An autonomous multi‐agent approach to supply chain event management

An autonomous multi‐agent approach to supply chain event management

0.00 Avg rating0 Votes
Article ID: iaor201110620
Volume: 135
Issue: 1
Start Page Number: 468
End Page Number: 478
Publication Date: Jan 2012
Journal: International Journal of Production Economics
Authors: , ,
Keywords: management
Abstract:

Organizations have made a significant effort to implement software for planning and scheduling, but disruptive event management is still a problem to be solved. Since a disruptive event can affect the overall performance of the supply chain, SCEM (Supply Chain Event Management) systems presenting different automation levels such as monitoring, alarm and decision support have been proposed. However, the management of disruptive events, taking into account the distributed nature of the supply chain, the members' autonomy and the ability to exert corrective control actions, has been identified as a problem that requires further research. This work presents an agent‐based approach for the SCEM problem, which can perform autonomous corrective control actions to minimize the effect of deviations in the plan that is currently being executed. These control actions consist of a distribution of the variation between supply chain members, using the plan's slack in a collaborative way. An innovative feature of this approach is its focus on resources, which are affected by disruptive events in a direct way. Based on this approach, a SCEM system is designed as a net of control points defined on resources connected through supply process orders. Two novel aspects are the distributed collaborative inter‐organizational architecture of the SCEM system and a Double Contract Net Protocol. This protocol allows a set of resource:representing agents to interact through an agent, representing a supply process order as a mediator. An application to a case study of the Multi‐Agent SCEM system implemented with JADE is provided.

Reviews

Required fields are marked *. Your email address will not be published.