An Intelligent Multi-Agent Architecture for Dynamic Regulation of ATM Congestion Control Parameters

  • Ahmed Mehaoua
  • Youssef Iraqi
  • Adel Ghlamallah
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT)


In this paper, we propose an intelligent multi-agent Quality of Service control architecture for the delivery and the control of MPEG-encoded applications over ATM best effort UBR+ service. The designed architecture relies on two components: an efficient video-oriented switch scheduling strategy with an adaptive discarding mechanism, and a multi-agent system based on rules and policies for global network resource management and dynamic switch parameters control. The newly presented cell elimination scheme adaptively and selectively adjusts discard level to switch buffer occupancy, video cell payload types and forward error correction drop tolerance parameter. To simplify its management and improve its performance, automatic and dynamic switch control parameters regulation (e.g. buffer thresholds, drop tolerance,…) are provided by a set of distributed and cooperative intelligent agents. The aim of this automated QoS control architecture is twofold. Firstly, ensuring a graceful picture quality degradation by minimizing cell loss probability for critical video data while guaranteeing a bounded end-to-end cell transfer delay. Secondly, optimizing the network effective throughput by reducing the transmission of non useful video data.


ATM UBR+ MPEG QoS Intelligent Agent Policy OAM 


  1. ATM Forum (1996) Traffic Management Specification 4.0, at-tm-0056.000, April 1996.Google Scholar
  2. ISO/IEC International standard 13818–1 (1995) Generic Coding of Moving Pictures and Associated audio information: Systems, 1995.Google Scholar
  3. ITU-T I.610 (1993) B-ISDN Operation and Maintenance Principles Functions, Geneva, March 1993.Google Scholar
  4. Magedanz T., Rothermel K., Krause S. (1996) Intelligent Agents: An Emerging Technology for Next Generation Telecommunications ?, in IEEE INFOCOM 96, San Francisco, CA, March 1996.Google Scholar
  5. Mehaoua A. and Boutaba R. (1997a) Performance Analysis of an Adaptive Partial Slice Discard Scheme (A-PSD) for MPEG Video over UBR+ Service, in 13th IFIP International Conference on Computer Communications (ICCC 97), Cannes, France, November 1997.Google Scholar
  6. Mehaoua A., Boutaba R. and Pujolle G. (1997b) An Extended Priority Data Partition scheme for MPEG Video Connections over ATM, in Second IEEE Symposium on Computers and Communications (ISCC’97), Alexandria, Egypt, July 1997.Google Scholar
  7. Romanov A. and Floyd S. (1994) Dynamics of TCP Traffic over ATM networks, in ACM SIGCOMM’94, pp. 79–88, September 1994.Google Scholar
  8. Schuhknet A., Dreo G. (1995) Preventing Rather Repairing: A new Approach in ATM Network Management, in INET’95 HyperMedia, Honolulu, Hawaii, June 1995.Google Scholar
  9. Zhang T., Covaci S., Popescu-Zeletin R. (1996) Intelligent Agents in Network and Service Management, in IEEE GLOBECOM’96, London, 1996, pp. 1855–1861.Google Scholar

Copyright information

© IFIP 1998

Authors and Affiliations

  • Ahmed Mehaoua
    • 1
  • Youssef Iraqi
    • 2
  • Adel Ghlamallah
    • 2
  1. 1.University of VersaillesVersaillesFrance
  2. 2.University of MontréalCanada

Personalised recommendations