Improved sample filtering method for measuring end-to-end path capacity

  • Li Wen-wei  (黎文伟)Email author
  • Tang Jun-long  (唐俊龙)
  • Zhang Da-fang  (张大方)
  • Xie Gao-gang  (谢高岗)


By analyzing the effect of cross traffic (CT) enforced on packet delay, an improved path capacity measurement method, pcapminp algorithm, was proposed. With this method, path capacity was measured by filtering probe samples based on measured minimum packet-pair delay. The measurability of minimum packet-pair delay was also analyzed by simulation. The results show that, when comparing with pathrate, if the CT load is light, both pcapminp and pathrate have similar accuracy; but in the case of heavy CT load, pcapminp is more accurate than Pathrate. When CT load reaches 90%, pcapminp algorithm has only 5% measurement error, which is 10% lower than that of pathrate algorithm. At any CT load levels, the probe cost of pcapminp algorithm is two magnitudes smaller than that of pathrate, and the measurement duration is one magnitude shorter than that of pathrate algorithm.

Key words

network measurement path capacity capacity measurement path delay 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    DOWNEY A. Using pathchar to estimate Internet link characteristics[C]// Proceeding of the 1999 ACM SIGCOMM Conference. Cambridge: ACM Press, 1999: 241–250.Google Scholar
  2. [2]
    LAI K, BAKER M. Measuring link bandwidths using a deterministic model of packet delay[C]// Proceeding of the 2000 ACM SIGCOMM Conference. Stockholm: ACM Press, 2000: 283–294.Google Scholar
  3. [3]
    CARTER R, CROVELLA M. Measuring bottleneck link speed in packet-switched networks[J]. Performance Evaluation, 1996, 27(8): 297–318.CrossRefGoogle Scholar
  4. [4]
    LAI K, BAKER M. Measuring bandwidth[C]// Proceeding of the 18th IEEE Conference on Computer Communications (INFOCOM). New York: IEEE Press, 1999: 235–245.Google Scholar
  5. [5]
    PAXSON V. Measurements and Analysis of End-to-End Internet Dynamics[D]. California: UC Berkeley, 1997.CrossRefGoogle Scholar
  6. [6]
    COSTANTINOS D, PARAMESWARAN R, DAVID M. What do packet dispersion techniques measure[C]// Proceeding of the 20th IEEE Conference on Computer Communications (INFOCOM). Anchorage: IEEE Press, 2001: 905–914.Google Scholar
  7. [7]
    COSTANTINOS D, PARAMESWARAN R, DAVID M. Packet dispersion techniques and a capacity estimation methodology[J]. IEEE/ACM Transaction on Network, 2004, 12(6): 963–977.CrossRefGoogle Scholar
  8. [8]
    LEE S, SHARMA P, BANERJEE S, et al. Measuring bandwidth between PlanetLab nodes[C]// Proceeding of the 2005 Passive and Active Measurement Workshop. Boston: Springer Press, 2005: 292–305.Google Scholar
  9. [9]
    RAVI P, CONSTANTINOS D, MARGARET M, et al. Bandwidth estimation: Metrics, measurement techniques, and tools[J]. IEEE Network, 2003, 17(6): 27–35.CrossRefGoogle Scholar
  10. [10]
    RAVI P, COSTANTINOS D, BRUCE A. The effect of layer-2 store-and-forward devices on per-hop capacity estimation[C]// Proceeding of the 22nd IEEE Conference on Computer Communications (INFOCOM). San Francisco: IEEE Press, 2003: 2090–2100.Google Scholar
  11. [11]
    JACOBSON V. Congestion avoidance and control[J]. ACM Computer Communication Review, 1988, 18(4): 314–329.CrossRefGoogle Scholar
  12. [12]
    LI W W, WANG J F, XIE G G, et al. An IPDV measurement method based-on packet-pair sampling[J]. Journal of Computer Research and Development, 2004, 41(8): 1354–1360. (in Chinese)CrossRefGoogle Scholar
  13. [13]
    THOMPSON K, MILLER G J, WILDER R. Wide-area internet traffic patterns and characteristics[J]. IEEE Network, 1997, 11(6): 10–23.CrossRefGoogle Scholar
  14. [14]
    PAPAGIANNAKI K, MOON S, FRALEIGH C. Measurement and analysis of single-hop delay on an IP backbone network[J]. IEEE Journal on Selected Areas in Communications, 2003, 21(6): 908–921.CrossRefGoogle Scholar

Copyright information

© Published by: Central South University Press, Sole distributor outside Mainland China: Springer 2007

Authors and Affiliations

  • Li Wen-wei  (黎文伟)
    • 1
    Email author
  • Tang Jun-long  (唐俊龙)
    • 2
  • Zhang Da-fang  (张大方)
    • 1
  • Xie Gao-gang  (谢高岗)
    • 3
  1. 1.School of SoftwareHunan UniversityChangshaChina
  2. 2.Department of Physics and Electronic ScienceChangsha University of Science and TechnologyChangshaChina
  3. 3.Institute of Computing TechnologyChinese Academy of SciencesBeijingChina

Personalised recommendations