A dependable system considering interdependence between agents

A multiagent system (MAS) has recently gained public attention as a method to solve competition and cooperation in distributed systems. However, MASs vulnerability due to the propagation of failure prevents from applying to large-scale system. This paper proposes a general composition method to improve its reliability easily applied to existent MASs. The method monitors messages between agents to detect undesirable behaviors such as failure. Collecting the information, the method generates global information of interdependence between agents and expresses it in a graph. This interdependence graph enables us to detect or predict undesirable behaviors. This paper also shows that the method can optimize performance of MAS and improve its reliability under complicated and dynamic environment by applying the global information acquired from the interdependence graph to a replication system.