Adaptive routing based on predictive reinforcement learning

Abstract

In this paper, optimized reinforcement learning-based adaptive network routing is investigated. Shortest path routing is most suitable network routing algorithm for wired network but not suitable for any wireless network. In high traffic conditions, shortest path will always select the shortest path (in terms of number of hops) between source and destination thus generating more congestion. The proposed method optimized reinforcement-based routing algorithm is based on predictive mechanism, where the path is selected on demand. It means, path is selected based on the actual traffic present on the network. Thus, they guarantee the least delivery time to reach the packets to the destination. Simulation and Analysis are done on periodic and non-periodic traffic and delivery time is used as an estimation parameter.

Keywords:

• Ad hoc network
• mobile ad hoc network (MANET)
• confidence-based routing (CBQ)
• dual reinforcement Q routing(DRQ)
• Q routing (QR)