Skip to main content

Bandwidth Allocation Management Based on Neural Networks Prediction for VoD System Providers

  • Conference paper
Service Assurance with Partial and Intermittent Resources (SAPIR 2004)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 3126))

  • 574 Accesses

Abstract

Video and LAN traffics can be modelled as self-similar processes and the Hurst parameter is a measure of the self-similarity of a process. The purpose of this work is to use this characteristic of Internet traffic to optimise the bandwidth utilization and consequently the network cost of Video on Demand Service Providers (VDSP). The work refers to one aspect of a global project that specifies intelligent agent architecture to manage the relationship among VDSP, Internet Service Providers (ISPs) and end-customers. In this paper, we also discuss the egress traffic aspect of the VDSP and propose a neural network approach to monitor and to estimate the nature of the egress traffic using the Hurst parameter. This approach takes into account the real MPEG-4 (Moving Picture Experts Group) streams with flow aggregated.

This work has been supported by CAPES (Brazil) under grant number 266/99-I.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Park, K., Willinger, W.: Self Similar Network Traffic and Performance Evaluation. Willey, Chichester (2000)

    Book  Google Scholar 

  2. Garrett, M., Willinger, W.: Analysis, modeling and generation of self-similar VBR traffic. In: Proceedings of ACM/SIGCOMM 1994, London, UK, pp. 269–280 (August 1994)

    Google Scholar 

  3. Beran, J., et al.: Long-range dependence in variable-bit-rate video traffic. IEEE Transactions on Communications 43, 1566–1579 (1995)

    Article  MathSciNet  Google Scholar 

  4. Paxson, V., Floyd, S.: Wide-Area Traffic: The Failure of Poisson Modelling. In: SIGCOMM 1994, pp. 257–268 (August 1994)

    Google Scholar 

  5. Mayor, G., Silvester, J.: A Trace-Driven Simulation of an ATM Queueing System with Real Network Traffic. In: Proc. of IEEE ICCCN, pp. 28–32 (October 1996)

    Google Scholar 

  6. Mayor, G., Silvester, J.: An ATM Queueing System with a Fractional Brownian Noise Arrival Process. In: Proc. of IEEE ICC, pp. 1607–1611 (1996)

    Google Scholar 

  7. Norros, I.: A Storage Model with Self-Similar Input. Queueing Systems 16, 387–396 (1994)

    Article  MATH  MathSciNet  Google Scholar 

  8. Taqqu, M., Teverovsky, V., Willinger, W.: Estimators for Long-Range Dependence: an Empirical Study. Fractals 3(4), 785–788 (1995)

    Article  MATH  Google Scholar 

  9. Leland, W., Taqqu, M., Willinger, W., Wilson, D.: On the Self-Similar Nature of Ethernet Traffic (Extended Version). IEEE/ACM Transaction on Networking 2(1), 1–15 (February 1994)

    Article  Google Scholar 

  10. Norros, I.: On the use of Fractional Brownian Motion in the Theory of Connectionless Networks. IEEE Journal on Selected Areas in Communications 13(6), 953–962 (August 1995)

    Article  Google Scholar 

  11. Hect-Nielsen, R.: Neurocomputing. Addison-Wesley Publishing Company, Reading (1990)

    Google Scholar 

  12. Fausset, L.: Fundamentals of Neural Networks. Prentice-Hall International, New Jersey (1994)

    Google Scholar 

  13. Fitzejk, F., Reisslen, M.: MPEG-4 and H-D62 Video Traces for Network Performance, http://www-tkn.ee.tu-berlin.de/research/trace/trace.html

  14. Joone - Java Oriented Object Neural Engine - User Manual, Version 1.0 beta http://www.jooneworld.com/

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Gomes, D.G., Agoulmine, N., de Souza, J.N. (2004). Bandwidth Allocation Management Based on Neural Networks Prediction for VoD System Providers. In: Dini, P., Lorenz, P., de Souza, J.N. (eds) Service Assurance with Partial and Intermittent Resources. SAPIR 2004. Lecture Notes in Computer Science, vol 3126. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27767-5_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-27767-5_4

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-22567-6

  • Online ISBN: 978-3-540-27767-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics