A Learning-Based Discrete Jaya Algorithm for Multiobjective Sustainable Distributed Blocking Flow Shop Scheduling Problem with Heterogeneous Factories

The sustainable scheduling of distributed manufacturing has received considerable attention from manufacturing researchers in developing sustainable manufacturing. The multi-objective sustainable distributed blocking flow shop scheduling problem with heterogeneous factories (HFMS-DBFSP) is studied in this paper. The model of the HFMS-DBFSP is proposed considering the three goals of total tardiness, total carbon emission, and negative social impact. A learning-based discrete Jaya algorithm (LDJaya) is presented to address the HFMS-DBFSP. The cooperative initialization method based on the characteristics of the HFMS-DBFSP is designed for population initialization. The self-learning operation selection strategy is introduced to guide the selection of operations, and local search operators are proposed to keep the population diverse. The carbon saving speed adjustment strategy is proposed to lower carbon emissions still further. The effectiveness of each of the strategies in the LDJaya is validated and benchmarked within the benchmark suite against the state-of-the-art algorithms. The simulation results of the experiment prove that the designed LDJaya is superior to other comparative algorithms in significance and efficiency in resolving the HFMS-DBFSP.