An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning

Celimuge Wu, Xianfu Chen, Yusheng Ji, Satoshi Ohzahata, Toshihiko Kato

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

9 Citations (Scopus)

Abstract

Designing an efficient multi-hop broadcast protocol is very important for the realization of collision avoidance systems and other many interesting applications in vehicular ad hoc networks (VANETs). Existing protocols are optimized for a specific scenario, and are not capable of working in various scenarios. Therefore, designing an intelligent protocol which can tune itself in relation to the change of network environment is particularly important. In this paper, we propose a broadcast protocol which is able to make forwarding decision based on a self-learning mechanism. The protocol employs a fuzzy logic-based relay node selection approach to take into account multiple metrics for the forwarding algorithm. The parameters used for the fuzzy logic are tuned online using a reinforcement learning approach. Transfer learning is used to transfer knowledge to new arriving vehicles (agents) in order to shorten the convergence time. The combination of reinforcement learning, transfer learning and fuzzy logic can provide an intelligent solution for broadcasting in VANETs. We conduct computer simulations to evaluate the proposed protocol.
Original languageEnglish
Title of host publicationVehicular Technology Conference (VTC Spring), 2015 IEEE 81st
Pages1-6
ISBN (Electronic)978-1-4799-8088-8
DOIs
Publication statusPublished - 2015
MoE publication typeA4 Article in a conference publication
Event81st Vehicular Technology Conference, VTC2015-Spring: VTC2015-Spring - Glasgow, Scotland, United Kingdom
Duration: 11 May 201514 May 2015
Conference number: 81

Publication series

Name
ISSN (Print)1550-2252

Conference

Conference81st Vehicular Technology Conference, VTC2015-Spring
CountryUnited Kingdom
CityGlasgow, Scotland
Period11/05/1514/05/15

Fingerprint

Vehicular ad hoc networks
Network protocols
Fuzzy logic
Reinforcement learning
Collision avoidance
Broadcasting
Computer simulation

Cite this

Wu, C., Chen, X., Ji, Y., Ohzahata, S., & Kato, T. (2015). An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning. In Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st (pp. 1-6) https://doi.org/10.1109/VTCSpring.2015.7145689
Wu, Celimuge ; Chen, Xianfu ; Ji, Yusheng ; Ohzahata, Satoshi ; Kato, Toshihiko. / An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning. Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st. 2015. pp. 1-6
@inproceedings{697daf19275a47418d727f034d8b67eb,
title = "An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning",
abstract = "Designing an efficient multi-hop broadcast protocol is very important for the realization of collision avoidance systems and other many interesting applications in vehicular ad hoc networks (VANETs). Existing protocols are optimized for a specific scenario, and are not capable of working in various scenarios. Therefore, designing an intelligent protocol which can tune itself in relation to the change of network environment is particularly important. In this paper, we propose a broadcast protocol which is able to make forwarding decision based on a self-learning mechanism. The protocol employs a fuzzy logic-based relay node selection approach to take into account multiple metrics for the forwarding algorithm. The parameters used for the fuzzy logic are tuned online using a reinforcement learning approach. Transfer learning is used to transfer knowledge to new arriving vehicles (agents) in order to shorten the convergence time. The combination of reinforcement learning, transfer learning and fuzzy logic can provide an intelligent solution for broadcasting in VANETs. We conduct computer simulations to evaluate the proposed protocol.",
author = "Celimuge Wu and Xianfu Chen and Yusheng Ji and Satoshi Ohzahata and Toshihiko Kato",
note = "Project : 101914",
year = "2015",
doi = "10.1109/VTCSpring.2015.7145689",
language = "English",
isbn = "978-1-4799-8089-5",
pages = "1--6",
booktitle = "Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st",

}

Wu, C, Chen, X, Ji, Y, Ohzahata, S & Kato, T 2015, An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning. in Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st. pp. 1-6, 81st Vehicular Technology Conference, VTC2015-Spring, Glasgow, Scotland, United Kingdom, 11/05/15. https://doi.org/10.1109/VTCSpring.2015.7145689

An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning. / Wu, Celimuge; Chen, Xianfu; Ji, Yusheng; Ohzahata, Satoshi; Kato, Toshihiko.

Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st. 2015. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning

AU - Wu, Celimuge

AU - Chen, Xianfu

AU - Ji, Yusheng

AU - Ohzahata, Satoshi

AU - Kato, Toshihiko

N1 - Project : 101914

PY - 2015

Y1 - 2015

N2 - Designing an efficient multi-hop broadcast protocol is very important for the realization of collision avoidance systems and other many interesting applications in vehicular ad hoc networks (VANETs). Existing protocols are optimized for a specific scenario, and are not capable of working in various scenarios. Therefore, designing an intelligent protocol which can tune itself in relation to the change of network environment is particularly important. In this paper, we propose a broadcast protocol which is able to make forwarding decision based on a self-learning mechanism. The protocol employs a fuzzy logic-based relay node selection approach to take into account multiple metrics for the forwarding algorithm. The parameters used for the fuzzy logic are tuned online using a reinforcement learning approach. Transfer learning is used to transfer knowledge to new arriving vehicles (agents) in order to shorten the convergence time. The combination of reinforcement learning, transfer learning and fuzzy logic can provide an intelligent solution for broadcasting in VANETs. We conduct computer simulations to evaluate the proposed protocol.

AB - Designing an efficient multi-hop broadcast protocol is very important for the realization of collision avoidance systems and other many interesting applications in vehicular ad hoc networks (VANETs). Existing protocols are optimized for a specific scenario, and are not capable of working in various scenarios. Therefore, designing an intelligent protocol which can tune itself in relation to the change of network environment is particularly important. In this paper, we propose a broadcast protocol which is able to make forwarding decision based on a self-learning mechanism. The protocol employs a fuzzy logic-based relay node selection approach to take into account multiple metrics for the forwarding algorithm. The parameters used for the fuzzy logic are tuned online using a reinforcement learning approach. Transfer learning is used to transfer knowledge to new arriving vehicles (agents) in order to shorten the convergence time. The combination of reinforcement learning, transfer learning and fuzzy logic can provide an intelligent solution for broadcasting in VANETs. We conduct computer simulations to evaluate the proposed protocol.

U2 - 10.1109/VTCSpring.2015.7145689

DO - 10.1109/VTCSpring.2015.7145689

M3 - Conference article in proceedings

SN - 978-1-4799-8089-5

SP - 1

EP - 6

BT - Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st

ER -

Wu C, Chen X, Ji Y, Ohzahata S, Kato T. An Intelligent Broadcast Protocol for VANETs Based on Transfer Learning. In Vehicular Technology Conference (VTC Spring), 2015 IEEE 81st. 2015. p. 1-6 https://doi.org/10.1109/VTCSpring.2015.7145689