OPNET을 이용한 자기유사성 트래픽 발생기 설계 및 성능 평가

Implementation and Performance Evaluation of Self-Similar Traffic Generator Using OPNET

  • 한경은 (전북대학교 컴퓨터공학과) ;
  • 정광본 (포항공과대학교 컴퓨터공학과) ;
  • 이승현 (전북대학교 정보통신학과) ;
  • 김영천 (전북대학교 컴퓨터공학과)
  • 발행 : 2006.05.01

초록

최근 인터넷 사용자가 급증함에 따라 전체 인터넷 트래픽의 90%이상을 차지하는 IP 트래픽이 통신망 성능에 미치는 영향은 매우 크다. 따라서 효율적인 망의 설계와 설계된 망의 정확한 성능 평가를 위하여 IP 트래픽의 특성을 반영한 자기유사성(self-similarity) 트래픽 발생기의 설계는 매우 중요하다. 본 논문에서는 OPNET을 이용하여 자기유사성 트래픽 발생기를 설계한다. 이를 위해 Pareto 분포를 갖는 ON-OFF 소스를 이용하고, 이를 다중화하여 중첩시킴으로써 자기유사성의 특성을 구현하였다. 또한 구현한 자기유사성 트래픽 발생기의 성능 평가를 위하여 다양한 통계학적인 접근방법을 통해 자기유사성의 특성을 분석 검증하고, 입력부하 및 다중화 된 소스의 개수에 따른 영향을 분석하였다. 설계된 자기유사성 트래픽 발생기는 유무선 통신망 모델 구현 및 성능 평가 시 IP 트래픽 발생기로 활용될 수 있으며, 자기유사성 트래픽 모델링에서 요구되는 구체적인 파라미터 값의 결정에도 도움이 될 것으로 기대된다.

Recently, with the exponential growth of the number of Internet users, IP traffic which occupies more than 90 percent of the entire Internet traffic affects significantly to the performance of networks. Therefore, the design of the self-similar traffic generator reflected the feature of IP traffic is very important to design the networks efficiently and evaluate the performance of it correctly. In this paper, we design the self-similar traffic generator using OPNET. In order to implement the self-similar characteristics, ON-OFF sources with Pateto distribution are employed and aggregated. The designed self-similarity traffic generator is evaluated and verified with R/S plot, variance time(VT) plot under the various offered loads and the number of sources. It is expected that the designed self-similar traffic generator can be put to practical use when wire or wireless networks is designed and verified as well as it can be useful to decide the specific parameter value for Internet traffic modeling.

키워드

참고문헌

  1. W. E. Leland, M. S. Taqqu, W. Willinger, D.V. Wilson, 'On the Self-Similar Nature of Ethernet Traffic(Extended Version)', Networking, IEEE/ACM Transactions on, Vol. 2, pp.1-15, Feb. 1994 https://doi.org/10.1109/90.282603
  2. W. E. Leland, M. S. Taqqu, W. Willinger, D. V. Wilson, 'Self-Similarity Through High-Variability : Statistical Analysis of Ethernet LAN Traffic at the Source Level,' Networking, IEEE/ACM Transactions on, Vol. 5, pp. 71-86, Feb. 1997 https://doi.org/10.1109/90.554723
  3. J. M. BareIo, L. I. Cerda, J. Garcia, 'Conceptes fonameatals de xarxes de computadors. Un enfocament analitic,' http://people.ac.upc.es/joseb/CURSO_DOCT_Joseb_TM_SelfSim.pdf
  4. P. Pruthi, 'Heavy-Taild ON/OFF Source Behavior and Self-Similar Traffic', ICC'95, 1995
  5. A. Adas, A. Mukherjee, 'On Resource Management and QoS Guarantees for long range dependent traffic,' IEEE INFOCOM'95, pp. 779-787, 1995
  6. R. Addie, M. Zukerman, T. Neam, 'Fractal traffic: measurements, modeling and performance evaluation,' IEEE INFOCOM'95, pp.977-984, 1995
  7. N. Likhanov, B. Tsybakov. 'Analysis of an ATM buffer with self-similar('fractal') input traffic,' IEEE INFOCOM'95, pp.985-992, 1995
  8. Kihong Park, Gitae Kim, Mark Crovella, 'On the Effect of Traffic Self-Similarity on Network Performance,' http://citeseer.ist.psu.edu/88701.html
  9. Thomas Karagiannis, Mart Molle, Michalis Faloutsos, 'Long-Range Dependence: Ten Years of Internet Traffic Modeling,' Internet Computing September/October 2004, Vol.8, pp.57-64 https://doi.org/10.1109/MIC.2004.46
  10. Glen Kramer, 'Self-similar Network Traffic: the notion and effects of self-similarity and long range dependence,' Presentation slides http://www.csif.cs.ucdavis.edu/~kramer/publications.html
  11. Glen Kramer, 'On generating self-similar traffic using pseudo-Pareto distribution,' Technical brief. http://wwwcsif.cs.ucdavis.edu/~kramer/publications
  12. M. Crovella and A. Bestavros, 'Analysis, Modeling and Generation of Self-similar VBR Video Traffic,' In Proc. ACM SIGCOMM'94, pp.269-280, 1994
  13. C. Huang, M. Devetsikiotis, I. Lambadaris, and A. Kaye., 'Modeling and Simulation of Self-similar Variable Bit Rate Compressed Video: A Unified Approach,' In Proc. ACM SIGCOMM'95, pp.114-125, 1995
  14. S. McCreary, et.al., 'Trends in Wide Area IP Traffic Patterns,' Cooperative Association for Internet Data Analysis, http://www.caida.org