Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks

Liu Lirui; Song Xiaoqin; Lei Lei; Zhang Lijuan

doi:10.1109/ICSIP57908.2023.10270860

Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks

Liu Lirui^*
, Song Xiaoqin
, Lei Lei
, Zhang Lijuan

^*Corresponding author for this work

Nanjing University of Aeronautics and Astronautics

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

2 Citations (Scopus)

Abstract

To solve the issue of the low transmission rate and energy efficiency in vehicle-to-vehicle (V2V) communication, a periodic-federated-adjusted double deep Q-network (PFADDQN) algorithm is proposed for intelligent reflecting surface (IRS)assisted vehicular networks. Considering the constraints in channel and power allocation in V2V communication, a joint benefit, which is defined as the combination of transmission success rate and energy consumption, is maximized. By using ajoint federated learning and double deep Q-network approach, the original NPhard optimization problem is solved. Simulation results demonstrate the superiority of our proposed PFADDQN algorithm over other baselines in IRS-assisted vehicular networks.

Original language	English
Title of host publication	2023 8th International Conference on Signal and Image Processing, ICSIP 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	877-881
Number of pages	5
ISBN (Electronic)	9798350397932
DOIs	https://doi.org/10.1109/ICSIP57908.2023.10270860
Publication status	Published - 2023
Externally published	Yes
Event	8th International Conference on Signal and Image Processing, ICSIP 2023 - Wuxi, China Duration: 8 Jul 2023 → 10 Jul 2023

Publication series

Name	2023 8th International Conference on Signal and Image Processing, ICSIP 2023

Conference

Conference	8th International Conference on Signal and Image Processing, ICSIP 2023
Country/Territory	China
City	Wuxi
Period	8/07/23 → 10/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

DDQN
Federated learning
Intelligent reflecting surface
Joint benefit
Reinforcement learning
Vehicular networks

Access to Document

10.1109/ICSIP57908.2023.10270860

Cite this

Lirui, L., Xiaoqin, S., Lei, L., & Lijuan, Z. (2023). Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks. In 2023 8th International Conference on Signal and Image Processing, ICSIP 2023 (pp. 877-881). (2023 8th International Conference on Signal and Image Processing, ICSIP 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSIP57908.2023.10270860

@inproceedings{28aa8c4769e14fdfb3fb6ed9823ab1aa,

title = "Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks",

abstract = "To solve the issue of the low transmission rate and energy efficiency in vehicle-to-vehicle (V2V) communication, a periodic-federated-adjusted double deep Q-network (PFADDQN) algorithm is proposed for intelligent reflecting surface (IRS)assisted vehicular networks. Considering the constraints in channel and power allocation in V2V communication, a joint benefit, which is defined as the combination of transmission success rate and energy consumption, is maximized. By using ajoint federated learning and double deep Q-network approach, the original NPhard optimization problem is solved. Simulation results demonstrate the superiority of our proposed PFADDQN algorithm over other baselines in IRS-assisted vehicular networks.",

keywords = "DDQN, Federated learning, Intelligent reflecting surface, Joint benefit, Reinforcement learning, Vehicular networks",

author = "Liu Lirui and Song Xiaoqin and Lei Lei and Zhang Lijuan",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 8th International Conference on Signal and Image Processing, ICSIP 2023 ; Conference date: 08-07-2023 Through 10-07-2023",

year = "2023",

doi = "10.1109/ICSIP57908.2023.10270860",

language = "English",

series = "2023 8th International Conference on Signal and Image Processing, ICSIP 2023",

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

pages = "877--881",

booktitle = "2023 8th International Conference on Signal and Image Processing, ICSIP 2023",

address = "United States",

}

Lirui, L, Xiaoqin, S, Lei, L & Lijuan, Z 2023, Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks. in 2023 8th International Conference on Signal and Image Processing, ICSIP 2023. 2023 8th International Conference on Signal and Image Processing, ICSIP 2023, Institute of Electrical and Electronics Engineers Inc., pp. 877-881, 8th International Conference on Signal and Image Processing, ICSIP 2023, Wuxi, China, 8/07/23. https://doi.org/10.1109/ICSIP57908.2023.10270860

Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks. / Lirui, Liu; Xiaoqin, Song; Lei, Lei et al.
2023 8th International Conference on Signal and Image Processing, ICSIP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 877-881 (2023 8th International Conference on Signal and Image Processing, ICSIP 2023).

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

TY - GEN

T1 - Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks

AU - Lirui, Liu

AU - Xiaoqin, Song

AU - Lei, Lei

AU - Lijuan, Zhang

PY - 2023

Y1 - 2023

N2 - To solve the issue of the low transmission rate and energy efficiency in vehicle-to-vehicle (V2V) communication, a periodic-federated-adjusted double deep Q-network (PFADDQN) algorithm is proposed for intelligent reflecting surface (IRS)assisted vehicular networks. Considering the constraints in channel and power allocation in V2V communication, a joint benefit, which is defined as the combination of transmission success rate and energy consumption, is maximized. By using ajoint federated learning and double deep Q-network approach, the original NPhard optimization problem is solved. Simulation results demonstrate the superiority of our proposed PFADDQN algorithm over other baselines in IRS-assisted vehicular networks.

AB - To solve the issue of the low transmission rate and energy efficiency in vehicle-to-vehicle (V2V) communication, a periodic-federated-adjusted double deep Q-network (PFADDQN) algorithm is proposed for intelligent reflecting surface (IRS)assisted vehicular networks. Considering the constraints in channel and power allocation in V2V communication, a joint benefit, which is defined as the combination of transmission success rate and energy consumption, is maximized. By using ajoint federated learning and double deep Q-network approach, the original NPhard optimization problem is solved. Simulation results demonstrate the superiority of our proposed PFADDQN algorithm over other baselines in IRS-assisted vehicular networks.

KW - DDQN

KW - Federated learning

KW - Intelligent reflecting surface

KW - Joint benefit

KW - Reinforcement learning

KW - Vehicular networks

UR - https://www.scopus.com/pages/publications/85174746880

U2 - 10.1109/ICSIP57908.2023.10270860

DO - 10.1109/ICSIP57908.2023.10270860

M3 - Conference contribution

AN - SCOPUS:85174746880

T3 - 2023 8th International Conference on Signal and Image Processing, ICSIP 2023

SP - 877

EP - 881

BT - 2023 8th International Conference on Signal and Image Processing, ICSIP 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th International Conference on Signal and Image Processing, ICSIP 2023

Y2 - 8 July 2023 through 10 July 2023

ER -

Lirui L, Xiaoqin S, Lei L, Lijuan Z. Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks. In 2023 8th International Conference on Signal and Image Processing, ICSIP 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 877-881. (2023 8th International Conference on Signal and Image Processing, ICSIP 2023). doi: 10.1109/ICSIP57908.2023.10270860

Federated Learning Empowered V2V Resource Allocation in IRS-assisted Vehicular Networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this