The Integrated Supply Chain Management Project

Enterprise Integration Laboratory
Department of Industrial Engineering, University of Toronto
4 Taddle Creek Road, Toronto, Ontario M5S 1A4
tel: +1-416-978-6823; fax: +1-416-971-2479;

The supply chain of a manufacturing enterprise is a world-wide network of suppliers, factories, warehouses, distribution centres and retailers through which raw materials are acquired, transformed and delivered to customers. In order to optimize performance, supply chain functions must operate in a coordinated manner. But the dynamics of the enterprise and the market make this difficult: bank rates change overnignt, political situations change, materials do not arrive on time, production facilities fail, workers are ill, customers change or cancel orders, etc. causing deviations from plan. In some cases, these events may be dealt with locally, i.e. they lie within the scope of a supply chain function. In other cases, the problem can not be "locally contained" and modifications across many functions are required.

Consequently, the supply chain management system must coordinate the revision of plans/schedules across supply chain functions. The agility with which the supply chain is managed at the tactical and operational levels in order to enable timely dissemina tion 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.


Our research addresses coordination problems at the tactical and operational levels. It organizes the supply chain as a network of cooperating, intelligent agents, each performing one or more supply chain functions, and each coordinating their actions with other agents. Our focus is in supporting the construction of supply chain intelli gent agent systems in a manner that guarantees that agents use the best communication, coordination and prob lem solving mechanisms available with minimal programming effort on the developers' side.

We achieve this goal


All above technology is currently in place. The TOVE virtual enterprise provides the unified testbed used by the agents we built for the major supply chain functions: Logistics, Transportation Management, Order Acquisition, Resource Management, Scheduling and Dispatching. These agents rely on ontologies for activity, state, time, resources, cost, quality and organization as a common vocabulary for communication and use the services of Information Agents that automatically distribute information and manage information consistency and evolution.

We have developed a unified theory of constraint-based scheduling and used it to build the Scheduling and other agents. Finally, theories of coordination as constraint relaxation have been developed and are being incorporated into agents.

On-going work

We are now developing a Generic Agent Shell that will support agent construction in a more principled way, pro viding several layers of reusable services and languages. They are concerned with Purpose built application programs can make use of this agent architecture to enhance their problem solving and to improve their robustness through coordination with other agent based applications. Pre-existing (legacy) application programs can also be incorporated with little adaption and can experience similar benefits. This latter point is important because in many cases developing the entire application afresh would be considered too expensive or too large a change away from proven technology.


We collaborate with Numetrix Limited, a major provider of supply chain products and with the Technical Uni versity of Berlin. Numetrix is working closely with us in both requirements analysis and specification of agent and architecture functionality. They will incorporate our ideas in their next generation of products. With the Technical University of Berlin we work closely to design and develop the Generic Agent Shell architecture that will support agent development.



For information about the management of the ISCM project, click here (but access restrictions apply)


EIL Homepage