Multi-agent system approach applied to a manufacturer’s supply chain using global objective function and learning concepts

The supply chain efficiency is essential to guarantee the producer competitiveness. As this environment encompasses intelligent actors, it can be model as a multi-agent system. In order to evaluate the interactions, competition, strategies and their consequences in this context, this study aims to analyze the multi-agent system approach applied in a manufacturer’s supply chain, considering a pull production system. Then, this study starts with the literature review about multi-agent systems and its application to supply chain. After, the proposed system is explained, describing its architecture, organization, objectives, negotiation and learning aspects. All the assumptions, individual objective functions and global objective functions are presented in this section. Following, the interactions and implementations aspects are addressed. The negotiation design was inspired in the monotonic concession protocol and the Dutch auctions. The agents learning aspect is broached by the \(\upvarepsilon \)-greedy heuristic. Finally, the experiments design, results and conclusions are presented. The results show the agents’ behavior and the overall system evaluation.