Nondominated sorting genetic algorithm-II with Q-learning for the distributed permutation flowshop rescheduling problem

Abstract

The distributed permutation flowshop problem (DPFSP) has been extensively studied in recent years. However, most of the research has overlooked the disturbance factors in the processing environment, such as the arrival of new jobs. To address this issue, a nondominated sorting genetic algorithm-II (NSGA-II) with Q-learning has been developed. First, an iterated greedy algorithm (IG) is proposed to generate an initial solution for the first stage. Then, the NSGA-II algorithm is designed to optimize dual-objective problems in the second stage, and the Q-learning algorithm is used to adjust the algorithm parameters. Next, two local search strategies based on key factories are adopted, including critical factory-based insert and swap operations. Finally, a comprehensive experiment of the proposed algorithm against other advanced multiobjective algorithms is conducted. The results confirm that the proposed algorithm can solve the distributed permutation flowshop rescheduling problem with high efficiency.