Toward a Society Oriented Approach for Fault Handling in Multi-Agent Systems

Fault handling/tolerance is important and remains a challenging problem in multi agents systems (MAS). The majority of existed distributed fault tolerant MAS are suffering from a robust solution for incomplete and uncertain situations. This paper proposes a novel society oriented approach for effectively handling the faults in dynamic situations with a high possibility of uncertainty. In this approach, the emerged implicit learning inspired by the concepts of stock market has considerably improved the fault tolerant ability. The experimental results illustrate the effectiveness of the presented approach in comparison to the case of central controller, the case of using purely redundant components, and helping without using a social value.