To relay or not to relay: Learning device-to-device relaying strategies in cellular networks

Nicholas Mastronarde, Viral Patel, Jie Xu, Lingjia Liu, Mihaela Van Der Schaar

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

We consider a cellular network where mobile transceiver devices that are owned by self-interested users are incentivized to cooperate with each other using tokens, which they exchange electronically to 'buy' and 'sell' downlink relay services, thereby increasing the network's capacity compared to a network that only supports base station-to-device (B2D) communications. We investigate how an individual device in the network can learn its optimal cooperation policy online, which it uses to decide whether or not to provide downlink relay services for other devices in exchange for tokens. We propose a supervised learning algorithm that devices can deploy to learn their optimal cooperation strategies online given their experienced network environment. We then systematically evaluate the learning algorithm in various deployment scenarios. Our simulation results suggest that devices have the greatest incentive to cooperate when the network contains (i) many devices with high energy budgets for relaying, (ii) many highly mobile users (e.g., users in motor vehicles), and (iii) neither too few nor too many tokens. Additionally, within the token system, self-interested devices can effectively learn to cooperate online, and achieve up to 20 percent throughput gains on average compared to B2D communications alone, all while selfishly maximizing their own utilities.

Original languageEnglish (US)
Article number7181721
Pages (from-to)1569-1585
Number of pages17
JournalIEEE Transactions on Mobile Computing
Volume15
Issue number6
DOIs
StatePublished - Jun 1 2016

Fingerprint

Learning algorithms
Communication
Supervised learning
Transceivers
Base stations
Wireless networks
Throughput

Keywords

  • Emerging technologies
  • learning
  • mobile communications systems
  • mobile environments
  • network management
  • wireless communications

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Software

Cite this

To relay or not to relay : Learning device-to-device relaying strategies in cellular networks. / Mastronarde, Nicholas; Patel, Viral; Xu, Jie; Liu, Lingjia; Van Der Schaar, Mihaela.

In: IEEE Transactions on Mobile Computing, Vol. 15, No. 6, 7181721, 01.06.2016, p. 1569-1585.

Research output: Contribution to journalArticle

Mastronarde, Nicholas ; Patel, Viral ; Xu, Jie ; Liu, Lingjia ; Van Der Schaar, Mihaela. / To relay or not to relay : Learning device-to-device relaying strategies in cellular networks. In: IEEE Transactions on Mobile Computing. 2016 ; Vol. 15, No. 6. pp. 1569-1585.
@article{819f860386a34828880e7107162896e9,
title = "To relay or not to relay: Learning device-to-device relaying strategies in cellular networks",
abstract = "We consider a cellular network where mobile transceiver devices that are owned by self-interested users are incentivized to cooperate with each other using tokens, which they exchange electronically to 'buy' and 'sell' downlink relay services, thereby increasing the network's capacity compared to a network that only supports base station-to-device (B2D) communications. We investigate how an individual device in the network can learn its optimal cooperation policy online, which it uses to decide whether or not to provide downlink relay services for other devices in exchange for tokens. We propose a supervised learning algorithm that devices can deploy to learn their optimal cooperation strategies online given their experienced network environment. We then systematically evaluate the learning algorithm in various deployment scenarios. Our simulation results suggest that devices have the greatest incentive to cooperate when the network contains (i) many devices with high energy budgets for relaying, (ii) many highly mobile users (e.g., users in motor vehicles), and (iii) neither too few nor too many tokens. Additionally, within the token system, self-interested devices can effectively learn to cooperate online, and achieve up to 20 percent throughput gains on average compared to B2D communications alone, all while selfishly maximizing their own utilities.",
keywords = "Emerging technologies, learning, mobile communications systems, mobile environments, network management, wireless communications",
author = "Nicholas Mastronarde and Viral Patel and Jie Xu and Lingjia Liu and {Van Der Schaar}, Mihaela",
year = "2016",
month = "6",
day = "1",
doi = "10.1109/TMC.2015.2465379",
language = "English (US)",
volume = "15",
pages = "1569--1585",
journal = "IEEE Transactions on Mobile Computing",
issn = "1536-1233",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - To relay or not to relay

T2 - Learning device-to-device relaying strategies in cellular networks

AU - Mastronarde, Nicholas

AU - Patel, Viral

AU - Xu, Jie

AU - Liu, Lingjia

AU - Van Der Schaar, Mihaela

PY - 2016/6/1

Y1 - 2016/6/1

N2 - We consider a cellular network where mobile transceiver devices that are owned by self-interested users are incentivized to cooperate with each other using tokens, which they exchange electronically to 'buy' and 'sell' downlink relay services, thereby increasing the network's capacity compared to a network that only supports base station-to-device (B2D) communications. We investigate how an individual device in the network can learn its optimal cooperation policy online, which it uses to decide whether or not to provide downlink relay services for other devices in exchange for tokens. We propose a supervised learning algorithm that devices can deploy to learn their optimal cooperation strategies online given their experienced network environment. We then systematically evaluate the learning algorithm in various deployment scenarios. Our simulation results suggest that devices have the greatest incentive to cooperate when the network contains (i) many devices with high energy budgets for relaying, (ii) many highly mobile users (e.g., users in motor vehicles), and (iii) neither too few nor too many tokens. Additionally, within the token system, self-interested devices can effectively learn to cooperate online, and achieve up to 20 percent throughput gains on average compared to B2D communications alone, all while selfishly maximizing their own utilities.

AB - We consider a cellular network where mobile transceiver devices that are owned by self-interested users are incentivized to cooperate with each other using tokens, which they exchange electronically to 'buy' and 'sell' downlink relay services, thereby increasing the network's capacity compared to a network that only supports base station-to-device (B2D) communications. We investigate how an individual device in the network can learn its optimal cooperation policy online, which it uses to decide whether or not to provide downlink relay services for other devices in exchange for tokens. We propose a supervised learning algorithm that devices can deploy to learn their optimal cooperation strategies online given their experienced network environment. We then systematically evaluate the learning algorithm in various deployment scenarios. Our simulation results suggest that devices have the greatest incentive to cooperate when the network contains (i) many devices with high energy budgets for relaying, (ii) many highly mobile users (e.g., users in motor vehicles), and (iii) neither too few nor too many tokens. Additionally, within the token system, self-interested devices can effectively learn to cooperate online, and achieve up to 20 percent throughput gains on average compared to B2D communications alone, all while selfishly maximizing their own utilities.

KW - Emerging technologies

KW - learning

KW - mobile communications systems

KW - mobile environments

KW - network management

KW - wireless communications

UR - http://www.scopus.com/inward/record.url?scp=84969610661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969610661&partnerID=8YFLogxK

U2 - 10.1109/TMC.2015.2465379

DO - 10.1109/TMC.2015.2465379

M3 - Article

AN - SCOPUS:84969610661

VL - 15

SP - 1569

EP - 1585

JO - IEEE Transactions on Mobile Computing

JF - IEEE Transactions on Mobile Computing

SN - 1536-1233

IS - 6

M1 - 7181721

ER -