A Multi-Agent Architecture for QoS Management in Multimedia Networks

  • Authors:
  • Raouf Boutaba;Youssef Iraqi;Ahmed Mehaoua

  • Affiliations:
  • University of Waterloo, School of Computer Science, 200 University Avenue West, Waterloo, Ont. N2L 3G1, Canada/ rboutaba@bbcr.uwaterloo.ca;University of Waterloo, School of Computer Science, 200 University Avenue West, Waterloo, Ontario N2L 3G1, Canada/ iraqi@bbcr.uwaterloo.ca;University of Versailles, CNRS-PRiSM Laboratory, 45 av. des Etats-Unis, Versailles, France/ mea@prism.uvsq.fr

  • Venue:
  • Journal of Network and Systems Management
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Increasing interest in the transmission of audiovisual applications over best-effort networks (i.e., IP and ATM ABR, and UBR services) and efficient video-aware congestion control techniques have to be designed in order to improve the video quality in the presence of cell loss. This paper presents a new slice-based discard scheme to be used with Guaranteed Frame Rate service (formerly UBR+). The scheme adaptively and selectively adjusts discard levels to the switch's buffer occupancy, video cell payload types, and Forward Error Correction Drop Tolerance. To improve its performance, we introduce a distributed multiagent system that provides a self-regulating network control management by means of automatic adjustment of congestion control parameters. The control agents are distributed in the network and operate on a local scope referred to as a “domain” consisting of two adjacent ATM switches. The aim of the overall Intelligent Quality-of-Service (QoS) control framework is twofold. First, to ensure graceful picture quality degradation by minimizing the cell loss probability for critical video data while guaranteeing a bounded cell transfer delay. Second, to optimize the network effective throughput by reducing the transmission of “nonuseful” data. Performance evaluations show significant improvement over traditional approaches.