ATM망에서의 실시간 통화유랑 예측에 관한 연구

A Study on The Real-time Prediction of Traffic Flow in ATM Network

  • 김윤석 (상지영서대학 전자과) ;
  • 진용옥 (경희대학교 전자정보학부)
  • 발행 : 2000.10.01

초록

본 논문은 ATM망의 통화유랑 제어중 최적한 폭주제어의 실현을 위해 필수적인 다중매체 통화유량 예측에 관한 논문으로서 ATM망에 유입 될 다중매체 통화유량의 특성이 시대의 발전에 따라 서서히 변화될 것이 예상되므로 모의실험에 사용 될 다중매체 통화유랑을 단위시간당 접속호수는 프아송분포, 각 호당 요구전송속도는 감마분포, 각 호의 유지시간은 지수분포를 기준으로 하여 각각의 분포특성을 변화시켜 통화유량 특성변화를 유도하여 발생시킨 후 이를 신경망과 실시간 처리를 위해 제안된 3중신경망 모델[3]로 추정하여 비교함으로써 제안된 모델이 ATM망의 통화유량 예측에 이용될 수 있음을 보인다.

this paper is a stucy onthe preductionof multi-media traffic flow for the realizationof optimum ATM congestion control. In ATM network it is expected that the characteristic of multi-media traffic flow is varied slowly with a time. Fjor the simulation, time-variable multi-media traffic is penerated using possion distribution(connect calls per process time).\, gamma distribution(transmission rate per a call) and exponential distribution(holding time per a call). And using back-propagation neural netwok and proposed tripple neural network, the simulation to predict generaed traffic is executed. From the result,it's capability is shown that the proposed neural network model can be used in the predictionof ATM traffic flow.

키워드

참고문헌

  1. A A. Lazer and G Pacifici, 'Control of resources in broadband networks with quality of services guarantees,' IEEE Communication Magazine, pp 66-73, October 1991 https://doi.org/10.1109/35.99263
  2. Alberto Leon-Garcia, 'Probability and Random Processes for Electrical Engineering', Addison Wesley, 1989
  3. 김윤석, '신경망을 이용한 다중매체 통화량 예측에 관한 연구' 한국통신학회논문지 제24권 제12T호,1999.12
  4. S.Y.yosef, C. M. Strange and J. A. Schormans, 'ATM modelling: Parameterisation of 4-phase MMPP model for admission control of superposed traffic sources,' ELECTRONIC LETTERS, Vol.33, No.10, pp.829-830, 8th May 1997 https://doi.org/10.1049/el:19970573
  5. Edmund S. Yu and C. Y Roger CHen, 'Traffic Prediction Using Neural Network,' Proceeding of Globecom, Vol.2., pp.991-995,1993 https://doi.org/10.1109/GLOCOM.1993.318226
  6. B. Maglaris, D. Anastassiou, P. sen, G. Karlsson and J. D Robbins, 'Performance models of statistical multiplexing in packet video communications,' IEEE Trans. Communications, Vol.6, No.7, July 1988 https://doi.org/10.1109/26.2812
  7. G E. Box and G M. Jenkins, Time Series Analysis, forecasting and control, Holden-Day, 1976
  8. J. D. Farmer, J. J. Sidorowich, 'Predicting chaotic time series,' Physical Review Latters, series B, Vol.59, No.8, pp.845-848, 1987 https://doi.org/10.1103/PhysRevLett.59.845
  9. You-Han Pao, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley Publishing Company, Inc., 1989