We use cookies to improve your experience with our site.

Indexed in:

SCIE, EI, Scopus, INSPEC, DBLP, CSCD, etc.

Submission System
(Author / Reviewer / Editor)
Advanced Search
Volume 21 Issue 6
November  2006
Turn off MathJax
Article Contents
Abstract
References
Qi-Jin Ji, Yong-Qiang Dong. Design and Analysis of a Multiscale Active Queue Management Scheme[J]. Journal of Computer Science and Technology, 2006, 21(6): 1022-1030.
Citation: Qi-Jin Ji, Yong-Qiang Dong. Design and Analysis of a Multiscale Active Queue Management Scheme[J]. Journal of Computer Science and Technology, 2006, 21(6): 1022-1030.
shu

Design and Analysis of a Multiscale Active Queue Management Scheme

  • School of Computer Science and Engineering, Southeast University, Nanjing 210096, P.R. ChinaKey Laboratory of Computer Network and Information Integration of Ministry of Education, Southeast University, Nanjing 210096, P.R. China

More Information
  • Received Date: March 22, 2005
  • Revised Date: May 14, 2006
  • Published Date: November 14, 2006
    Abstract
  • Since Internet is dominated by TCP-basedapplications, active queue management (AQM) is considered as aneffective way for congestion control. However, most AQM schemes sufferobvious performance degradation with dynamic traffic. Extensivemeasurements found that Internet traffic is extremely bursty andpossibly self-similar. We propose in this paper a new AQM scheme calledmultiscale controller (MSC) based on the understanding of trafficburstiness in multiple time scale. Different from most of other AQMschemes, MSC combines rate-based and queue-based control in two timescales. While the rate-based dropping on burst level (large timescales) determines the packet drop aggressiveness and is responsiblefor low and stable queuing delay, good robustness and responsiveness,the queue-based modulation of the packet drop probability on packetlevel (small time scales) will bring low loss and high throughput.Stability analysis is performed based on a fluid-flow model of theTCP/MSC congestion control system and simulation results show that MSCoutperforms many of the current AQM schemes.
    • FullText(HTML)
    • References (24)
  • [1]
    Jacobson V. Congestion avoidance and control. In -\it Proc. ACM SIGCOMM'88}, Stanford, USA, Sept.~1988, pp.314--329.
    [2]
    Braden B, Clark D, Crowcroft J -\it et al}. Recommendations on queue management and congestion avoidance in the Internet. IETF RFC 2309, April 1998.
    [3]
    Floyd S, Kohler E. Internet research needs better models. -\it ACM Comput. Commun. Rev}., Jan. 2003, 33(1): 29--34.
    [4]
    Hui J Y. Resource allocation for broadband networks. -\it IEEE J. Select. Areas in Commun}., Dec. 1988, 6(9): 1598--1608.
    [5]
    Riedi R H, Willinger W. Toward an Improved Understanding of Network Traffic Dynamics. Self-Similar Network Traffic and Performance Evaluation, New York: John Wiley \& Sons, 2000.
    [6]
    Floyd S, Jacobson V. Random early detection gateways for congestion avoidance. -\it IEEE/ACM Trans. Net.}, Aug. 1993, 1(4): 397--413.
    [7]
    Floyd S, Gummadi R, Shenker S. Adaptive RED: An algorithm for increasing the robustness of RED's active queue management. Aug. 2001, http://www. icir.org/floyd/papers/adaptiveRed.pdf.
    [8]
    Feng W C, Kandlur D, Saha D -\it et al}. Blue: A new class of active queue management algorithms. Technical Report, CSE-TR-387-99, UM, 1999.
    [9]
    Kunniyur S, Srikant R. Analysis and design of an adaptive virtual queue (AVQ) algorithm for active queue management. In -\it Proc. ACM SIGCOMM'01}, San Diego, CA, Aug. 2001, pp.123--134.
    [10]
    Floyd S. TCP and explicit congestion notification. -\it ACM Comput. Commun. Rev}., Oct. 1994, 24: 10--23.
    [11]
    Athuraliya S, Low S, Li V -\it et al.} REM: Active queue management. -\it IEEE Network Magazine}, May 2001, 15: 48--53.
    [12]
    Hollot C V, Misra V, Towsley D -\it et al}. On designing improved controllers for AQM routers supporting TCP flows. In -\it Proc. IEEE INFOCOM'01}, Anchorage, 2001, 3: 1726--1734.
    [13]
    Kwon M, Fahmy S. A comparison of load-based and queue-based active queue management algorithms. In -\it Proc. SPIE ITCom}, Aug. 2002, 4866: 35--46.
    [14]
    Gao Y, He G, Hou J. On exploiting traffic predictability in active queue management. In -\it Proc. IEEE INFOCOM'02}, New York, USA, June 2002, pp.1360--1369.
    [15]
    Gao Y, Hou J C. A state feedback control approach to stabilizing queues for ECN-enabled TCP flows. In -\it Proc. IEEE INFOCOM}, San Francisco, CA, 2003, 3: 2301--2311.
    [16]
    Ji Q, Dong Y. Performance evaluation of active queue management schemes: A comparative study. -\it Journal of Communications}, Nov. 2005, 26(11): 100--105, 111. (In Chinese)
    [17]
    Sang A, San-qi Li. A predictability analysis of network traffic. In -\it Proc. INFOCOM 2000}, Tel Aviv, Israel, March 26--30, 2000, 1: 342--351.
    [18]
    Stoica I, Shenker S, Zhang H. Core-stateless fair queuing: Achieving approximately fair bandwidth allocations in high speed networks. In -\it Proc. ACM SIGCOMM'98}, Vancouver, Sept. 1998, pp.118--130.
    [19]
    Tuan T, Park K. Multiple time scale congestion control for self-similar network traffic. -\it Perf. Eval}., 1999, 36: 359--386.
    [20]
    Misra V, Gong W B, Towsley D. Fluid-based analysis of a network of AQM routers supporting TCP flows with an application to RED. In -\it Proc. ACM/SIGCOMM}, Stockholm, Sweden, 2000, pp.151--160.
    [21]
    Hollot C, Misra V, Towsley D -\it et al}. A control theoretic analysis of RED. In -\it Proc. IEEE INFOCOM}, Anchorage, 2001, 3: 1510--1519.
    [22]
    Hollot C, Misra V, Towsley D -\it et al}. Analysis and design of controllers for AQM routers supporting TCP flows. -\it IEEE Trans. Automatic Control}, Jun. 2002, 47: 945--959.
    [23]
    NS-2 Network Simulator. -http://www.isi.edu/nsnam/ns/}.
    [24]
    Crovella E, Bestavros A. Self-similarity in World Wide Web traffic: Evidence and possible causes. -\it IEEE/ACM Trans. Networking}, Dec. 1997, 5(6): 836--846.
    • Relative Articles
  • Supplements (0)

Catalog

    Get Citation
    XML
    Article views (15) PDF downloads (1216) Cited by()
    Related

    Copyright ©2025 JCST, All Rights Reserved     京ICP备05002829号-1

    Institute of Computing Technology, Chinese Academy of Sciences
    P.O. Box 2704, Beijing 100190, P.R. China

    Tel.: 86-10-62610746 E-mail: jcst@ict.ac.cn

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return