A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems

Mimi Chen; Jiajun Chen; Xiaojing Chen; Shunqing Zhang; Shugong Xu

doi:10.1109/WCNC.2019.8886105

A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems

Mimi Chen, Jiajun Chen, Xiaojing Chen, Shunqing Zhang, Shugong Xu

Shanghai University

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

18 Citations (Scopus)

Abstract

In vehicular communications, intracell interference and the stringent latency requirement are challenging issues. In this paper, a joint spectrum reuse and power allocation problem is formulated for hybrid vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Recognizing the high capacity and low-latency requirements for V2I and V2V links, respectively, we aim to maximize the weighted sum of the capacities and latency requirement. By decomposing the original problem into a classification subproblem and a regression subproblem, a convolutional neural network (CNN) based approach is developed to obtain real-time decisions on spectrum reuse and power allocation. Numerical results further demonstrate that the proposed CNN can achieve similar performance as the Exhaustive method, while needs only 3.62% of its CPU runtime.

Original language	English
Title of host publication	2019 IEEE Wireless Communications and Networking Conference, WCNC 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538676462
DOIs	https://doi.org/10.1109/WCNC.2019.8886105
Publication status	Published - Apr 2019
Externally published	Yes
Event	2019 IEEE Wireless Communications and Networking Conference, WCNC 2019 - Marrakesh, Morocco Duration: 15 Apr 2019 → 19 Apr 2019

Publication series

Name	IEEE Wireless Communications and Networking Conference, WCNC
Volume	2019-April
ISSN (Print)	1525-3511

Conference

Conference	2019 IEEE Wireless Communications and Networking Conference, WCNC 2019
Country/Territory	Morocco
City	Marrakesh
Period	15/04/19 → 19/04/19

Keywords

deep neural networks
Resource allocation
spectrum reuse
vehicular communications

Access to Document

10.1109/WCNC.2019.8886105

Cite this

Chen, M., Chen, J., Chen, X., Zhang, S., & Xu, S. (2019). A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems. In 2019 IEEE Wireless Communications and Networking Conference, WCNC 2019 Article 8886105 (IEEE Wireless Communications and Networking Conference, WCNC; Vol. 2019-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WCNC.2019.8886105

@inproceedings{6d680db5c4be4e458ec5d1133d8a271b,

title = "A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems",

abstract = "In vehicular communications, intracell interference and the stringent latency requirement are challenging issues. In this paper, a joint spectrum reuse and power allocation problem is formulated for hybrid vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Recognizing the high capacity and low-latency requirements for V2I and V2V links, respectively, we aim to maximize the weighted sum of the capacities and latency requirement. By decomposing the original problem into a classification subproblem and a regression subproblem, a convolutional neural network (CNN) based approach is developed to obtain real-time decisions on spectrum reuse and power allocation. Numerical results further demonstrate that the proposed CNN can achieve similar performance as the Exhaustive method, while needs only 3.62% of its CPU runtime.",

keywords = "deep neural networks, Resource allocation, spectrum reuse, vehicular communications",

author = "Mimi Chen and Jiajun Chen and Xiaojing Chen and Shunqing Zhang and Shugong Xu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Wireless Communications and Networking Conference, WCNC 2019 ; Conference date: 15-04-2019 Through 19-04-2019",

year = "2019",

month = apr,

doi = "10.1109/WCNC.2019.8886105",

language = "English",

series = "IEEE Wireless Communications and Networking Conference, WCNC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 IEEE Wireless Communications and Networking Conference, WCNC 2019",

}

Chen, M, Chen, J, Chen, X, Zhang, S & Xu, S 2019, A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems. in 2019 IEEE Wireless Communications and Networking Conference, WCNC 2019., 8886105, IEEE Wireless Communications and Networking Conference, WCNC, vol. 2019-April, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE Wireless Communications and Networking Conference, WCNC 2019, Marrakesh, Morocco, 15/04/19. https://doi.org/10.1109/WCNC.2019.8886105

A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems. / Chen, Mimi; Chen, Jiajun; Chen, Xiaojing et al.
2019 IEEE Wireless Communications and Networking Conference, WCNC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8886105 (IEEE Wireless Communications and Networking Conference, WCNC; Vol. 2019-April).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems

AU - Chen, Mimi

AU - Chen, Jiajun

AU - Chen, Xiaojing

AU - Zhang, Shunqing

AU - Xu, Shugong

PY - 2019/4

Y1 - 2019/4

N2 - In vehicular communications, intracell interference and the stringent latency requirement are challenging issues. In this paper, a joint spectrum reuse and power allocation problem is formulated for hybrid vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Recognizing the high capacity and low-latency requirements for V2I and V2V links, respectively, we aim to maximize the weighted sum of the capacities and latency requirement. By decomposing the original problem into a classification subproblem and a regression subproblem, a convolutional neural network (CNN) based approach is developed to obtain real-time decisions on spectrum reuse and power allocation. Numerical results further demonstrate that the proposed CNN can achieve similar performance as the Exhaustive method, while needs only 3.62% of its CPU runtime.

AB - In vehicular communications, intracell interference and the stringent latency requirement are challenging issues. In this paper, a joint spectrum reuse and power allocation problem is formulated for hybrid vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Recognizing the high capacity and low-latency requirements for V2I and V2V links, respectively, we aim to maximize the weighted sum of the capacities and latency requirement. By decomposing the original problem into a classification subproblem and a regression subproblem, a convolutional neural network (CNN) based approach is developed to obtain real-time decisions on spectrum reuse and power allocation. Numerical results further demonstrate that the proposed CNN can achieve similar performance as the Exhaustive method, while needs only 3.62% of its CPU runtime.

KW - deep neural networks

KW - Resource allocation

KW - spectrum reuse

KW - vehicular communications

UR - http://www.scopus.com/inward/record.url?scp=85074777830&partnerID=8YFLogxK

U2 - 10.1109/WCNC.2019.8886105

DO - 10.1109/WCNC.2019.8886105

M3 - Conference Proceeding

AN - SCOPUS:85074777830

T3 - IEEE Wireless Communications and Networking Conference, WCNC

BT - 2019 IEEE Wireless Communications and Networking Conference, WCNC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Wireless Communications and Networking Conference, WCNC 2019

Y2 - 15 April 2019 through 19 April 2019

ER -

A Deep Learning Based Resource Allocation Scheme in Vehicular Communication Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this