• DocumentCode
    382434
  • Title

    Admission controller design for high-speed networks: a hybrid system approach

  • Author

    Jagannathan, S.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Missouri Univ., Rolla, MO, USA
  • Volume
    1
  • fYear
    2002
  • fDate
    2002
  • Firstpage
    542
  • Abstract
    A novel real-time discrete-event admission control (AC) scheme for high-speed networks is proposed with the aim of attaining a desired quality of service (QoS) and high network utilization. The AC encapsulates an adaptive bandwidth estimation scheme, a congestion indicator, and a peak bit/cell rate (PBR/PCR) estimate from new sources. The admission controller dynamics are expressed as a discrete-event system while the bandwidth estimator design is based on Lyapunov theory and the congestion controller dynamics are given in discrete-time. The novel aspect of the proposed approach is the application of hybrid system theory to prove the performance of the proposed admission controller, stability and the development of a rigorous and repeatable design procedure. The performance of the proposed AC is evaluated using the QoS metrics, which are given in terms of service delay, packet/cell losses, and network utilization. Simulation results are presented by streaming ON/OFF and MPEG video data into the network. Results show that the proposed AC admits significantly more traffic compared to other available admission control schemes thereby guaranteeing high network utilization while maintaining the desired QoS.
  • Keywords
    Lyapunov methods; adaptive control; asynchronous transfer mode; discrete event systems; multimedia communication; neurocontrollers; quality of service; telecommunication congestion control; ATM; Lyapunov theory; MPEG video data; QoS metrics; adaptive bandwidth estimation scheme; admission controller dynamics; congestion controller dynamics; congestion indicator; discrete-event system; high network utilization; high-speed networks; hybrid system theory; multimedia services; neural network-based online adaptive bandwidth estimation; packet/cell losses; peak bit/cell rate estimate; quality of service; real-time discrete-event admission control scheme; service delay; Admission control; Bandwidth; Bioreactors; Control systems; Discrete event systems; High-speed networks; Performance loss; Quality of service; Stability; Streaming media;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control Applications, 2002. Proceedings of the 2002 International Conference on
  • Print_ISBN
    0-7803-7386-3
  • Type

    conf

  • DOI
    10.1109/CCA.2002.1040243
  • Filename
    1040243