Advertisement

Telecommunication Systems

, Volume 5, Issue 2, pp 273–301 | Cite as

Bandwidth efficiency of the networking broadband services architecture: A case study

  • M. Peyravian
  • L. Gün
Article
  • 20 Downloads

Abstract

IBM's networking broadband services (NBBS) is a unique network control point architecture capable of managing both asynchronous transfer mode (ATM) networks as well as more generic fast packet networks with variable size packets. The NBBS traffic management functions provide value-added enhanced variable bit rate (VBR) services based on statistical traffic descriptors in addition to providing ATM Forum compliant VBR services based on deterministic rule-based traffic descriptors. In this paper, we first summarize NBBS traffic management functions that are relevant to our study. These include traffic estimation, monitoring, policing and dynamic bandwidth adaptation procedures. The NBBS traffic estimation and adaptation module has a novel feature that continuously monitors the source traffic and dynamically adjusts the bandwidth reserved in the network links for the network connection when it detects a significant change in the connection traffic characteristics. The main contribution of this paper is to integrate all these functions in a trace driven simulation experiment to study their aggregate effect in a general network setting using actual traffic traces. Based on observed SNA, TCP, and compressed video traces we observed that NBSS dynamic bandwidth adaptation function provides a three-fold savings in bandwidth use compared to static peak bandwidth allocation in our case study. Our study also provides useful insights into network dimensioning problem in order to achieve a desired level of network availability for different services. Finally, we provide a simple formula for estimating the amount of bandwidth savings achieved through dynamic bandwidth adaptation versus static peak bandwidth allocation in a general network setting by making a comparison on the individual traces in isolation.

Keywords

Asynchronous Transfer Mode Source Traffic Bandwidth Efficiency Traffic Trace Network Availability 
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]
    W.P. Lovegrove and J.L. Hammond, Simulation methods for studying nonstationary behavior of computer networks, IEEE J. Select. Areas Commun. 8 (1990) 1696–1708.Google Scholar
  2. [2]
    M. Peyravian, Providing different levels of network availability in high-speed networks,Proc. GLOBECOM '94 (1994) pp. 941–945.Google Scholar
  3. [3]
    R.E. Walpole and R.H. Myers,Probability and Statistics for Engineers and Scientists (Macmillan, New York, 1985).Google Scholar
  4. [4]
    L. Gün and R. Guérin, Bandwidth management and congestion control framework of the broadband network architecture, Comp. Networks and ISDN Syst. 26 (1993) 61–78.Google Scholar
  5. [5]
    M. Peyravian and R. Onvural, Network throughput versus routing frequency update in ATM networks, IBM Technical Report TR29.1898, Research Triangle Park, NC (1994).Google Scholar
  6. [6]
    M. Butto, E. Cavallero and A. Tonietti, Effectiveness of the leaky bucket policing mechanism in ATM networks, IEEE J. Select. Areas Commun. 9(3) (1991).Google Scholar
  7. [7]
    I. Cidon, I. Gopal, M. Kaplan and S. Kutten, Distributed control for PARIS,Proc. 9th Ann. ACM Symp. on Principles of Distributed Computing (1990) pp. 145–160.Google Scholar
  8. [8]
    T. Tedijanto and L. Gün, Effectiveness of dynamic bandwidth management mechanisms in ATM networks,Proc. INFOCOM '93 (1993) pp. 358–367.Google Scholar
  9. [9]
    M. Peyravian, Broadband network services bandwidth adaptation performance, IBM Technical Report TR29.1916, Research Triangle Park, NC (1994).Google Scholar
  10. [10]
    R. Guérin and L. Gün, A unified approach to bandwidth allocation and access control in fast packet-switched networks,Proc. INFOCOM '92 (1992) pp. 1–12.Google Scholar
  11. [11]
    I. Gün, An approximation method for capturing complex traffic behavior in high-speed networks, Perform. Eval. 19 (1994) 5–23.Google Scholar
  12. [12]
    M. Decina, T. Toniatti, P. Vaccari and L. Verri, Bandwidth assignment and virtual call blocking in ATM networks,Proc. INFOCOM '90 (1990) pp. 881–888.Google Scholar
  13. [13]
    I. Cidon, R. Guérin and A. Khamisy, Protective buffer management policies,Proc. INFOCOM '92 (1993) pp. 1051–1058.Google Scholar
  14. [14]
    R. Guérin, H. Ahmadi and M. Naghshineh, Equivalent capacity and its application to bandwidth allocation in high speed networks, IEEE J. Select. Areas Commun. 9 (1991) 968–981.Google Scholar
  15. [15]
    P.W. Tse and M. Zukerman, Connection admission control in ATM networks,Proc. INFOCOM '92 (1994) pp. 1790–1794.Google Scholar
  16. [16]
    S.Q. Li, S. Chong, C. Hwang and X. Zhao, Link capacity allocation and network control by filtered input rate in high speed networks,Proc. GLOBECOM '93 (1993) pp. 744–750.Google Scholar

Copyright information

© J.C. Baltzer AG, Science Publishers 1996

Authors and Affiliations

  • M. Peyravian
    • 1
  • L. Gün
    • 2
  1. 1.IBM, Networking SystemsResearch Triangle ParkUSA
  2. 2.Motorola, Networking ResearchMansfieldUSA

Personalised recommendations