A new model for MPEG video traffic at the frame level using self-similar processes
M.E. Sousa‐Vieira, J.C. López-Ardao, Raúl F. Rodríguez‐Rubio · Spring Simulation Multiconference · 2007
With the increasing popularity of multimedia applications, video data represents a large portion of the traffic in modern networks. Consequently, adequate models of video traffic, characterized by a high burstiness and a strong positive correlation, are very important for the performance evaluation of networks architectures and protocols. In this paper we propose a new model for MPEG video traffic at the frame level, based on self-similar processes and able to deal with intra-GOP correlations in a parsimonious way. After anlyzing the capabilities of our solution for capturing empirical distributions and correlation structures, we study its goodness to estimate adequately three important performance metrics: loss probability, mean delay and jitter.