A calculus for stochastic QoS analysis and its application to conformance study

Abstract

With the advent of the Internet, there is a proliferation of multimedia applications which need Quality of Service (QoS) guarantees. Many schemes have been proposed for QoS provisioning in computer networks. It is important to evaluate the performance of these QoS provisioning schemes. In this thesis, a stochastic network calculus is proposed to systematically investigate the stochastic QoS performance of various deterministic and stochastic servers. The stochastic backlog, delay and output burstiness under a single deterministic server and stochastic sever are first derived. Then, the stochastic end-to-end QoS bounds have also been derived. Results on the per-flow stochastic QoS performance are also derived under aggregate scheduling. In addition, as an application of the stochastic network calculus proposed in this thesis, the conformance performance of a flow is studied to investigate to what extent the flow is non-conformant to its original traffic specification after crossing a network with Service Level Agreements.