期刊文献+

光网络中个性化移动学习路径自动生成技术研究 被引量:1

Research on automatic generation of individualized mobile learning path in optical networks
下载PDF
导出
摘要 为了提高光网络中个性化移动学习过程中路径信息传输性能,降低路径损耗,提出一种基于移动Agent能量平衡环形路由算法(EBRRMA)的光网络中个性化移动学习路径自动生成技术。构建光网络的个性化移动学习路径的分布结构模型,结合转发路由节点部署方法进行路径传输信道特征分析,采用环形路由探测技术进行个性化移动学习路径的迁移处理,结合负载均衡控制方法进行光网络个性化移动学习路径分配中信道自适应调度设计,采用鲁棒性预测方法分析光网络中个性化移动学习路径的吞吐性能,以网络跳数最小为约束代价,进行移动学习路径的路由探测控制设计,采用能量平衡环形路由算法实现光网络中个性化移动学习路径的能量配置均衡设计,生成最优的移动学习路径。仿真结果表明,采用该方法进行光网络中个性化移动学习路径生成设计,降低了网络开销和跳数,网络传输时延得到有效控制,提高了网络输出的稳定性和均衡性。 In order to improve the performance of path information transmission in the process of personalized mo- bile learning in optical networks,an automatic generation technology of personalized mobile learning paths in optical networks based on mobile Agent energy balance circular routing algorithm ( EBRRMA) is proposed. The distributed structure model of personalized mobile learning path in optical network is constructed,and the characteristic of path transmission channel is analyzed by combining the deployment method of forwarding route node,and the migration of personalized mobile learning path is processed by ring route detection technology. Combined with load balancing control method,channel equalization is designed for personalized mobile learning path allocation in optical networks. Robust prediction method is used to analyze the throughput performance of personalized mobile learning paths in optical net- works,and the minimum number of hops is taken as the constraint cost. The route detection control of mobile learning path is designed,and the energy allocation equilibrium design of personalized mobile learning path in optical network is realized by energy balance ring routing algorithm,and the optimal mobile learning path is generated. Simulation re- sults show that this method is used to design personalized mobile learning path in optical networks,which reduces net- work overhead and hops,effectively controls network transmission delay,and improves the stability and equalization of network output.
作者 汤恒耀 张青 姜国松 TANG Hengyao;ZHANG Qing;JIANG Guosong(School of Computer Science,Huanggang Normal University,Huanggang 438000,China;Post-doctoral Research Centers of Information and Communication Engineering,Communication University of China,Beijing 100024,China)
出处 《激光杂志》 北大核心 2019年第10期172-176,共5页 Laser Journal
基金 湖北省自科基金项目资助(No.2015CFC820、No.2019CFC861)
关键词 光网络 个性化移动学习 路径生成 负载均衡 optical network personalized mobile learning path generation load balancing
  • 相关文献

参考文献8

二级参考文献101

  • 1Sun Liang,Ji Shuiwang,Ye Jieping.Multi-Label Dimensionality Reduction[M].Florida:CRC Press,2013:20-22.
  • 2Fisher R A.The use of multiple measurements in taxonomicproblems[J].Annals of Eugenics,1936,7(2):179-188.
  • 3Wold H.Estimation of principal components and related models by iterative least squares[J].Multivariate Analysis,1966,1:391-420.
  • 4Zhang Yin,Zhou Zhihua.Multi-label dimensionality reduction via dependence maximization[J].ACM Trans on Knowledge Discovery from Data(TKDD),2010,4(3):14.
  • 5Zhang Minling,Pena J M,Robles V.Feature selection formulti-label naive Bayes classification[J].Information Sciences,2009,179(19):3218-3229.
  • 6Hu Qinghua,Yu Daren,Liu Jinfu,et al.Neighborhoodrough set based heterogeneous feature subset selection[J].Information Sciences,2008,178(18):3577-3594.
  • 7Yu Ying,Pedrycz W,Miao Duoqian.Neighborhood roughsets based multi-label classification for automatic imageannotation[J].International Journal of Approximate Reasoning,2013,54(9):1373-1387.
  • 8Yu Ying,Pedrycz W,Miao Duoqian.Multi-labelclassification by exploiting label correlations[J].Expert Systems with Applications,2014,41(6):2989-3004.
  • 9Trohidis K,Tsoumakas G,Kalliris G,et al.Multi-labelclassification of music into emotions[C]//Proc of the 9th Inl Society for Music Information Retrieval.Philadelphia:ISMIR,2008:325-330.
  • 10Briggs F,Huang Y,Raich R,et al.The 9 annual MLSPcompetition:New methods for acoustic classification of multiple simultaneous bird species in a noisy environment[C]//Proc of 2013 IEEE Int Workshop on Machine Learning for Signal Processing.Los Alamitos.CA:IEEE,2013:22-25.

共引文献235

同被引文献11

引证文献1

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