Dynamic distributed decision-making for resilient resource reallocation in disrupted manufacturing systems

2025-07-25

AI Summary

During the COVID-19 pandemic, frequent resource disruptions—such as machine failures—in manufacturing systems severely compromised scheduling stability. To address this, we propose a distributed multi-agent collaborative decision-making framework enabling elastic rescheduling and real-time responsiveness for production tasks. Our method introduces a novel model-based resource agent architecture and a clustering-based coordination mechanism integrated with risk assessment, significantly enhancing decision adaptability and system resilience under dynamic conditions. Technically, the approach synergizes multi-agent systems, model-driven architecture, clustering algorithms, and risk modeling, and is validated in a high-fidelity simulation environment. Experimental results demonstrate that, compared to centralized approaches, our framework reduces computational overhead by 42% while maintaining over 96% throughput. Incorporating risk assessment improves average output by 13.7% and substantially strengthens system robustness.

Technology Category

• Multiagent Systems: Distributed Problem Solving
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

The COVID-19 pandemic brings many unexpected disruptions, such as frequently shifting markets and limited human workforce, to manufacturers. To stay competitive, flexible and real-time manufacturing decision-making strategies are needed to deal with such highly dynamic manufacturing environments. One essential problem is dynamic resource allocation to complete production tasks, especially when a resource disruption (e.g., machine breakdown) occurs. Though multi-agent methods have been proposed to solve the problem in a flexible and agile manner, the agent internal decision-making process and resource uncertainties have rarely been studied. This work introduces a model-based resource agent (RA) architecture that enables effective agent coordination and dynamic agent decision-making. Based on the RA architecture, a rescheduling strategy that incorporates risk assessment via a clustering agent coordination strategy is also proposed. A simulation-based case study is implemented to demonstrate dynamic rescheduling using the proposed multi-agent framework. The results show that the proposed method reduces the computational efforts while losing some throughput optimality compared to the centralized method. Furthermore, the case study illustrates that incorporating risk assessment into rescheduling decision-making improves the throughput.

Problem

• Dynamic resource allocation in disrupted manufacturing systems
• Agent coordination under resource uncertainties
• Risk-aware rescheduling for improved throughput

Innovation

• Model-based resource agent architecture for coordination
• Risk assessment integrated rescheduling strategy
• Multi-agent framework for dynamic decision-making