TY - GEN
T1 - Learning relaying strategies in cellular D2D networks with token-based incentives
AU - Mastronarde, Nicholas
AU - Patel, Viral
AU - Xu, Jie
AU - Van Der Schaar, Mihaela
PY - 2013/1/1
Y1 - 2013/1/1
N2 - 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.
AB - 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.
KW - D2D cooperative relaying
KW - LTE-Advanced
KW - online learning
KW - token exchange system
UR - http://www.scopus.com/inward/record.url?scp=84902973642&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902973642&partnerID=8YFLogxK
U2 - 10.1109/GLOCOMW.2013.6824980
DO - 10.1109/GLOCOMW.2013.6824980
M3 - Conference contribution
AN - SCOPUS:84902973642
SN - 9781479928514
T3 - 2013 IEEE Globecom Workshops, GC Wkshps 2013
SP - 163
EP - 169
BT - 2013 IEEE Globecom Workshops, GC Wkshps 2013
PB - IEEE Computer Society
T2 - 2013 IEEE Globecom Workshops, GC Wkshps 2013
Y2 - 9 December 2013 through 13 December 2013
ER -