the proposed strategy can effectively improve the performance of the algorithm, with solutions superior to those obtained by the comparison algorithms, thus verifying the feasibility and effectiveness of the scheduling model and the proposed algorithm.

Key words: distributed flexible job shop scheduling, sequence-dependent setup times, genetic algorithm, makespan