An implementation of the dynamic rate leaky bucket algorithm combined with a neural network based prediction

신경회로망 예측기법을 결합한 Dynamic Rate Leaky Bucket 알고리즘의 구현

  • Published : 1997.02.01


The advent of B-ISDN using ATM(asynchronous transfer mode) made possible a variety of new multimedia services, however it also created a problem of congestion control due to bursty nature of various traffic sources. To tackle this problem, UPC/NPC(user parameter control/network parameter control) have been actively studied and DRLB(dynamic rate leaky bucket) algorithm, in which the token generation rate is changed according to states of data source andbuffer occupancy, is a good example of the UPC/NPC. However, the DRLB algorithm has drawbacks of low efficiency and difficult real-time implementation for bursty traffic sources because the determination of token generation rate in the algorithm is based on the present state of network. In this paper, we propose a more plastic and effective congestion control algorithm by combining the DRLB algorithm and neural network based prediction to remedy the drawbacks of the DRLB algorithm, and verify the efficacy of the proposed method by computer simulations.



  1. Blue Book Recommendation Ⅰ.121 Vol.Ⅲ.7 Broadband aspects of ISDN CCITT Study Group ⅩⅦ
  2. 광대역 정보통신 이병기;강민호;이종희
  3. IEEE Jour. sel. Areas in Commun. v.9 no.2 Performance analysis of a control throttle where tokens and jobs queue A. W. Berger
  4. IEEE Trans. Automatic Control v.9 no.2 Over load control using rate control throttle:selecting token bank capacity for robustness to arrival rates A. W. Berger
  5. Proc. Int'l Conf. on Commun. v.1 Design of leaky bucket access control schemes in ATM networks H. J. Chao
  6. IEEE Jour. Sel. Areas in Commun. v.9 no.3 Effectiveness of leaky bucket policing mechanism in ATM networks M. Butto;E. Cavellero;A. Tonietti
  7. Draft Recommendation Ⅰ.150 Report R 23-E B-ISDN ATM functional characteristic CCITT Study Group ⅩⅦ
  8. Computer Networks and ISDN Systems v.25 Perormance analysis of leaky-bucket bandwidth enforcement strategy for bursty traffics in an ATM network Y. H. Kim;B. C. Shin;C. K. Un
  9. Electr. Letter v.29 no.17 Performance of dynamic rate leaky bucket algorithm J. Y. Lee;C. K. Un
  10. 1993년도 한국통신학회 하계종합학술발표회 논문집 리키버킷을 사용한 B-ISDN 중간 노드의 성능 평가 강상욱;정남진;홍성찬;여현;최승철
  11. IEEE Commun. Mag. v.30 no.7 Congestion control methods for BISDN S. Yazid;H. T. Mouftah
  12. Proc. IEEE Globecom Characterization of packetized voice traffic in ATM networks using neural networks A. Taraff;W. Habib;N. Saadawi
  13. Proc. IEEE Globecom v.2 Traffic prediction using neural networks E. S. Yu;C. Y. Chen
  14. Neural Networks v.2 Multilayer feedforward networks are universal approximators K. Hornik;M. Stinchcombe;H. White
  15. Neural Networks v.2 On the approximate realization of continuous mappings by neural networks K. Funahashi
  16. Mathematics of Contr., Signal and Syst. v.2 Approximation by superpositions of a sigmoidal function G. Cybenko
  17. IEEE Jour. Sel. Areas in Commun. v.4 no.6 A Markov modulated characterization of packetized voice and data traffic and related statistical multiplexer performance H. Heffes;D. Lucantoni
  18. IEEE Jour. Sel. Areas in Commun. v.9 no.3 Modeling and performance comparison of policing mechanisms for ATM networks E. P. Rathgeb
  19. Asnchronous Transfer Mode Networks: performance Issues R. O. Onvural
  20. Neural Networks-A Comprehensive Foundation S. Haykin
  21. 1996년도 한국통신학회 추계종합학술발표회 논문집 ATM 망에서 VBR 신호에 대한 신경회로망 예측 기법 기반의 continuous rate leaky bucket 알고리즘의 구현 이두헌;신요안;김영한
  22. Proc. 4th Int'I Workshop on Packet Video Congestion cotrol strategies for packet video M. W. Garret;M. Vetterli