Improving Multimedia Streaming Over Wireless Using End-to-End Estimation of Wireless Losses

Many networked applications use end-to-end congestion control protocols to avoid the occurrence of congestion collapse phenomena. However, such transport protocols may suffer from link underutilization when there are wireless links along the path: the inability to distinguish wireless losses from congestion losses often results in unnecessary throughput decreases. Since networks are becoming increasingly heterogeneous, a mix of wired and wireless links, it is important to have some means of identifying the cause of a packet loss and to adapt the response of the transport protocol. In this paper, we present an end-to-end solution to this problem and propose a novel method for wireless loss estimation in IP DiffServ networks (WLED). WLED aims at enhancing the performance of equation-based rate control protocols for multimedia applications, by means of directly estimating the wireless and congestion loss rates. We discuss the integration of WLED with a recent, equation-based rate control protocol and we evaluate WLED's performance through simulation. Our results illustrate a new benefit of using DiffServ-like differentiation mechanisms for multimedia streaming in wireless networks, like UMTS, that support quality of service (QoS).