• DocumentCode
    2873842
  • Title

    Delay Performance of Load-Balanced Packet Switching under Different Traffic Patterns

  • Author

    Hui Li ; Bing-Rui Wang ; Hui-Yao An ; Li Yu ; Wei Wang ; Jia-Qing Huang ; Peng Yi ; Bin-Qiang Wang

  • Author_Institution
    Key Lab. of Integrated Microsyst., Peking Univ., Shenzhen, China
  • Volume
    2
  • fYear
    2009
  • fDate
    18-19 July 2009
  • Firstpage
    402
  • Lastpage
    406
  • Abstract
    A concentrator-based load balancing multi-path self routing switching fabric(LB-MPSR-C) was proposed recently, which was based on sorting concentrators, load-balanced and Birkhoff von-Neumann switching theory. This structure can achieve 100% throughput under admissible traffic pattern, its scalability for super large scale switching system and property of lowest hardware complexity have been deeply studied. This paper will focus on its delay performance under various traffic patterns. Compared with the output-buffer and load balanced Birkhoff-von Neumann structures, LB-MPSR-C has better delay performance under uniform burst traffic, especially under large scale and heavy traffic condition. Because practical network traffics are burst, it means that LB-MPSR-C is more suitable for building large scale switching systems.
  • Keywords
    buffer storage; packet switching; resource allocation; telecommunication network routing; telecommunication traffic; Birkhoff von-Neumann switching theory; admissible traffic pattern; concentrator-based load balancing; delay performance; large scale switching system; load-balanced packet switching; multipath self routing switching fabric; output-buffer; uniform burst traffic; Delay; Large-scale systems; Load management; Packet switching; Routing; Scalability; Sorting; Switching systems; Telecommunication traffic; Throughput; component; delay analysis; switching structure;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
  • Conference_Location
    Shenzhen
  • Print_ISBN
    978-0-7695-3699-6
  • Type

    conf

  • DOI
    10.1109/APCIP.2009.290
  • Filename
    5197222