Energy-saving distributed flexible job-shop scheduling with fuzzy processing time in IIoT: A novel evolutionary multitasking algorithm

Abstract

With the rapid development of Industrial Internet of Things (IIoT), the complexity of production environment has increased significantly. The flexible job-shop scheduling problem (FJSP) is often framed as a multi-objective optimization issue. However, as the scale and computational demands continue to grow, traditional multi-objective algorithms struggle to identify optimal scheduling policies. To address this challenge, we designed a novel evolutionary multitasking (EMT) framework to handle the complexity of FJSP in IIoT scenarios, considering uncertainty in time constraints through fuzzy processing time. Existing studies do not consider FJSP in IIoT scenario, our study fulfills this research gap. The energy-saving distributed FJSP with fuzzy processing time in IIoT (EFDFJSP) was studied, aiming to simultaneously optimize makespan and energy consumption. The problem was modeled as a multi-task multi-objective EFDFJSP (MMEFDFJSP) for the first time. And we proposed a novel reinforcement learning (RL)-based multi-task multi-objective algorithm with feedback mechanism (EMTRL-FD). Additionally, we proposed a local search (LS) operator selection strategy to efficiently allocate computing resources. Experimental results demonstrate that EMTRL-FD outperforms existing state-of-the-art algorithms in solving EFDFJSP.