Advertisement

On the Identifiability of Link Service Curves from End-Host Measurements

  • Amr Rizk
  • Markus Fidler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5425)

Abstract

We estimate service curves of network internal links from end-host measurements of probing traffic. Our approach belongs to the field of network tomography, which deals with the fundamental challenge of identifiability in a priori under-determined network equation systems. As opposed to recent methods that estimate sole quantities, such as delay and bandwidth, we characterize links using the more generic concept of service curve that comprises various derived quantities including the ones mentioned above. Key to our solution is the Legendre-Fenchel transform that achieves additivity of link service curves. Our measurement results reveal that the burstiness of cross traffic flows, which has significant impact on the shape of leftover service curves, can be attributed to individual links. Using the network calculus we show fundamental limits of certain tomography approaches regarding the identification of propagation delays as well as regarding the resolution of post-narrow links.

Keywords

Individual Link Path Measurement Small Packet Bandwidth Estimate Network Tomography 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Caceres, R., Duffield, N.G., Horowitz, J., Towsley, D.: Multicast-based inference of network-internal loss characteristics. IEEE Trans. Inform. Theory 45(7), 2462–2480 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Chang, C.-S.: Performance Guarantees in Communication Networks. Springer, Heidelberg (2000)CrossRefzbMATHGoogle Scholar
  3. 3.
    Coates, M., Hero, A., Nowak, R., Yu, B.: Internet tomography. IEEE Signal Processing Magazine 19(3), 47–65 (2002)CrossRefGoogle Scholar
  4. 4.
    Cruz, R.L.: A calculus for network delay, Part I and Part II. IEEE Trans. Inform. Theory 37(1), 114–141 (1991)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Fidler, M., Recker, S.: Conjugate network calculus: A dual approach applying the legendre transform. Computer Networks 50(8), 1026–1039 (2006)CrossRefzbMATHGoogle Scholar
  6. 6.
    Fidler, M., Schmitt, J.B.: On the way to a distributed systems calculus: A network calculus with data scaling. In: ACM SIGMETRICS, June 2006, pp. 287–298 (2006)Google Scholar
  7. 7.
    Harfoush, K., Bestavros, A., Byers, J.: Measuring bottleneck bandwidth of targeted path segments. In: IEEE INFOCOM, April 2003, pp. 2079–2089 (2003)Google Scholar
  8. 8.
    Jain, M., Dovrolis, C.: End-to-end available bandwidth: Measurement methodology, dynamics, and relation with TCP throughput. IEEE/ACM Trans. Networking 11(4), 537–549 (2003)CrossRefGoogle Scholar
  9. 9.
    Lai, K., Baker, M.: Measuring link bandwidths using a deterministic model of packet delay. In: ACM SIGCOMM, October 2000, pp. 283–294 (2000)Google Scholar
  10. 10.
    Le Boudec, J.-Y., Thiran, P.: Network Calculus A Theory of Deterministic Queuing Systems for the Internet. Springer, Heidelberg (2001)zbMATHGoogle Scholar
  11. 11.
    Lhommeau, M., Hardouin, L., Ferrier, J.-L., Ouerghi, I.: Interval analysis in dioid: Application to robust open-loop control for timed event graphs. In: CDC - ECC 2005, December 2005, pp. 7744–7749 (2005)Google Scholar
  12. 12.
    Liebeherr, J., Fidler, M., Valaee, S.: Min-plus system interpretation of bandwidth estimation. In: Proc. IEEE INFOCOM (May 2007)Google Scholar
  13. 13.
    Liebeherr, J., Fidler, M., Valaee, S.: A system theoretic approach to bandwidth estimation. Technical Report arXiv:0801.0455v1 (January 2008)Google Scholar
  14. 14.
    Parekh, A.K., Gallager, R.G.: A generalized processor sharing approach to flow control in integrated services networks: The single-node case. IEEE/ACM Trans. Networking 1(3), 344–357 (1993)CrossRefGoogle Scholar
  15. 15.
    Pasztor, A., Veitch, D.: Active probing using packet quartets. In: ACM IMC, November 2002, pp. 293–305 (2002)Google Scholar
  16. 16.
    Presti, F.L., Duffield, N., Horowitz, J., Towsley, D.: Multicast-based inference of network-internal delay distributions. IEEE/ACM Trans. Networking 10(6), 761–775 (2002)CrossRefzbMATHGoogle Scholar
  17. 17.
    Ribeiro, V., Riedi, R., Baraniuk, R.: Locating available bandwidth bottlenecks. IEEE Internet Computing 8(5), 34–41 (2004)CrossRefGoogle Scholar
  18. 18.
    Rizk, A.: Network tomography using min-plus system theory. Master’s thesis, TU Darmstadt (March 2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Amr Rizk
    • 1
  • Markus Fidler
    • 1
  1. 1.Multimedia Communications LabTU DarmstadtGermany

Personalised recommendations