Local and global consensus in asynchronous group communications

Knowledge integration is used more and more often in different theoretical and practical works. It is usually understood as an instantaneous change of knowledge states. In our research we consider integration as a process and study its different elements. Here we focus on using asynchronous communication between agents in a decentralized system. We add a structure of preferred connections and simulate different types of groups. We show that this approach works similar to the classical centralized one, while removing the need for a single critical agent. We also use this approach in a prototype of a weather prediction system to show that the results are similar to obtained with other modes of agent communication.