Edge-Based V2X communications with big data intelligence

Siri Guleng, Celimuge Wu, Zhi Liu, Xianfu Chen

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Vehicular Internet-of-Things applications require an efficient Vehicle-to-Everything (V2X) communication scheme. However, it is particularly challenging to achieve a high throughput and low latency with limited wireless resources in highly dynamic vehicular networks. In this article, we propose a scheme that enhances V2V communications through integration of vehicle edge-based forwarding and learning-based edge selection policy optimization. The proposed scheme has three main characteristics. First, the Hierarchical edge-based preemptive route creation is introduced to create hierarchical edges and conduct efficient packet forwarding as well as route aggregation. Second, Two-stage learning is introduced to select efficient edge nodes using big data driven traffic prediction and reinforcement learning-based edge node selection. Third, Context-aware edge selection is employed to improve the performance of edge-based forwarding in various contexts. We use real traffic big data and realistic vehicular network simulations to evaluate the performance of the proposed scheme and show the advantage over other baseline approaches.

Original languageEnglish
Article number8951087
Pages (from-to)8603-8613
Number of pages11
JournalIEEE Access
Volume8
DOIs
Publication statusPublished - 1 Jan 2020
MoE publication typeA1 Journal article-refereed

Fingerprint

Communication
Reinforcement learning
Agglomeration
Throughput
Big data
Internet of things

Keywords

  • Edge computing
  • traffic big data
  • V2X communications
  • vehicular ad hoc networks

Cite this

Guleng, Siri ; Wu, Celimuge ; Liu, Zhi ; Chen, Xianfu. / Edge-Based V2X communications with big data intelligence. In: IEEE Access. 2020 ; Vol. 8. pp. 8603-8613.
@article{ee9fce9719d04c70aaa99984ef312006,
title = "Edge-Based V2X communications with big data intelligence",
abstract = "Vehicular Internet-of-Things applications require an efficient Vehicle-to-Everything (V2X) communication scheme. However, it is particularly challenging to achieve a high throughput and low latency with limited wireless resources in highly dynamic vehicular networks. In this article, we propose a scheme that enhances V2V communications through integration of vehicle edge-based forwarding and learning-based edge selection policy optimization. The proposed scheme has three main characteristics. First, the Hierarchical edge-based preemptive route creation is introduced to create hierarchical edges and conduct efficient packet forwarding as well as route aggregation. Second, Two-stage learning is introduced to select efficient edge nodes using big data driven traffic prediction and reinforcement learning-based edge node selection. Third, Context-aware edge selection is employed to improve the performance of edge-based forwarding in various contexts. We use real traffic big data and realistic vehicular network simulations to evaluate the performance of the proposed scheme and show the advantage over other baseline approaches.",
keywords = "Edge computing, traffic big data, V2X communications, vehicular ad hoc networks",
author = "Siri Guleng and Celimuge Wu and Zhi Liu and Xianfu Chen",
year = "2020",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2020.2964707",
language = "English",
volume = "8",
pages = "8603--8613",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE Institute of Electrical and Electronic Engineers",

}

Edge-Based V2X communications with big data intelligence. / Guleng, Siri; Wu, Celimuge; Liu, Zhi; Chen, Xianfu.

In: IEEE Access, Vol. 8, 8951087, 01.01.2020, p. 8603-8613.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Edge-Based V2X communications with big data intelligence

AU - Guleng, Siri

AU - Wu, Celimuge

AU - Liu, Zhi

AU - Chen, Xianfu

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Vehicular Internet-of-Things applications require an efficient Vehicle-to-Everything (V2X) communication scheme. However, it is particularly challenging to achieve a high throughput and low latency with limited wireless resources in highly dynamic vehicular networks. In this article, we propose a scheme that enhances V2V communications through integration of vehicle edge-based forwarding and learning-based edge selection policy optimization. The proposed scheme has three main characteristics. First, the Hierarchical edge-based preemptive route creation is introduced to create hierarchical edges and conduct efficient packet forwarding as well as route aggregation. Second, Two-stage learning is introduced to select efficient edge nodes using big data driven traffic prediction and reinforcement learning-based edge node selection. Third, Context-aware edge selection is employed to improve the performance of edge-based forwarding in various contexts. We use real traffic big data and realistic vehicular network simulations to evaluate the performance of the proposed scheme and show the advantage over other baseline approaches.

AB - Vehicular Internet-of-Things applications require an efficient Vehicle-to-Everything (V2X) communication scheme. However, it is particularly challenging to achieve a high throughput and low latency with limited wireless resources in highly dynamic vehicular networks. In this article, we propose a scheme that enhances V2V communications through integration of vehicle edge-based forwarding and learning-based edge selection policy optimization. The proposed scheme has three main characteristics. First, the Hierarchical edge-based preemptive route creation is introduced to create hierarchical edges and conduct efficient packet forwarding as well as route aggregation. Second, Two-stage learning is introduced to select efficient edge nodes using big data driven traffic prediction and reinforcement learning-based edge node selection. Third, Context-aware edge selection is employed to improve the performance of edge-based forwarding in various contexts. We use real traffic big data and realistic vehicular network simulations to evaluate the performance of the proposed scheme and show the advantage over other baseline approaches.

KW - Edge computing

KW - traffic big data

KW - V2X communications

KW - vehicular ad hoc networks

UR - http://www.scopus.com/inward/record.url?scp=85078277738&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2020.2964707

DO - 10.1109/ACCESS.2020.2964707

M3 - Article

AN - SCOPUS:85078277738

VL - 8

SP - 8603

EP - 8613

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8951087

ER -