A Multi-Agent System for Supply Chain Management MIHAELA ULIERU, DOUGLAS NORRIE, WEIMING SHEN Mechanical and Manufacturing Engineering Department The University of Calgary 2500 University Drive NWCalgary, Alberta, T2N 1N4 CANADA Abstract: In today’s globalization of manufacturing operations managing the supply chain has become an extremely challenging task as it implies tracking order fulfillment, due dates and billing between partners working at different time-zones, with different currencies, tax systems and way to represent information. To achieve on-line control over the status of an order receipt/delivery in a global manufacturing environment the only possibility is to use latest network technologies for accessing and exchanging electronic information. Latest research in distributed artificial intelligence offers excellent tools for modeling the interactions between different nodes of the supply-chain network. This paper presents a multi-agent system approach to the design of global supply chain management networks. The main advantages of this system in unifying heterogeneous information and offering easy tractability for the manager are illustrated on a particular implementation. Keywords: supply chain management, multi-agent systems, electronic information Proc.pp..3901-3906 1 Introduction The supply chain of a manufacturing enterprise can be regarded as a world-wide network of suppliers, factories, warehouses, distribution centers, and retailers through which raw materials are acquired, transformed and delivered to customers. Supply chain management is the decision- making process that optimizes supply chain performance [1]. In today's competitive business environment industry is recognizing the importance of efficient supply chain management. The major challenge of a supply chain is in coordinating activities across different organizations. The agility with which the supply chain is managed at the tactical and operational levels in order to enable timely dissemination of information, accurate coordination of decisions and management of actions among people and systems, is what will ultimately determine the efficient, coordinated achievement of enterprise goals. While much effort has already been invested in the development of agent technology for manufacturing applications [2], little has been done on the supply chain as a whole. The most extensive research explorations on this topic have been done in Canada at the University of Toronto [3]. They used agents to encapsulate existing software systems in order to integrate manufacturing activities with those of their suppliers, customers and partners. In our approach the supply chain is regarded as a set of entities and processes. Entities may be suppliers, plants, distribution centers, customers, etc. or it may be internal departments such as sales, planning, purchasing, materials, or research and development. A process is simply a series of actions. Entities will be modeled as