INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
A network with reliable and rapid communication is critical for urban Vehicular Ad Hoc Networks (VANETs). VANETs consisting of vehicular nodes moving on the roads with wireless communication. However, the highly dynamic topology of VANETs and limited communication of performance have brought great challenges to the routing design of VANETs. It is difficult for existing routing protocols for VANETs to adapt the high dynamics of VANETs. Moreover, few of existing routing protocols simultaneously meet the requirement of high packet delivery and low delay in Intelligent Transportation Systems (ITSs). This paper proposes a novel Q-learning based routing algorithm under next-hop selection optimization of geographic routing protocol. To adopt the decision making on the next-hop selection algorithms, an off-policy algorithm as it learns an optimal action maximize Q value based on a reward function that estimates a link reliability between nodes in the routing decision process to select the more reliable next-hop. The performance of the proposed routing approach is evaluated using comprehensive network simulation. Simulation results show that the proposed algorithm can provide higher packet arrival ratio, lower delay than existing routing protocols.
Keywords:
Vehicular Ad-hoc Networks; Q-learning Routing; Link Reliability; Geographic Routing
Cite Article:
"Q-Learning Based Routing Algorithm for Urban Vehicular Networks", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 6, page no.140 - 144, June-2023, Available :http://www.ijsdr.org/papers/IJSDR2306024.pdf
Downloads:
000337351
Publication Details:
Published Paper ID: IJSDR2306024
Registration ID:206994
Published In: Volume 8 Issue 6, June-2023
DOI (Digital Object Identifier):
Page No: 140 - 144
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn