期刊文献+

网络相变的非线性成因与分布式代理对策 被引量:3

Nonlinear phase transitions in networks and distributed proxy approach
原文传递
导出
摘要 为改善计算机网络非线性影响,以及用户行为带来的网络性能波动,分析了网络性能相变的非线性机制,在改进的二维耦合网络模型中对规则网络、具有访问群聚特性的网络和引入分布式代理的网络进行仿真对比。研究表明:在路由器非线性的作用下,网络存在相变特性;与目的节点随机选取的规则网络相比,超文本链接网络中访问行为的大规模群聚特性使网络相变点明显左移,网络性能相对恶化;针对这种情况采用分布式代理对策,使网络相变点右移,网络性能得到明显改善。 The network performance fluctuations caused by user behaviors were analyzed to reduce the effect of nonlinear phase transition in the computer network. A modified two-dimensional coupling network model was used to analyze the regular networks and the clustering characteristic with a distributed proxy used to improve the performance. The results show that the nonlinear network router characteristics cause the network performance to have phase transitions. Compared with regular networks, the extreme clustering of the access behavior in http networks gives rise to a left-shift of the phase transition point, which degrades the network performance. A distributed proxy approach is used to increase the resource node proxies and right-shift the phase transition point with obvious improvement of the network performance.
出处 《清华大学学报(自然科学版)》 EI CAS CSCD 北大核心 2009年第8期1131-1134,共4页 Journal of Tsinghua University(Science and Technology)
基金 国家自然科学基金资助项目(60672142 60772053 60674048)
关键词 网络相变 非线性 元胞自动机 分布式代理 phase transition nonlinear cellular automationdistributed proxy
  • 相关文献

参考文献9

二级参考文献40

  • 1[1]Banavar J R, Marritan A and Rinaldo A 1999 Nature399 130
  • 2[2]Huberman B A and Lukose R M 1997 Science277 535
  • 3[3]Barabási A L, Albert R, Jeong H and Bianconi G 2000 Science287 2115a
  • 4[4]Willinger W, Taqqu M S, Sherman R and Wilson D V 1997 IEEE/ACM Trans . on Networking5 71
  • 5[5]Crovella M E, Bestavros A and Taqqu M S 1998 A Practical Guide to Hea vy Tails:Statistical Techniques and Applications(Boston Birkhuser) 3- 25
  • 6[6]Csabai I 1994 J.Phys. A 27 L417
  • 7[7]Takayasu M, Fukuda K and Takayasu H 1999 Physica A 274 140
  • 8[8]Leland W, Taqqu M, Willinger W and Wilson D 1994 IEEE/ACM Transaction s on Networking2 1
  • 9[9]Takayasu M, Takayasu H and Sato T 1996 Physica A 233 824
  • 10[10]Yuan J, Ren Y and Shan X 2000 Phys.Rev.E 61 1067

共引文献39

同被引文献35

  • 1李?,山秀明,任勇.具有幂率度分布的因特网平均最短路径长度估计[J].物理学报,2004,53(11):3695-3700. 被引量:18
  • 2蔡青松,李子木,胡建平.Internet上的流媒体特性及用户访问行为研究[J].北京航空航天大学学报,2005,31(1):25-30. 被引量:13
  • 3王磊,周淑华,袁坚,任勇,山秀明.虚拟网络行为对互联网整体特性的影响[J].物理学报,2007,56(1):36-42. 被引量:16
  • 4Wang L , Ren Y , Li Y P, et al. Measurement and statistics of application business in complex internet[ C]. Proc of International Conference on Complex Sciences: Theory and Applications, Shanghai, China ,2009:400-410.
  • 5Wang L, Ren Y, Wang Y, et al. Traffic localizing strategy for peer-to-peer systems[ C ]. Proc of IEEE Computer Society World Congress on Computer Science and Information Engineering, Los Angeles, USA,2009, 2:409 -413.
  • 6Barabasi A-L,Albert R. Emergence of scaling in random networks[ J]. Sience. 1999,286(5439) :509 -512.
  • 7Xie H Y, Yang Y R, Krishnamurthy A, et al. P4P: provider portal for applications [ DB/OL]. [2010 -09 -20]. http://ccr. sigcomm. org/online/? q = node/402.
  • 8Internet world stats [ DB/OL ]. [ 2010 - 09 - 29 ]. http ://internetworld stats. com/stats, htm.
  • 9Yuan J, Mills K. A Cross-correlation based method for spatial-temporal traffic analysis [ J]. Performance Evaluation, 2005, 61(2 -3): 163 -180.
  • 10Liu F, Shan X M, Ren Y, et al. Phase transition and 1/f noise in a computer network model[J]. Physiea A, 2003, 328(3 - 4) : 341 -350.

引证文献3

二级引证文献11

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