A new approach for the prediction of end-toend performance of multimedia streams

This paper proposes a new and accurate way of predicting the end-to-end performance of a multimedia stream. It con-sists of coupling an approach we have previously developed, which is able to capture very precisely the way humans assess an arriving stream, with classical performance evaluation mod-els. The former approach can automatically quantify the quality of the connection as humans would do (using statistical learn-ing tools), considering this quantitative measure of quality as a function of measurable parameters of the network and the source; the latter allows mapping this “ultimate ” quality value to input parameters such as offered traffic or loads, through, for instance, queuing models. In the paper, we also propose a sim-plification of the global approach dealing with simple closed formulas. We illustrate our approach with a simple case study of unidirectional VoIP performance. 1