Estimating Link Capacity in High Speed Networks

  • Ling-Jyh Chen
  • Tony Sun
  • Li Lao
  • Guang Yang
  • M. Y. Sanadidi
  • Mario Gerla
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3976)


Knowledge of bottleneck capacity of an Internet path is critical for efficient network design, management, and usage. With emerging high speed Internet links, most traditional estimation techniques are limited in providing fast and accurate capacity estimations. In this paper, we propose a new technique, called PBProbe, to estimate high speed links. PBProbe is based on CapProbe; however, instead of solely relying on packet pairs, PBProbe employs a “packet bulk” technique and adapts the bulk length in order to overcome the well known problem with packet pair based approaches, namely the lack of accurate timer resolution. As a result, PBProbe not only preserves the simplicity and speed of CapProbe, but it also correctly estimates link capacities within a much larger range. Using analysis, we evaluate PBProbe with various bulk lengths and network configurations. We then perform emulation and Internet experiments to verify the accuracy and speed of PBProbe on high speed links. The results show that PBProbe is consistently fast and accurate in the great majority of test cases.


Link Capacity High Speed Network Capacity Estimation Packet Overhead Internet Experiment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Clink: a tool for estimating internet link characteristics,
  2. 2.
    Pchar: A tool for measuring internet path characteristics,
  3. 3.
    Dovrolis, C., Ramanathan, P., Moore, D.: What do packet dispersion techniques measure? In: IEEE Infocom (2001)Google Scholar
  4. 4.
    Jacobson, V.: Pathchar: A tool to infer characteristics of internet paths, Available,
  5. 5.
    Kapoor, R., Chen, L.-J., Lao, L., Gerla, M., Sanadidi, M.Y.: Capprobe: A simple and accurate capacity estimation technique. In: ACM SIGCOMM (2004)Google Scholar
  6. 6.
    Lai, K., Baker, M.: Measuring bandwidth. In: IEEE Infocom, pp. 235–245 (1999)Google Scholar
  7. 7.
    Saroiu, S., Gummadi, P.K., Gribble, S.D.: Sprobe: A fast technique for measuring bottleneck bandwidth in uncooperative environments. In: IEEE Infocom (2002)Google Scholar
  8. 8.
    Chen, L.-J., Sun, T., Yang, G., Sanadidi, M.Y., Gerla, M.: End-to-end asymmetric link capacity estimation. In: IFIP Networking (2005)Google Scholar
  9. 9.
    Lin, Y., Wu, H., Cheng, S., Wang, W., Wang, C.: Measuring asymmetric link bandwidths in internet using a multi-packet delay model. In: IEEE ICC (2003)Google Scholar
  10. 10.
    Chen, L.-J., Sun, T., Yang, G., Sanadidi, M.Y., Gerla, M.: Adhoc probe: Path capacity probing in ad hoc networks. In: WICON (2005)Google Scholar
  11. 11.
    Jin, G., Tierney, B.: System capability effect on algorithms for network bandwidth measurement. In: ACM IMC (2003)Google Scholar
  12. 12.
    Kapoor, R., Chen, L.-J., Sanadidi, M.Y., Gerla, M.: Accuracy of link capacity estimates using passive and active approaches with capprobe. In: IEEE ISCC (2004)Google Scholar
  13. 13.
    Lai, K., Baker, M.: Measuring link bandwidths using a deterministic model of packet delay. In: ACM SIGCOMM (2000)Google Scholar
  14. 14.
    Lee, S.-J., Sharma, P., Banerjee, S., Basu, S., Fonseca, R.: Measuring bandwidth between planetlab nodes. In: PAM (2005)Google Scholar
  15. 15.
    Savage, S.: Sting: a tcp-based network measurement tool. In: USENIX Symposium on Internet Technologies and Systems (1999)Google Scholar
  16. 16.
    Lakshminarayanan, K., Padmanabhan, V.N., Padhye, J.: Bandwidth estimation in broadband access networks. In: IMC (2004)Google Scholar
  17. 17.
    Prasad, R., Jain, M., Dovrolis, C.: Evaluating pathrate and pathload with realistic cross-traffic (2003), Bandwidth Estimation Workshop, Available,
  18. 18.
    Chen, L.-J., Sun, T., Xu, D., Sanadidi, M.Y., Gerla, M.: Access link capacity monitoring with tfrc probe. In: E2EMON (2004)Google Scholar
  19. 19.
  20. 20.
    Nistnet: network emulation package,
  21. 21.
    Cenic network statistics,

Copyright information

© IFIP International Federation for Information Processing 2006

Authors and Affiliations

  • Ling-Jyh Chen
    • 1
  • Tony Sun
    • 2
  • Li Lao
    • 2
  • Guang Yang
    • 2
  • M. Y. Sanadidi
    • 2
  • Mario Gerla
    • 2
  1. 1.Institute of Information ScienceAcademia SinicaTaipeiTaiwan
  2. 2.Department of Computer ScienceUCLALos AngelesUSA

Personalised recommendations