Exploiting social preferences for congestion control in opportunistic networks (original) (raw)

It has been observed that opportunistic networks exhibit a highly unbalanced traffic load distribution, mainly because of the heterogeneity in mobility and the greedy routing decisions, leading to packet drops due to storage constraints. The existing strategies rely either on fairness techniques or on diverting traffic to alternative routes in order to control congestion. The result is a dilemma between performance and fairness. In this work, we introduce a congestion control mechanism that provides a tunable trade-off between efficiency and fairness. We rely on the social preferences of the nodes for dynamically tuning the aforementioned trade-off. Our simulations show that the proposed algorithm achieves high delivery ratio, combined with low endto-end delay and routing cost, without sacrificing fairness under high traffic load.