Self-synchronization of cooperative agents in a distributed environment

Multiagent systems have been widely used in applications that are inherently distributed such as information retrieval, network diagnosis, and distributed vehicle monitoring. The use of multiple cooperative agents offers some important advantages (such as parallelism, robustness and scalability) for those applications. However, the synchronization of those multiple agents is an important challenge, specially when they are executing on different computers. In this paper we present a formal description of a mechanism based on deadline commitments to synchronize agents in a distributed application. In our proposal, agents synchronize themselves reacting to changes in the environment. The proposal considers a loose coupling among agents with the goal of maintaining the autonomy and independency of the involved agents.