A negotiation-based Multi-agent System for Supply Chain Management

This paper describes an ongoing effort in developing a Multiagent System (MAS) for supply chain management. In our framework, functional agents can join in, stay, or leave the system. The Supply Chain Management System (SCMS) functionality is implemented through agent-based negotiation. When an order arrives, a virtual supply chain may emerge from the system through automated or semi-automated negotiation processes between functional agents. We present our framework and describe a number of negotiation performatives, which can be used to construct pair-wise and third party negotiation protocols for functional agent cooperation. We also explain how to formally model the negotiation process by using Colored Petri Nets (CPN) and we provide an example of establishing a virtual chain by solving a distributed constraint satisfaction problem.

[1]  Mark S. Fox,et al.  The Information Agent: an infrastructure agent supporting collaborative enterprise architectures , 1994, Proceedings of 3rd IEEE Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises.

[2]  Makoto Yokoo,et al.  The Distributed Constraint Satisfaction Problem: Formalization and Algorithms , 1998, IEEE Trans. Knowl. Data Eng..

[3]  Manuela M. Veloso,et al.  Multiagent Systems: A Survey from a Machine Learning Perspective , 2000, Auton. Robots.