Distributed Spectrum and Power Allocation for D2D-U Networks: a Scheme Based on NN and Federated Learning

Rui Yin; Zhiqun Zou; Celimuge Wu; Jiantao Yuan; Xianfu Chen

doi:10.1007/s11036-021-01736-2

Distributed Spectrum and Power Allocation for D2D-U Networks: a Scheme Based on NN and Federated Learning

Rui Yin, Zhiqun Zou, Celimuge Wu^*, Jiantao Yuan, Xianfu Chen

^*Corresponding author for this work

BA6401 Connectivity solutions

Research output: Contribution to journal › Article › Scientific › peer-review

13 Citations (Scopus)

Abstract

In this paper, a Device-to-Device communication on unlicensed bands (D2D-U) enabled network is studied. To improve the spectrum efficiency (SE) on the unlicensed bands and fit its distributed structure while ensuring the fairness among D2D-U links and the harmonious coexistence with WiFi networks, a distributed joint power and spectrum scheme is proposed. In particular, a parameter, named as price, is defined, which is updated at each D2D-U pair by a online trained Neural network (NN) according to the channel state and traffic load. In addition, the parameters used in the NN are updated by two ways, unsupervised self-iteration and federated learning, to guarantee the fairness and harmonious coexistence. Then, a non-convex optimization problem with respect to the spectrum and power is formulated and solved on each D2D-U link to maximize its own data rate. Numerical simulation results are demonstrated to verify the effectiveness of the proposed scheme.

Original language	English
Pages (from-to)	2000-2013
Journal	Mobile Networks and Applications
Volume	26
Issue number	5
Early online date	12 Mar 2021
DOIs	https://doi.org/10.1007/s11036-021-01736-2
Publication status	Published - Oct 2021
MoE publication type	A1 Journal article-refereed

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant No. 61771429, No. 61703368, in part by Zhejiang University City College Scientific Research Foundation under Grant No. JZD18002, in part by Zhejiang Provincial Key Laboratory of Information Processing, Communication and Networking, and in part by the selective Grants for Postdoctoral Programs ZJ2020035 in Zhejiang Province, in part by ROIS NII Open Collaborative Research 2020-20S0502, and JSPS KAKENHI grant numbers 18KK0279, 19H04093 and 20H00592.

Keywords

D2D-U
Federated learning
Neural network
Price model
Resource allocation

Access to Document

10.1007/s11036-021-01736-2

Cite this

@article{db5c56ff98f74535b4908066997a038b,

title = "Distributed Spectrum and Power Allocation for D2D-U Networks: a Scheme Based on NN and Federated Learning",

abstract = "In this paper, a Device-to-Device communication on unlicensed bands (D2D-U) enabled network is studied. To improve the spectrum efficiency (SE) on the unlicensed bands and fit its distributed structure while ensuring the fairness among D2D-U links and the harmonious coexistence with WiFi networks, a distributed joint power and spectrum scheme is proposed. In particular, a parameter, named as price, is defined, which is updated at each D2D-U pair by a online trained Neural network (NN) according to the channel state and traffic load. In addition, the parameters used in the NN are updated by two ways, unsupervised self-iteration and federated learning, to guarantee the fairness and harmonious coexistence. Then, a non-convex optimization problem with respect to the spectrum and power is formulated and solved on each D2D-U link to maximize its own data rate. Numerical simulation results are demonstrated to verify the effectiveness of the proposed scheme.",

keywords = "D2D-U, Federated learning, Neural network, Price model, Resource allocation",

author = "Rui Yin and Zhiqun Zou and Celimuge Wu and Jiantao Yuan and Xianfu Chen",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature.",

year = "2021",

month = oct,

doi = "10.1007/s11036-021-01736-2",

language = "English",

volume = "26",

pages = "2000--2013",

journal = "Mobile Networks and Applications",

issn = "1383-469X",

publisher = "Springer",

number = "5",

}

TY - JOUR

T1 - Distributed Spectrum and Power Allocation for D2D-U Networks

T2 - a Scheme Based on NN and Federated Learning

AU - Yin, Rui

AU - Zou, Zhiqun

AU - Wu, Celimuge

AU - Yuan, Jiantao

AU - Chen, Xianfu

PY - 2021/10

Y1 - 2021/10

N2 - In this paper, a Device-to-Device communication on unlicensed bands (D2D-U) enabled network is studied. To improve the spectrum efficiency (SE) on the unlicensed bands and fit its distributed structure while ensuring the fairness among D2D-U links and the harmonious coexistence with WiFi networks, a distributed joint power and spectrum scheme is proposed. In particular, a parameter, named as price, is defined, which is updated at each D2D-U pair by a online trained Neural network (NN) according to the channel state and traffic load. In addition, the parameters used in the NN are updated by two ways, unsupervised self-iteration and federated learning, to guarantee the fairness and harmonious coexistence. Then, a non-convex optimization problem with respect to the spectrum and power is formulated and solved on each D2D-U link to maximize its own data rate. Numerical simulation results are demonstrated to verify the effectiveness of the proposed scheme.

AB - In this paper, a Device-to-Device communication on unlicensed bands (D2D-U) enabled network is studied. To improve the spectrum efficiency (SE) on the unlicensed bands and fit its distributed structure while ensuring the fairness among D2D-U links and the harmonious coexistence with WiFi networks, a distributed joint power and spectrum scheme is proposed. In particular, a parameter, named as price, is defined, which is updated at each D2D-U pair by a online trained Neural network (NN) according to the channel state and traffic load. In addition, the parameters used in the NN are updated by two ways, unsupervised self-iteration and federated learning, to guarantee the fairness and harmonious coexistence. Then, a non-convex optimization problem with respect to the spectrum and power is formulated and solved on each D2D-U link to maximize its own data rate. Numerical simulation results are demonstrated to verify the effectiveness of the proposed scheme.

KW - D2D-U

KW - Federated learning

KW - Neural network

KW - Price model

KW - Resource allocation

UR - https://www.scopus.com/pages/publications/85102558118

U2 - 10.1007/s11036-021-01736-2

DO - 10.1007/s11036-021-01736-2

M3 - Article

AN - SCOPUS:85102558118

SN - 1383-469X

VL - 26

SP - 2000

EP - 2013

JO - Mobile Networks and Applications

JF - Mobile Networks and Applications

IS - 5

ER -

Distributed Spectrum and Power Allocation for D2D-U Networks: a Scheme Based on NN and Federated Learning

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

MISSION: Mission-Critical Internet of Things Applications over Fog Networks

Best Paper Award at EAI MONAMI 2020 conference

Cite this

Distributed Spectrum and Power Allocation for D2D-U Networks: a Scheme Based on NN and Federated Learning

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

MISSION: Mission-Critical Internet of Things Applications over Fog Networks

Prizes

Best Paper Award at EAI MONAMI 2020 conference

Cite this