Incentivizing Device-to-Device Load Balancing for Cellular Networks : An Online Auction Design

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

38 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Article number7839907
Pages (from-to)265-279
Journal / PublicationIEEE Journal on Selected Areas in Communications
Volume35
Issue number2
Online published2 Feb 2017
Publication statusPublished - Feb 2017
Externally publishedYes

Abstract

The device-to-device load balancing (D2D-LB) paradigm has been advocated in recent small-cell architecture design for cellular networks. The idea is to exploit inter-cell D2D communication and dynamically relay traffic of a busy cell to adjacent under-utilized cells to improve spectrum temporal efficiency, addressing a fundamental drawback of small-cell architecture. Technical challenges of D2D-LB have been studied in previous works. The potential of D2D-LB, however, cannot be fully realized without providing proper incentive mechanism for device participation. In this paper, we address this economical challenge using an online procurement auction framework. In our design, multiple sellers (devices) submit bids to participate in D2D-LB and the auctioneer (cellular service provider) evaluates all the bids and decides to purchase a subset of them to fulfill load balancing requirement with the minimum social cost. Different from similar auction design studies for cellular offloading, battery limit of relaying devices imposes a time-coupled capacity constraint that turns the underlying problem into a challenging multi-slot one. Furthermore, the dynamics in the input to the multi-slot auction problem emphasize the need for online algorithm design. We first tackle the single-slot version of the problem, show that it is NP-hard, and design a polynomial-time offline algorithm with a small approximation ratio. Building upon the single-slot results, we design an online algorithm for the multi-slot problem with sound competitive ratio. Our auction algorithm design ensures that truthful bidding is a dominant strategy for devices. Extensive experiments using real-world traces demonstrate that our proposed solution achieves near offline-optimum and reduces the cost by 45% compared with an alternative heuristic.

Research Area(s)

  • approximation and competitive analysis, Cellular networks, device-to-device load balancing, online algorithm design, procurement auction design, truthful analysis

Citation Format(s)

Incentivizing Device-to-Device Load Balancing for Cellular Networks : An Online Auction Design. / Hajiesmaili, Mohammad H.; Deng, Lei; Chen, Minghua et al.

In: IEEE Journal on Selected Areas in Communications, Vol. 35, No. 2, 7839907, 02.2017, p. 265-279.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review