Dynamic resource control for continuous media traffic over ATM networks

  • Authors:
  • Rose P. Tsang;Paisal Keattithananant;Taisheng Chang;Jenwei Hsieh;David H. C. Du

  • Affiliations:
  • Sandia National Laboratories, Distributed Information Technologies Center, Infrastructure and Networking Research, Livermore, CA 94551, USA;Information Superhighway Testbed, National Electronics and Computer Technology Center, Ministry of Science Technology and Environment, Bangkok, Thailand;Distributed Multimedia Research Center and Computer Science Department, University of Minnesota, Minneapolis, MN 55455, USA;Distributed Multimedia Research Center and Computer Science Department, University of Minnesota, Minneapolis, MN 55455, USA;Distributed Multimedia Research Center and Computer Science Department, University of Minnesota, Minneapolis, MN 55455, USA

  • Venue:
  • Computer Communications
  • Year:
  • 1996

Quantified Score

Hi-index 0.24

Visualization

Abstract

Real-time continuous media traffic, such as digital video and audio, is expected to comprise a large percentage of the network load on future high speed packet switch networks such as ATM. A major feature which distinguishes high speed networks from traditional slower speed networks is the large amount of data the network must process very quickly. For efficient network usage, traffic control mechanisms are essential. Currently, most mechanisms for traffic control (such as flow control) have centered on the support of Available Bit Rate (ABR), i.e. non real-time traffic. Traffic control for continuous media traffic is an inherently difficult problem due to the time-sensitive nature of the traffic and its unpredictable bit rate variability. In this study, we present a scheme which controls traffic by dynamically allocating/de-allocating resources among competing VCs based upon their real-time requirements. This scheme incorporates a form of rate-control, real-time burst-level scheduling and link-link flow control. We show analytically potential performance improvements of our rate-control scheme, and present a scheme for buffer dimensioning. We also present simulation results of our schemes and discuss the trade-offs inherent in maintaining high network utilization and statistically guaranteeing many users' Quality of Service.