Abstract
네트워크를 설계하고 서비스를 구현하는데 있어서 중요한 변수중의 하나는 트래픽의 특성을 파악하는 것이나 기존의 트래픽 예측과 분석은 포아송(Poisson) 또는 마코비안(Markovian)을 기본으로 하는 모델을 사용하였다. LAN, WAN 및 VBR(Variable Bit Rate) 트래픽 특성에 관한 최근의 실험적 연구들은 기존의 포아송 가정에 의한 모델들이 네트워크 트래픽의 장기간 의존성 및 자기 유사한 특성들을 과소평가 함으로써 실제 트래픽의 특성을 제대로 나타낼 수 없다는 것을 지적해 왔고 최근 실제 트래픽과 유사한 모델로서 자기 유사한 특성을 이용한 접근법이 대두되고 있다. 따라서, 본 논문에서는 실제 트래픽과 유사한 자기 유사 데이터 트래픽을 백그라운드 부하로 발생시켜 기존의 ABR (Available Bit Rate) 혼잡제어 알고리즘 중 대표적인 EFCI(Explicit Forward Congestion Indication), EPRCA(Enhanced Proportional Rate Control Algorithm), ERICA(Explicit Rate Indication for Congestion Avoidance), NIST(National Institute of Standards and Technology) 스위치 알고리즘이 버스트한 트래픽에 대해 효율적으로 반응하는지를 ACR(Allowed Cell Rate), 버퍼 사용율, 셀 폐기율, 전송효율 등으로 나누어 분석을 하였다. One of the most important matters in designing network and realizing service, is to grip on the traffic characteristics. Conventional traffic prediction and analysis used the models which based on the Poisson or Markovian. Recently, experimental research on the LAN, WAN and VBR traffic properties have been pointed rut that they weren't able to display actual real traffic specificities because the models based on the Poisson assumption had been underestimated the long range dependency of network traffic and self-similar peculiarities, it has been lately presented that the new approach method using self-similarity characteristics as similar as the real traffic models. Therefore, in this paper, we generated self-similar data traffic like real traffic as background load. On the existing ABR congestion control algorithm, we analyzed by classify into ACR, buffer utilization. cell drop rate, transmission throughput with the representative EFCI, ERICA, EPRCA and NIST twitch algorithm to show the efficient reaction about the burst traffic.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.