An Enhanced Reinforcement Routing Protocol for Inter-Vehicular Unicast Application

C. Wu and T. Kato (Japan)

Keywords

VANET, routing protocol, AODV, and QLearning

Abstract

In Vehicular Ad-Hoc Network (VANET), as a result of frequent changes of network topology caused by vehi cle’s movement, the general purpose ad hoc routing pro tocols such as AODV and DSR cannot work efficiently. This paper proposed a VANET routing protocol QLAODV which fits for unicast application in high mobility scenario. QLAODV is a distributed reinforcement learning routing protocol, which uses Q-Learning algorithm to infer net work state information and uses unicast control packets checking the availability of paths in a real time manner in order to allow Q-Learning to work efficiently in highly dy namic network environment. In this paper, we show the performance analysis of QLAODV by simulation with NS2 in different mobility models, and give the simulation results confirming that QLAODV outperforms original AODV sig nificantly in highly dynamic networks.

Important Links:



Go Back