SIDEMAN: Service Discovery in Mobile Social Networks

In this paper we present SIDEMAN, a service discovery algorithm that exploits human mobility patterns in Mobile Social Networks (MSN). SIDEMAN takes advantage of two aspects of MSN, namely, that users tend to form communities, and that users in the same community share interests for similar services. The performance of SIDEMAN has been evaluated through simulations in real and synthetic scenarios: A set of traces collected at IEEE Infocom 2006 and traces obtained from the HCMM mobility model, respectively. We have compared our algorithm to the social version of two popular discovery techniques, namely, flooding and gossiping. We investigated the following key metrics: How proactive an algorithm is in distributing services of interest (Recall); how many services are already with a user when s/he needs them (Gain); the energy cost necessary for service discovery; the time needed to reply to a service query, and the average number of services stored and exchanged. Our results show that in all considered scenarios SIDEMAN is remarkably effective in obtaining flawless Recall and a Gain that is always comparable to that of the other algorithms. Furthermore, most services are retrieved in reasonable time and at a remarkably lower energy cost than that of flooding and gossiping-based solutions.