A study on modeling vehicles mobility with MLC for enhancing vehicle-to-vehicle connectivity in VANET

In Vehicular ad hoc networks (VANETs), vehicle-to-vehicle (V2V) is a significant mode of communication in which vehicles communicate with other moving vehicles with the aid of wireless transceivers. Due to the rapid mobility of vehicles, network connectivity over VANETs is frequently unstable, especially in sparse highways. This paper analyzes V2V connectivity dynamics by designing the microscopic mobility and lane changing decision model using an adaptive cursive control mechanism and recurrent neural network. Extensive simulators like SUMO and NS2 analyze the validity of this proposed model. The proposed analytical model provides a framework for examining the impact of mobility dependent metrics such as vehicle velocity, acceleration/deceleration, safety gap, vehicle arrival rate, vehicle density and network metric data delivery rate for characterizing the VANET connectivity of the proposed network. The simulation results synchronized those of the proposed model, which illustrated that the developed analytical model of this work is effective.