A source model of video traffic based on full-length VBR MPEG4 video traces

MPEG encoded video accounts for a considerable share of high-volume traffic in both wireline and wireless networks of the next generation. MPEG video requires high bandwidth, and its QoS is highly sensitive to packet loss, delay and bit error rate. Such unique features raise great challenges for traffic engineering. However, the scarcity of video traces bottlenecks the advances in video traffic study. In this paper, we propose a VBR video traffic model that accurately characterizes VBR MPEG4 video traces and mimics their statistical properties. Two highlights of our model include a novel scene-based Markov modulated process and the feedback control on the frame size distribution. We validate our model by comparing various statistics of the simulated traces with those of the original traces. It is shown that our model provides an effective solution to obtain ample high-quality traces for video traffic analysis and network performance evaluation.

[1]  Tamás Borsos,et al.  A Practical Model for VBR Video Traffic with Applications , 2001, MMNS.

[2]  David M. Lucantoni,et al.  Modeling multiple IP traffic streams with rate limits , 2001 .

[3]  Michael Devetsikiotis,et al.  Modelling prioritized MPEG video using TES and a frame spreading strategy for transmission in ATM networks , 1995, Proceedings of INFOCOM'95.

[4]  T. V. Lakshman,et al.  Statistical analysis and simulation study of video teleconference traffic in ATM networks , 1992, IEEE Trans. Circuits Syst. Video Technol..

[5]  Abdelnaser Mohammad Adas.  Supporting real time VBR video using dynamic reservation based on linear prediction , 1996, Proceedings of IEEE INFOCOM '96. Conference on Computer Communications.

[6]  John Cosmas,et al.  Characterization of Video Codecs as Autoregressive Moving Average Processes and Related Queueing System Performance , 1991, IEEE J. Sel. Areas Commun..

[7]  Tapas K. Das,et al.  A scene-based generalized Markov chain model for VBR video traffic , 1998, ICC '98. 1998 IEEE International Conference on Communications. Conference Record. Affiliated with SUPERCOMM'98 (Cat. No.98CH36220).

[8]  Armand M. Makowski,et al.  Modeling video traffic using M/G/∞ input processes: a compromise between Markovian and LRD models , 1998, IEEE J. Sel. Areas Commun..

[9]  T. V. Lakshman,et al.  Source models for VBR broadcast-video traffic , 1996, TNET.

[10]  Amy R. Reibman,et al.  Modeling one- and two-layer variable bit rate video , 1999, TNET.

[11]  P. Skelly,et al.  A histogram-based model for video traffic behavior in an ATM multiplexer , 1993, TNET.

[12]  Benjamin Melamed,et al.  Modeling full-length VBR video using Markov-renewal-modulated TES models , 1998, IEEE J. Sel. Areas Commun..

[13]  Martin Reisslein,et al.  Network performance evaluation using frame size and quality traces of single-layer and two-layer video: A tutorial , 2004, IEEE Communications Surveys & Tutorials.

[14]  Oliver Rose,et al.  Estimation of the Hurst Parameter of Long-Range Dependent Time Series , 1996 .

[15]  Dilip Sarkar,et al.  Modeling full-length video using Markov-modulated gamma-based framework , 2001, GLOBECOM'01. IEEE Global Telecommunications Conference (Cat. No.01CH37270).