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% higher throughput on average than with B2D communications alone, all while selfishly maximizing their own utilities.

Improving cellular downlink throughput by multi-hop relay-assisted outband D2D communications

“…Meanwhile, this scheme restricts the number of relays to one in any transmission path and compares three kinds of relay selection criterion with the standard connectivity. However, literature [27] investigates a selling relays service based on tokens exchange in the two--hop outband D2D communications. As described in [11], interaction among conventional cellular communications, two-hop outband D2D communications and multi-hop outband D2D communications should be investigated and analyzed.…”

OPPay: Design and Implementation of a Payment System for Opportunistic Data Services

“…For example, [18] proposed an incentive-compatible routing algorithms for opportunistic networks. [19] designed a supervised learning algorithm for participants to decide cooperation strategies in the network. [13] created a Backpressure based virtual economic network for participants to trade sensor data.…”

“…Extensive research has been conducted on designing incentivisation schemes to support various types of opportunistic data services [8], [13], [16], [17], [18], [19]. However, all of these work are focused on the theoretical aspects and fail to consider practical issues in the implementation of a payment system.…”

An Overview of Device-to-Device Communications Technology Components in METIS

“…Indeed, collaboration consumes resources like energy and computing power and does not provide immediate benefits. Therefore, UEs may not be interested in cooperation without an incentive [16]. Over the last decade, several techniques have been proposed to encourage cooperation and improve the efficiency of wireless networks using relaying.…”