期刊文献+

高时延混合网络拥塞控制仿真实验设计

Design of Congestion Control Simulation Experiment for High-Delay Hybrid Network
下载PDF
导出
摘要 TCP Hybla拥塞控制算法因其具有较好的吞吐量和兼容性,被广泛应用于高时延混合网络中以解决网络性能下降问题。针对Hybla拥塞控制原理抽象,过程变化快,在混合网络环境下较之传统实验教学难以直观展现的问题,引入了NS-3仿真实验平台。通过搭建哑铃状高时延混合网络环境,添加追踪和流量监测机制得到仿真数据。与Hybla理论分析对比,实验数据与理论结果一致,真实反映了混合网络环境。同时通过与其他拥塞控制算法对比,直观地验证了TCP Hybla算法能够提供较好的网络公平性、友好性以及响应灵敏性,突破了传统实验教学难以形象直观分析拥塞控制的局限性。 TCP Hybla congestion control algorithm is widely used in high-delay hybrid networks to solve the problem of network performance degradation because of its good throughput and compatibility. In order to solve the problem that Hybla congestion control principle is abstract and the process changes quickly,and it is difficult to visualize in hybrid network environment compared with traditional experiment teaching, an NS-3 simulation experiment platform is introduced. By building a dumbbell-like high-latency hybrid network environment and adding trace and flow monitor mechanism,the simulation data are obtained. Compared with Hybla theory,the experimental data are consistent with the theoretical results,and truly reflect the hybrid network environment. At the same time,compared with other congestion control algorithms,TCP Hybla algorithm can provide better network fairness,friendliness and response sensitivity,breaking through the limitations of traditional experimental teaching which is difficult to visually and intuitively analyze congestion control.
作者 马琛璐 唐俊勇 MA Chenlu;TANG Junyong(School of Computer Science&Engineering,Xi’an Technological University,Xi’an 710021,China)
出处 《实验室研究与探索》 CAS 北大核心 2020年第7期93-97,142,共6页 Research and Exploration In Laboratory
基金 十三五装备发展预研项目(41402020202) 西安工业大学重点教改项目(17JGZ10、No.18JGZ01) 西安市科技计划项目2017075CG/RC038(XAGY004)。
关键词 高时延 混合网络 NS-3仿真 实验教学 high-delay hybrid network NS-3 simulation experimental teaching
  • 相关文献

参考文献4

二级参考文献34

  • 1于晓梅,赵耀培,郑明春.异质网络传输控制技术研究[J].计算机应用研究,2004,21(11):106-113. 被引量:5
  • 2周兆清,陈立军.TCP/IP协议在卫星链路上的应用研究[J].无线电工程,2006,36(1):47-50. 被引量:9
  • 3Keshav S. A Control-Theoretic Approach to Flow Control[C]// Proc. ACM SIGCOMM. [S. l.]: [s. n. ] ,1991.
  • 4Allman M , Paxson V. On Estimating End-to-End Net- work Path Properties [ C]//Proc. ACM SIGCOMM. [S. l. ]:[s.n. ],1999.
  • 5Mogul J C. Observing TCP Dynamics in Real Networks [ C]//Proc. ACM SIGCOMM Symp. Comm. Architectures and Protocols. [ S.l. ] : [ s. n. ], 1992.
  • 6Zhang L, Shenker S , Clark D. Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic [ C ]//Proc. SIGCOMM Symp. Comm. Architectures and Protocols. [ S. l. ] : [s.n. ],1991.
  • 7Brakmo L S , Peterson L L. TCP Vegas: End-to-End Congestion Avoidance on a Global Internet[J]. IEEE J Selected Areas inComm, 1995,13 (8) : 1465 - 1480.
  • 8Paxson V, Allman M. Computing TCP' s Retransmission Timer. RFC 2988 [ S].
  • 9Hoe J C. Improving the Start-Up Behavior of a Congestion Control Scheme for TCP [ J ]. ACM SIGCOMM Computer Comm Rev , 1996,26 (4) :270- 280.
  • 10Mo J, Anantharam V, La R J. Analysis and Comparison of TCP Reno and Vegas[ C]// Proc. ACM GLO- BECOM. [S.L.]:[S.N.],1999.

共引文献28

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部