Sustainable scheduling within the manufacturing field has garnered substantial attention from both academia and industry. The escalating market demands have heightened requirements on the flexibility of production modes, multi-zone, and multi-objective. In this context, our study explores the intricacies of the multi-objective distributed flow shop group scheduling problem with sequence-dependent setup times, aiming to concurrently optimize makespan and total energy consumption (DFm|group, sdst|#(Cmax, TEC) ). Firstly, a mathematical model is constructed to analyze problem characteristics. Subsequently, we introduce a collaborative multi-objective evolutionary algorithm driven by indicators (CMOEA/I). In CMOEA/I, an indicator-driven approach is proposed for solution selection, which approximates the Pareto front based on the convergence indicator, while screening potential solutions based on the spread indicator. Furthermore, a collaborative model and local search are developed by incorporating the intrinsic linkages of factories, groups, and jobs. Additionally, to further explore the potential non-dominated solutions, a speed variation strategy is devised based on the pivots of decreasing speed to save energy and increasing speed to reduce makespan. An extensive set of simulation experiments is conducted on a diverse range of test instances. Through meticulous statistical analysis, the outcomes demonstrate that the CMOEA/I exhibits efficacy when contrasted with other advanced algorithms.

Amid the global push for sustainable development, rising market demands have necessitated a multiregional, multiobjective, and flexible production model. Against this backdrop, this article investigates the multiobjective distributed flow shop group scheduling problem by formulating a mathematical model and introducing an advanced memetic algorithm integrated with reinforcement learning (RLMA). The RLMA involves a novel cooperative crossover operation in conjunction with the nature of the coupled problems to extensively explore the solution space. Additionally, the Sarsa algorithm enhanced with eligibility traces guides the selection of optimal schemes during the local enhancement phase. To ensure a balance between convergence and diversity, a solution selection strategy based on penalty-based boundary intersection decomposition is utilized. Furthermore, the increasing-efficiency and reducing-consumption strategies integrating a rapid evaluation mechanism are designed by dynamically changing the machine speed to balance economic and sustainability metrics. Comprehensive numerical experiments and comparative analyses demonstrate that the proposed RLMA surpasses existing state-of-the-art algorithms in addressing this complex problem.

Energy conservation, emission reduction, and green and low carbon are of great significance to sustainable development, and are also the theme of the transformation and upgrading of the manufacturing industry. This paper concentrates on studying the energy-efficient hybrid flowshop scheduling problem with consistent sublots (HFSP_ECS) with the objective of minimizing the energy consumption. To solve the problem, the HFSP_ECS is decomposed by the idea of “divide-and-conquer”, resulting in three coupled subproblems, i.e., lot sequence, machine assignment, and lot split, which can be solved by using a cooperative methodology. Thus, an improved cooperative coevolutionary algorithm (vCCEA) is proposed by integrating the variable neighborhood descent (VND) strategy. In the vCCEA, considering the problem-specific characteristics, a two-layer encoding strategy is designed to represent the essential information, and a novel collaborative model is proposed to realize the interaction between subproblems. In addition, special neighborhood structures are designed for different subproblems, and two kinds of enhanced neighborhood structures are proposed to search for potential promising solutions. A collaborative population restart mechanism is established to ensure the population diversity. The computational results show that vCCEA can coordinate and solve each subproblem of HFSP_ECS effectively, and outperform the mathematical programming and the other state-of-the-art algorithms.