Learning Automata Based-AODV Routing Protocol for Inter-vehicle Communication: A Simulation Approach

The Ad-hoc On-Demand Distance Vector (AODV) routing protocol is a Mobile Ad-hoc Network (MANET) routing protocol that is experimentally used in Vehicular Ad-hoc Networks (VANETs) to support Vehicle-to-Vehicle (V2V) communication. Unfortunately, the standard AODV can lead to degraded responsiveness due to excessive information flow in the VANET environment. The research proposed a Learning Automata-based AODV (LA-AODV) that integrates reinforcement learning for enhanced relay node selection and communication responsiveness in VANET. By considering real-time vehicle parameters during relay node selection, LA-AODV optimizes Quality of Service (QoS) and indirectly reduces road incidents. Simulation results using Network Simulator 3 (NS-3) in a grid traffic scenario demonstrate and validate that LA-AODV outperforms AODV regarding Packet Delivery Ratio (PDR), average end-to-end delay, throughput, and communication overhead. Using Learning Automata for relay node selection in LA-AODV improves the QoS of V2V communication, making it suitable for applications in smart transportation and intelligent vehicle networks supported with V2V communication in each vehicle. This research contributes to the field by improving the AODV protocol for V2V communication, especially in VANET research