Concepts and Algorithms for Agent-based Decentralized and Integrated Scheduling of Production and Auxiliary Processes

TL;DR

This paper proposes an agent-based decentralized scheduling approach for production systems that integrates multiple processes, scales linearly with system size, and is applicable across various factory organizations, addressing Industry 4.0 needs.

Contribution

It introduces a scalable, integrated scheduling method using multi-agent systems suitable for large, complex production networks with diverse organizational structures.

Findings

Scheduling execution time scales linearly with system size

The approach effectively manages interdependencies between processes

Concurrent negotiation capabilities are validated

Abstract

Individualized products and shorter product life cycles have driven companies to rethink traditional mass production. New concepts like Industry 4.0 foster the advent of decentralized production control and distribution of information. A promising technology for realizing such scenarios are Multi-agent systems. This contribution analyses the requirements for an agent-based decentralized and integrated scheduling approach. Part of the requirements is to develop a linearly scaling communication architecture, as the communication between the agents is a major driver of the scheduling execution time. The approach schedules production, transportation, buffering and shared resource operations such as tools in an integrated manner to account for interdependencies between them. Part of the logistics requirements reflect constraints for large workpieces such as buffer scarcity. The approach aims at providing a general solution that is also applicable to large system sizes that, for example, can be found in production networks with multiple companies. Further, it is applicable for different kinds of factory organization (flow shop, job shop etc.). The approach is explained using an example based on industrial requirements. Experiments have been conducted to evaluate the scheduling execution time. The results show the approach's linear scaling behavior. Also, analyses of the concurrent negotiation ability are conducted.