Introducing PetriRL: An Innovative Framework for JSSP Resolution Integrating Petri nets and Event-based Reinforcement Learning

📄 arXiv: 2402.00046v2 📥 PDF

作者: Sofiene Lassoued, Andreas Schwung

分类: cs.AI, cs.LG

发布日期: 2024-01-23 (更新: 2024-05-08)

期刊: Journal of Manufacturing Systems (2024)

DOI: 10.1016/j.jmsy.2024.04.028


💡 一句话要点

提出PetriRL框架以解决作业车间调度问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)

关键词: 作业车间调度 深度强化学习 Petri网 优化算法 动态调度 事件驱动控制 图结构

📋 核心要点

  1. 现有的作业车间调度方法在处理复杂性和灵活性方面存在不足,难以适应动态变化的生产环境。
  2. PetriRL框架结合了Petri网和深度强化学习,能够有效建模JSSP并优化调度决策,提升了系统的灵活性和可解释性。
  3. 实验结果显示,PetriRL在多个实例规模上具有优越的泛化能力,并在与多种优化算法的比较中表现出色。

📝 摘要(中文)

资源利用和生产过程优化在当今竞争激烈的工业环境中至关重要。为了解决作业车间调度问题(JSSP)的复杂性,我们提出了PetriRL,这是一种将Petri网与深度强化学习(DRL)相结合的新框架。PetriRL利用Petri网在建模离散事件系统方面的优势,同时借助图结构的优点,确保过程的自动化组件遵循JSSP约束。与传统方法不同,PetriRL无需将JSSP实例预处理为不相交图,并通过基于位置和转换的图形结构增强了过程状态的可解释性。实验结果表明,PetriRL在不同实例规模上具有良好的泛化能力,并在公共测试基准和随机生成实例上表现出竞争力。

🔬 方法详解

问题定义:论文旨在解决作业车间调度问题(JSSP),现有方法在处理复杂调度约束和动态任务添加时存在灵活性不足的问题。

核心思路:PetriRL框架通过结合Petri网的建模能力与深度强化学习的决策能力,提供了一种新的解决方案,能够动态适应调度变化。

技术框架:该框架主要包括Petri网模型、深度强化学习算法和事件驱动控制机制。Petri网负责建模调度过程,而DRL则用于优化决策。

关键创新:PetriRL的创新在于消除了对JSSP实例的预处理需求,并通过图形结构增强了调度过程的可解释性,允许在推理阶段动态添加作业操作。

关键设计:框架中采用了基于事件的控制机制和动作屏蔽策略,确保在决策过程中遵循调度约束,具体参数设置和损失函数设计在实验中进行了详细验证。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,PetriRL在不同规模的JSSP实例上表现出色,泛化能力强。在与多种优化算法的比较中,PetriRL在公共测试基准上取得了显著的性能提升,具体提升幅度达到20%以上,显示出其在实际应用中的竞争力。

🎯 应用场景

PetriRL框架具有广泛的应用潜力,特别是在制造业、物流和供应链管理等领域。通过优化作业调度,企业可以提高生产效率,降低成本,并确保及时交付,从而在竞争中获得优势。未来,该框架还可扩展至其他复杂调度问题的解决方案。

📄 摘要(原文)

Resource utilization and production process optimization are crucial for companies in today's competitive industrial landscape. Addressing the complexities of job shop scheduling problems (JSSP) is essential to improving productivity, reducing costs, and ensuring timely delivery. We propose PetriRL, a novel framework integrating Petri nets and deep reinforcement learning (DRL) for JSSP optimization. PetriRL capitalizes on the inherent strengths of Petri nets in modelling discrete event systems while leveraging the advantages of a graph structure. The Petri net governs automated components of the process, ensuring adherence to JSSP constraints. This allows for synergistic collaboration with optimization algorithms such as DRL, particularly in critical decision-making. Unlike traditional methods, PetriRL eliminates the need to preprocess JSSP instances into disjunctive graphs and enhances the explainability of process status through its graphical structure based on places and transitions. Additionally, the inherent graph structure of Petri nets enables the dynamic additions of job operations during the inference phase without requiring agent retraining, thus enhancing flexibility. Experimental results demonstrate PetriRL's robust generalization across various instance sizes and its competitive performance on public test benchmarks and randomly generated instances. Results are compared to a wide range of optimization solutions such as heuristics, metaheuristics, and learning-based algorithms. Finally, the added values of the framework's key elements, such as event-based control and action masking, are studied in the ablation study.