A Fluid-Based Model of Time-Limited TCP Flows in a DiffServ Environment

Abstract — The Differentiated Services (DiffServ DS) architecture allows IP networks to offer different QoS levels to different users and applications. In this architecture, routers in the core network offer the same Per-Hop Behavior (PHB) to all the packets classified as belonging to the same class at the edge of the network. One of the most important standard types of PHB is the Assured Forwarding (AF) PHB. Within each AF class, IP packets can be marked with different drop precedence (DP) values, and treated differently in congested DS nodes. To this end, DS nodes in the core network implement Active Queue Management (AQM) mechanisms. The challenge in this context is appropriate configuration of the AQM control parameters. For this reason, it is important to provide designers with an accurate analytical framework to calculate the end-to-end performance of TCP flows in a DiffServ network. The target of this paper is to provide an accurate fluid-flow analytical model of a DiffServ network where the RIO-C, RIO-DC and WRED AQM techniques are implemented. We address a network simultaneously loaded with both short-lived and long-lived TCP flows, and we consider one AF class in which two DPs are defined, one for packets complying with the negotiated profile (IN packets), and another for packets that do not respect it (OUT packets). The proposed model can be applied to any complex network topology, not just to a bottleneck link. In addition, it is able to capture cases in which not all network routers implement the same AQM technique.