Abstract

This thesis is related to distributed decision making and collaboration within a supply chain context. Mainly, we focus on unexpected swings in demand and on unexpected exceptions (problem of production, problem of transportation, etc.), which are important coordination and communication issues in supply chain management. Supply chain is a distributed environment. Therefore, we apply an agent-based distributed architecture in order to guarantee the autonomy and the strategic data confidentiality of all participants. Agent technology provides to the distributed environment a great promise of effective communication. An agent is a program that performs a specific task intelligently without any human supervision and can communicate with other agents cooperatively.

After a critical review on supply chain activities and their management and multi-agent systems, we propose a model based on agents and interactions. This model aims at modeling many supply chains structures. To represent the three main functions of the company (source, make and deliver) and consider the control processes in the supply chain and its environment, each actor is modeled by the fourth agents (App, Fab, Liv and AgentSCM). These collaborative agents communicate between them and negotiate using protocols. They collect strategies from managers; seek the accurate data and aim at building a rule-base for better coordination and better decision-making process.

The usefulness of the model and the distributed architecture has been validated on an industrial case study (distribution company). The aforementioned company operates in the sectors of toilets and showers (washbasin, baths, etc.), taps, tiling, plumbing and pieces of furniture. Also, a simulation concerns CPFR process is performed in order to evaluate its benefit.

Keywords: Multi-agent systems, Negotiation Protocols, Supply Chain Management, Demand uncertainty, Distributed and Proactive Simulation, Agent UML, Rush unexpected order.