Loughborough University
Browse

File(s) under embargo

Reason: Publisher requirement.

9

month(s)

19

day(s)

until file(s) become available

PRVC: A novel vehicular ad-hoc network caching based on pre-trained reinforcement learning

conference contribution
posted on 2024-05-01, 15:34 authored by Ziyang ZhangZiyang Zhang, Lin GuanLin Guan, Yuanchen LiYuanchen Li, Seth Johnson, Qinggang MengQinggang Meng

In recent years, network caching in Vehicular Ad-hoc Network (VANET) has gained significant interest, with particular interest around high mobility nodes. Traditional methods, based on Mobile Ad-hoc Network (MANET) caching, face limitations due to MANET’s computational constraints and struggle to effectively address VANET-specific caching needs, leading to subpar performance. Addressing this, this paper introduces the novel Vehicular Ad-hoc Network Caching Method based on Pre-trained Reinforcement Learning (PRVC). This new approach uses pretrained reinforcement learning to enhance VANET caching Quality of Service (QoS) and adapt to changing cache interests. Our empirical experiments show that PRVC outperforms benchmarks in cache hit rate, latency, and link load.

History

School

  • Science

Department

  • Computer Science

Published in

Proceedings of the 38th International Conference on Advanced Information Networking and Applications (AINA-2024)

Volume

1

Pages

43–54

Source

The 38th International Conference on Advanced Information Networking and Applications (AINA-2024)

Publisher

Springer

Version

  • AM (Accepted Manuscript)

Rights holder

© The Author(s), under exclusive license to Springer Nature Switzerland AG

Publisher statement

This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-57840-3_5. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms

Acceptance date

2024-01-18

Publication date

2024-04-11

Copyright date

2024

ISBN

9783031578397; 9783031578403

Book series

Lecture Notes on Data Engineering and Communications Technologies

Language

  • en

Editor(s)

Leonard Barolli

Location

Kitakyushu, Japan

Event dates

17th April 2024 - 19th April 2024

Depositor

Ziyang Zhang. Deposit date: 26 April 2024

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC