Passing the torch: Role alternation for fair energy usage in D2D group communication

Abstract

By using device-to-device (D2D) communication, opportunistic networks promise to fill the gaps of the networking infrastructure in remote areas, to enable communication in emergency situations, and to inspire new applications. Yet, to become feasible in practice and accepted by users, it is crucial that the energy costs of D2D connections are small and shared fairly. Fairness, in particular, is a major issue with today's D2D technologies (Bluetooth, Wi-Fi Direct): since each connected peer must assume one of two different roles - access point/client, master/slave, the energy consumption inside a connected group is very asymmetric. While a large body of research exists on role assignment and topology control, the above issue of energy fairness is either not at all addressed (e.g. in the context of Bluetooth scatternets) or is addressed under fundamentally different conditions (e.g. in very dense and often static wireless sensor networks). In this paper, we tackle the fairness problem of the energy consumed in a group of D2D-connected nodes, by using role switching: the two types of roles are alternated among group members, thus producing a fairer cost sharing. First, we analyze contact traces for their group topologies and find that four simple motifs - clique, star, chain and NxM-clique - cover up to 94% of the aggregated lifetime of all connected groups. We then determine the optimal role switching strategies for these motifs by formulating the cycle of role assignments as an optimization problem. Since deriving the optimal cycle online, in a distributed manner is hardly possible in practice, we also propose two role switching heuristics for online use: a randomized switching scheme tunable for efficiency or fairness, and a deterministic scheme which additionally guarantees the group's connectivity. Finally, we evaluate our solutions on real contact traces and show that our heuristics find very good points of operation in the fairness-efficiency tradeoff.