Buffer Management Policies for DTN Applications with Different QoS Requirements

Delay and Disruption Tolerant Networks (DTNs) have been proposed for challenging environments where the instability or lack of end-to-end paths is the rule rather than the exception. In this context, the principle of store-carry-and forward is used to sustain data sessions under intermittent connectivity, and data replication to increase the probability of on-time delivery. However, these techniques create the need for efficient scheduling and buffer management techniques, as the data load is generally larger than the amount of the available resources (i.e. bandwidth per communication opportunity, and buffer storage). A number of recent schemes have been proposed to make forwarding decisions that improve or even optimize the usage of these resources, in one way or another. Nevertheless, the majority of these schemes consider application sessions (and thus data messages) of equal importance. Furthermore, the few proposals that consider different traffic classes, do so in a somewhat "ad-hoc" manner, failing to provide real QoS guarantees. To this end, in this paper we formulate the problem of maximizing the network performance, in a limited resource network, subject to constraints corresponding to distinct QoS requirements (e.g., delivery probability) for each application class. Based on this formulation, we propose a distributed algorithm which: (i) guarantees that the individual QoS constraints are satisfied, when this is feasible given the amount of available resources, and (ii) allocates any remaining resources optimally, so as to maximize the desired performance metric. Simulation results, based on synthetic and realistic mobility scenarios, support our theoretical claims and further show that our policy outperforms other existing QoS prioritization schemes.