The supply chain is a network of suppliers, factories, warehouses, distribution centres and retail-ers through which raw materials are acquired, transformed and delivered to the customer. Supplychain management is the strategic, tactical and operational level decision making that optimises supply chain performance. The strategic level defines the supply chain network, i.e., selection of suppliers, transportation routes, manufacturing facilities, production levels, warehouses, etc. The tactical level plans and schedules the supply chain to meet actual demand. The operational level executes plans. Tactical and operational level decision making functions are distributed across the supply chain.
In order to optimise performance, supply chain functions must operate in an integrated manner. But the dynamics of the enterprise and the market make this difficult; materials do not arrive ontime, 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 function. In other cases, the problem cannot be “locally contained”; modifications across many functions are required. Consequently, the supply chain management system must coordinate the revision of plans/schedules across supply chain functions.
The Integrated Supply Chain Management (ISCM) project addresses coordination problems at the tactical and operational levels. It is composed of a set of cooperating, intelligent agents, each per-forming one or more supply chain functions, and coodinating their decisions with other agents -this is called a Logistical Execution System (LES). The focus of our research is on the develop-ment of 1) a theory of coordination that allows agents to cooperatively manage change, 2) a theory of agent problem-solving that enables agents to cooperate with other agents in their exploration of solutions, and reason in an “anytime” manner, and 3) a theory of agency and support tools that enable users to build multi-agent systems with minimal programming effort, based on trusted reusable components.
Our approach views problem-solving as a constraint satisfaction/optimisation process where agents influence each other’s problem solving behaviour through the communication of con- straints. Coordination occurs when agents develop plans that satisfy their own internal constraints but also the constraints of other agents. Negotiation occurs when constraints, that cannot be satis-fied, are modified by the subset of agents directly concerned. One of the main thrusts of this research is to investigate the use of constraints, their specification and relaxation (i.e., modifica-tion), as a means of coordination and negotitation. The recent advent of the Internet and WWW as infrastructures for global connectivity has confirmed the distributed multi-agent orientation of the project and has allowed us to develop new Internet agent technologies that can aptly support the global integration and management of the supply chain.
The objectives of the project are to:
- Develop a sharable representation of supply chain knowledge.
- Identify an appropriate decomposition of supply chain functions and encapsulate into agents.
- Develop an incremental, “anytime” model of problem solving for each functional agent so that it can provide rapid responses to unplanned for events.
- Extend each function oriented agent so that it is able to answer more questions within its functional domain.
- Investigate the issues of agent oriented programming and agent architectures and their application to agent oriented manufacturing systems that can operate distributedly and cooperatively over global networks.
- Develop protocols, strategies and tools for the: communication of information, coordination of decisions, and management of change within multi-agent environments.