Traffic Aware QoS Routing in Ad Hoc Wireless Networks

Prior research has shown that traffic in data networks is better described by heavy-tailed distributions. For ad hoc wireless networks, it is imperative to understand the impact of the heavy-tailed nature ofnetwork trafficfor routing decisions since heavy-tailedness can lead to severe performance degradation. In this paper, we present our current work on ad hoc routing by exploiting the heavy-tailed nature of the session (flow) lifetime. In particular, long- and short-lived flows are differentiated based on the unique predictability nascent in heavy-tailed distributions, with the long-lived flows distributed across the network as disperse as possible, and the short-lived flows treated as "filler" traffic. Simulation results reveal that our Heavy-tailedness Aware Routing Protocol (HARP) significantly outperforms the state-of-the-art under heavy-tailed workload. Such awareness is particularly important, since heavy-tailedness is essentially the nature of the workload in multi-hop wireless networks.