Application of AI techniques to adaptive routing in wide-area networks

Adaptive decentralized routing in wide-area networks is characterized by all nodes making routing decisions based on their current view of the status of remote nodes. Unfortunately, each node's view can be, and usually is, different, especially when the network is very large. The authors introduce the idea of cooperating intelligent agents, embedded within nodes, which infer the states of remote nodes using all relevant local information including knowledge of past behavior, to reduce explicit communication of remote status information.<
>