Deflection routing in complex networks

Abstract

Deflection routing is a viable contention resolution scheme in bufferless network architectures where contention is the main source of information loss. In recent years, various reinforcement learning-based deflection routing algorithms have been proposed. However, performance of these algorithms has not been evaluated in larger networks that resemble the autonomous system-level view of the Internet. In this Chapter, we compare performance of three reinforcement learning-based deflection routing algorithms by using the National Science Foundation network topology and topologies generated using Waxman and Barabási-Albert algorithms. We examine the scalability of these deflection routing algorithms by increasing the network size while keeping the network load constant.