Quality-of-service differentiation on the Internet: A taxonomy

Internet applications and clients have very diverse service expectations, demanding for provisioning of different levels of quality of service (QoS) to multiple traffic classes on the Internet. To meet this demand, many different approaches and performance metrics have been proposed in an attempt to achieve per-class QoS differentiation in the network core, network edges, proxy and end servers. However, due to the wide variety of approaches to the problem, it is difficult to meaningfully compare different approaches since there is no uniform means for quantitatively or qualitatively evaluating them. Thus, it is hard to build upon existing work or identify areas worthy of additional efforts without understanding of the relationships between existing efforts.In this paper, a taxonomy of approaches to per-class QoS differentiation is presented in an attempt to provide a common terminology and classification mechanism necessary in addressing this problem. The taxonomy categorizes state-of-the-art QoS differentiation approaches in three dimensions. The first categorization dimension is the locations where the approaches are deployed, i.e., server, proxy and network sides. The QoS differentiation approaches are secondly categorized according to their policies, i.e., admission control, resource management, and content adaptation. The third categorization dimension is their implementation layer, i.e., application level, and kernel level. Representative QoS differentiation approaches in each category are reviewed.