REVOLUTIONIZING VANETS WITH GRAPH NEURAL NETWORKS USING DYNAMIC TRAFFIC MANAGEMENT

ICTACT Journal on Communication Technology ( Volume: 15 , Issue: 2 )

Abstract

The increasing movement from rural areas to urban areas, along with the widening gap in population, has resulted in metropolitan areas becoming extremely overpopulated. As a result of the high volume of traffic that occurs in these areas, traffic monitoring is an extremely important activity. According to the findings of this study, an improved authentication and communication protocol that is based on clusters could be implemented for Intelligent Transportation Systems in Vehicular Ad Hoc Networks (VANETs). Our number one objective is to enhance the sharing of resources amongst vehicles through improved communication. Cluster-based routing protocols allowed us to increase the scalability, stability, and dependability of fast-moving VANETs. This was accomplished in the context of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. To easing concerns regarding privacy and safety, we arranged for the vehicles to be certified by an independent contractor. Through the utilization of Graph Neural Networks (GNNs), we can reduce the number of instances in which links fail, as well as minimize end-to-end (E2E) delays and route requests. Our approach has resulted in several important benefits, including enhancements to throughput, reductions in the amount of time required for TCP socket initialization, acceleration of TCP handshake response, and DNS lookup. Short-range peer-to-peer wireless communication is the focus of the protocols that are used within a cluster that is 400 meters in radius. Utilizing new peer-to-peer wireless communications over VANET is what is meant by the term resource-conserving in this context. Within the framework of the suggested protocol secure authentication method, a certifying authority is responsible for the generation of a secure authentication key for the vehicle, which is subsequently provided to the vehicle.

Authors

M. Umaselvi1, S. Leena Maria2, M.J. Sridevi3, B. Gayathri4, Khaled A. A. Alloush5
P.A. College of Engineering and Technology, India1, Government Engineering College, Hassan, India2, Government First Grade College for Women, India3, Bishop Heber College, India4, Arab Open University, Saudi Arabia5

Keywords

VANETs, V2V, Graph Neural Network, TCP

Published By
ICTACT
Published In
ICTACT Journal on Communication Technology
( Volume: 15 , Issue: 2 )
Date of Publication
June 2024
Pages
3217 - 3222

ICT Academy is an initiative of the Government of India in collaboration with the state Governments and Industries. ICT Academy is a not-for-profit society, the first of its kind pioneer venture under the Public-Private-Partnership (PPP) model

Contact Us

ICT Academy
Module No E6 -03, 6th floor Block - E
IIT Madras Research Park
Kanagam Road, Taramani,
Chennai 600 113,
Tamil Nadu, India

For Journal Subscription: journalsales@ictacademy.in

For further Queries and Assistance, write to us at: ictacademy.journal@ictacademy.in