Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments

Yu Pu, Fang Li () and Shahin Rahimifard
Additional contact information
Yu Pu: School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
Fang Li: School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
Shahin Rahimifard: School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University, Loughborough LE11 3TU, UK

Sustainability, 2024, vol. 16, issue 8, 1-26

Abstract: In response to the challenges of dynamic adaptability, real-time interactivity, and dynamic optimization posed by the application of existing deep reinforcement learning algorithms in solving complex scheduling problems, this study proposes a novel approach using graph neural networks and deep reinforcement learning to complete the task of job shop scheduling. A distributed multi-agent scheduling architecture (DMASA) is constructed to maximize global rewards, modeling the intelligent manufacturing job shop scheduling problem as a sequential decision problem represented by graphs and using a Graph Embedding–Heterogeneous Graph Neural Network (GE-HetGNN) to encode state nodes and map them to the optimal scheduling strategy, including machine matching and process selection strategies. Finally, an actor–critic architecture-based multi-agent proximal policy optimization algorithm is employed to train the network and optimize the decision-making process. Experimental results demonstrate that the proposed framework exhibits generalizability, outperforms commonly used scheduling rules and RL-based scheduling methods on benchmarks, shows better stability than single-agent scheduling architectures, and breaks through the instance-size constraint, making it suitable for large-scale problems. We verified the feasibility of our proposed method in a specific experimental environment. The experimental results demonstrate that our research can achieve formal modeling and mapping with specific physical processing workshops, which aligns more closely with real-world green scheduling issues and makes it easier for subsequent researchers to integrate algorithms with actual environments.

Keywords: multi-agent proximal policy optimization; job shop scheduling problem; graph neural network; green scheduling (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/16/8/3234/pdf (application/pdf)
https://www.mdpi.com/2071-1050/16/8/3234/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:16:y:2024:i:8:p:3234-:d:1374658

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().