Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments
Sustainability · 12.04.2024 · 16 (8) · 3234
DOI: 10.3390/su16083234 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sustainability, online erschienen am 12.04.2024. Verfasst von Yu Pu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Guangdong Province, Guangzhou Science and Technology Plan Project, National Key R&D Project.
Abstract (Originalsprache)
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.
Förderung
- Natural Science Foundation of Guangdong Province
- Guangzhou Science and Technology Plan Project
- National Key R&D Project
- Open Project Fund of the Key Laboratory of Big Data and Intelligent Robot of the Ministry of Education
Zitieren
APA
Pu, Y., Li, F., & Rahimifard, S. (2024). Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments. Sustainability, 16(8), 3234. https://doi.org/10.3390/su16083234
Vancouver
Pu Y, Li F, Rahimifard S. Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments. Sustainability. 2024;16(8):3234. doi:10.3390/su16083234
BibTeX
@article{Pu2024,
author = {Pu, Yu and Li, Fang and Rahimifard, Shahin},
title = {Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments},
journal = {Sustainability},
year = {2024},
volume = {16},
number = {8},
pages = {3234},
doi = {10.3390/su16083234}
}
EUVIMED