Performance of the Neural network controlled ATM switch

  • V. M. Skulic
  • Z. R. Petrovic
Part of the IFIP — The International Federation for Information Processing book series (IFIPAICT)


In this paper a new N×N space division ATM switch architecture based on banyan and neural network is presented. The switching function is performed by extended banyan network and the neural network controller is introduced to allow the recirculation of the misrouted cells. The paper analyses the switching performances, especially cell loss probability, and shows the advantages of the proposed switch.


Banyan HOL blocking recirculation neural network 


  1. Brown T.X. and Liu K.H. (1990) Neural Network Design of a Banyan Network Controller. IEEE Journal on Selected Areas in Communications, vol. 8 no. 8, 1428–38.Google Scholar
  2. Giacomazzi P. and Pattavina A. (1996) Performance Analysis of the ATM Shuffleout Switch Under Arbitrary Nonuniform Traffic Patterns, IEEE Transactions on Communications, vol. 44 no. 11.Google Scholar
  3. Hopfield J.J. and Tank D.W. (1985) Neural computation decisions in optimisation problems. Biological Cybern., vol. 52, 141–52.MathSciNetzbMATHGoogle Scholar
  4. Karol M.J, Hluchuj M.G. and Morgan S.P. (1987) Input vs. output queueing on space-division packet switch. IEEE Transactions on Communications, vol. COM-35, 1347–56.Google Scholar
  5. Tobagi F.A, Kwok T. and Chiussi F.M. (1991) Architecture, Performance, and Implementation of the Tandem Banyan Fast Packet Switch. IEEE Journal on Selected Areas in Communications, vol. 9 no.8, 1173–93.Google Scholar
  6. Urushidani S. (1991) Rerouting Network: A High-Performance Self-Routing Switch for B-ISDN. IEEE Journal on Selected Areas in Communications, vol. 9 no. 8, 1194–204.Google Scholar
  7. Park Y.K, Cherkassky V. and Lee G. (1994) Omega Network-Based ATM Switch with Neural Network-Controlled Bypass Queueing and Multiplexing. IEEE Journal on Sel. Areas in Communications, vol. 12 no. 9.Google Scholar
  8. Petrovic Z.R, Skulic V.M. and Cvetinovic M. (1997) Performance of the new ATM switch for B-ISDN. J.C.Baltzer Telecommunication Systems, vol. 7, 379–90.CrossRefGoogle Scholar
  9. Schwartz M. (1996) Broadband Integrated Networks. Prentice Hall, New Jersey.Google Scholar
  10. Skulic V.M. and Petrovic Z.R. (1997) Neural network controlled ATM switch, different types of traffic. Proceedings of Telsiks ‘87, Nis, Yugoslavia, 807–10Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1998

Authors and Affiliations

  • V. M. Skulic
    • 1
  • Z. R. Petrovic
    • 1
  1. 1.Faculty of Electrical EngineeringUniversity of BelgradeBelgradeYugoslavia

Personalised recommendations