Learning relaying strategies in cellular D2D networks with token-based incentives

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Scopus citations


We consider a cellular network where intelligent cellular devices owned by selfish users are incentivized to cooperate with each other by using tokens, which they exchange electronically to 'buy' and 'sell' downlink relay services, thereby increasing the network's capacity. We endow each device with the ability to learn its optimal cooperation strategy online in order to maximize its long-term utility in the dynamic network environment. We investigate the impact of the token exchange system on the overall downlink network performance and the performance of individual devices in various deployment scenarios involving mixtures of high and low mobility users. Our results suggest that devices have the greatest incentive to cooperate when the network contains many highly mobile users (e.g., users in motor vehicles). Moreover, within the token system, devices can effectively learn to cooperate online, and achieve over 20% higher throughput on average than with direct transmission alone, all while selfishly maximizing their own utility.

Original languageEnglish (US)
Title of host publication2013 IEEE Globecom Workshops, GC Wkshps 2013
PublisherIEEE Computer Society
Number of pages7
ISBN (Print)9781479928514
StatePublished - 2013
Externally publishedYes
Event2013 IEEE Globecom Workshops, GC Wkshps 2013 - Atlanta, GA, United States
Duration: Dec 9 2013Dec 13 2013

Publication series

Name2013 IEEE Globecom Workshops, GC Wkshps 2013


Other2013 IEEE Globecom Workshops, GC Wkshps 2013
Country/TerritoryUnited States
CityAtlanta, GA


  • D2D cooperative relaying
  • LTE-Advanced
  • online learning
  • token exchange system

ASJC Scopus subject areas

  • Computer Networks and Communications


Dive into the research topics of 'Learning relaying strategies in cellular D2D networks with token-based incentives'. Together they form a unique fingerprint.

Cite this