期刊文献+

A TWO-LAYER RECURRENT NEURAL NETWORK BASED APPROACH FOR OVERLAY MULTICAST

A TWO-LAYER RECURRENT NEURAL NETWORK BASED APPROACH FOR OVERLAY MULTICAST
下载PDF
导出
摘要 Overlay multicast has become one of the most promising multicast solutions for IP network,and Neutral Network(NN) has been a good candidate for searching optimal solutions to the constrained shortest routing path in virtue of its powerful capacity for parallel computation. Though traditional Hopfield NN can tackle the optimization problem,it is incapable of dealing with large scale networks due to the large number of neurons. In this paper,a neural network for overlay multicast tree com-putation is presented to reliably implement routing algorithm in real time. The neural network is constructed as a two-layer recurrent architecture,which is comprised of Independent Variable Neurons(IDVN) and Dependent Variable Neurons(DVN) ,according to the independence of the decision variables associated with the edges in directed graph. Compared with the heuristic routing algorithms,it is characterized as shorter computational time,fewer neurons,and better precision. Overlay multicast has become one of the most promising multicast solutions for IP network, and Neutral Network(NN) has been a good candidate for searching optimal solutions to the constrained shortest routing path in virtue of its powerful capacity for parallel computation. Though traditional Hopfield NN can tackle the optimization problem, it is incapable of dealing with large scale networks due to the large number of neurons. In this paper, a neural network for overlay multicast tree computation is presented to reliably implement routing algorithm in real time. The neural network is constructed as a two-layer recurrent architecture, which is comprised of Independent Variable Neurons (IDVN) and Dependent Variable Neurons (DVN), according to the independence of the decision variables associated with the edges in directed graph. Compared with the heuristic routing algorithms, it is characterized as shorter computational time, fewer neurons, and better precision.
出处 《Journal of Electronics(China)》 2008年第2期209-217,共9页 电子科学学刊(英文版)
基金 the High-tech Project of Jiangsu Province (No.BG2003001).
关键词 神经网络 多点传送 神经元 双层网络 Neural Network (NN) Neuron Multicast Overlay network Constrained term Inde-pendent variables
  • 相关文献

参考文献10

  • 1Y. Chu,S. Rao,S. Seshan, et al.Enabling confer- encing applications on the Internet using an overlay multicast architecture[].Proceedings of the ACM SIGCOMM.2001
  • 2S. Banerjee,B. Bhattacharjee,C. Kommareddy, et al.Scalable application layer multicast[].Proceedings of the ACM SIGCOMM.2002
  • 3K. Hua,D. Tran,and R. Villafane.Overlay multicast for video on demand on the Internet[].Proceedings of the ACM Symposium on Applied Computing.2003
  • 4J. Jannotti,D. Gifford,K. Johnson, et al.Overcast:Reliable multicasting with an overlay network[].Pro- ceedings of the USENIX Symposium on Operating System Design and Implementation.2000
  • 5S. Shi,and J. Turner.Routing in overlay multicast networks[].Proceedings of INFOCOM’.2002
  • 6V. Kompella.Multicast routing algorithms for mul- timedia traffic[]..1993
  • 7R. Widyono.The design and evaluation of routing algorithms for real-time channels[].Technical Report TR-- International Computer Science Institute Berkeley.1994
  • 8X. Zhang,and G. Zhang.A multicast routing algo- rithm for overlay network built on leased lines[].Pro- ceedings of the Symposium on Applications & the Internet.2005
  • 9Z. Xia,,P. Li,,and I. Yen.A neural network based approach for overlay multicast in media streaming systems[].Proceedings of the International Parallel and Distributed Processing Symposium.2004
  • 10A. Filip,R. Bernardete,R. Luis, et al.A neural network for shortest path computation[].IEEE Transactions on Neural Networks.2001

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