A Review of Multi-objective Green Flexible Job Shop Scheduling Based on Intelligent Optimization Algorithms

Abstract

The flexible job shop scheduling problem (FJSP) is a representative and complex optimization problem in production scheduling because it simultaneously involves operation sequencing and machine assignment. With the rapid development of green manufacturing and intelligent manufacturing, research on FJSP has gradually shifted from traditional efficiency-oriented objectives, such as makespan and machine utilization, toward multi-objective green optimization that considers energy consumption, carbon emissions, energy cost, processing cost, and resource balance. From the perspective of industrial engineering and management, this paper reviews recent studies on multi-objective green flexible job shop scheduling. First, it clarifies the basic characteristics and research evolution of FJSP. Second, it summarizes the main research progress from three aspects: green objective modeling, realistic constraint scenarios, and intelligent optimization algorithms. Third, it evaluates the applicability of genetic algorithms, NSGA-II, memetic algorithms, hybrid metaheuristics, and deep reinforcement learning. Finally, it identifies current limitations in green indicator systems, model realism, algorithm interpretability, and engineering implementation, and proposes future research directions. The review indicates that multi-objective green FJSP has moved beyond the stage of simply comparing algorithmic performance and is increasingly becoming a comprehensive optimization problem for complex manufacturing systems. Future research should strengthen systematic modeling of green objectives, dynamic scenario representation, and integration with real enterprise production systems.