Design, simulation and analysis of collaborative strategies in multi-agent systems : the case of supply chain management
|Advisor:||Chaib-draa, Brahim; D'Amours, Sophie|
|Abstract:||A supply chain is a set of companies that manufacture and distribute products to consumers. We study the “bullwhip effect” that is propagated therein by modelling each company as an intelligent agent. This effect is the amplification of the variability of orders placed by companies, as one moves away from end-customers. Firstly, we model each company in a Québec wood supply chain as an intelligent agent, in order to propose two decentralized coordination mechanisms reducing this phenomenon. Simulations of this multi-agent system show that our mechanism is efficient for a supply chain as a whole. Secondly, additional simulations are used to build a game, which we analyze with Game Theory. We verify here that companies have no incentive to cease unilaterally from using our two coordination mechanisms (Nash equilibrium).|
|Document Type:||Thèse de doctorat|
|Open Access Date:||11 April 2018|
|Collection:||Thèses et mémoires|
All documents in CorpusUL are protected by Copyright Act of Canada.