Environment-Adaptive Multiple Access for Distributed V2X Network: A Reinforcement Learning Framework

Seungmo Kim, Byung Jun Kim, B. Brian Park

Research output: Contribution to book or proceedingConference articlepeer-review

13 Scopus citations

Abstract

The huge research interest in cellular vehicle-to-everything (C-V2X) communications in recent days is attributed to their ability to schedule multiple access more efficiently as compared to its predecessor technology, i.e., dedicated short-range communications (DSRC). However, one of the foremost issues still remaining is the need for the V2X to operate stably in a highly dynamic environment. This paper proposes a way to exploit the dynamicity. That is, we propose a resource allocation mechanism adaptive to the environment, which can be an efficient solution for air interface congestion that a V2X network often suffers from. Specifically, the proposed mechanism aims at granting a higher chance of transmission to a vehicle with a higher crash risk. As such, the channel access is prioritized to those with urgent needs. The proposed framework is established based on reinforcement learning (RL), which is modeled as a contextual multi-armed bandit (MAB). Importantly, the framework is designed to operate at a vehicle autonomously without any assistance from a central entity, which, henceforth, is expected to make a particular fit to distributed V2X network such as C-V2X mode 4.

Original languageEnglish
Title of host publication2021 IEEE 93rd Vehicular Technology Conference, VTC 2021-Spring - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728189642
DOIs
StatePublished - Apr 2021
EventIEEE Vehicular Technology Conference - Virtual, Online
Duration: Apr 25 2021Apr 28 2021
Conference number: 93
https://ieeexplore.ieee.org/xpl/conhome/9448628/proceeding (Link to proceedings)

Publication series

NameIEEE Vehicular Technology Conference
Volume2021-April
ISSN (Print)1550-2252

Conference

ConferenceIEEE Vehicular Technology Conference
Abbreviated titleVTC
CityVirtual, Online
Period04/25/2104/28/21
Internet address

Scopus Subject Areas

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics

Keywords

  • C-V2X
  • Connected vehicles
  • Intelligent transportation system
  • Multi-armed bandit
  • NR-V2X mode 4
  • PC5
  • Reinforcement learning
  • Sidelink

Fingerprint

Dive into the research topics of 'Environment-Adaptive Multiple Access for Distributed V2X Network: A Reinforcement Learning Framework'. Together they form a unique fingerprint.

Cite this