Green flexible job-shop scheduling considering transportation time and machine multi-rotation speeds

Abstract

This paper tackles, for the first time, a Green Flexible Job-Shop Scheduling Problem simultaneously considering Automated Guided Vehicle (AGV) transportation time and multi-rotation-speed machines under multi-objective optimization. Such an integrated setting, rarely addressed in existing studies, poses new challenges due to the tight coupling between transportation, processing speed decisions, and energy–time trade-offs. To solve this complex problem, we propose a novel Dueling Double Deep Q-Network (D3QN)-based scheduling framework with a hierarchical action space. By embedding expert-designed dispatching rules into four sub-decision layers (job, machine, speed, AGV), the framework drastically reduces action dimensionality and improves convergence and generalization. A layered reward mechanism is further designed to balance makespan and energy consumption, while a vectorized state representation enables adaptive decision-making in dynamic environments. Extensive simulations and real-world case studies show that the proposed approach achieves up to 18.6% energy savings and notable scheduling efficiency improvements over benchmark algorithms.