基于贝叶斯算法的XG-EPON业务感知机制被引量：1

Eervice-aware mechanism in XG-EPON based on Bayesian algorithm

下载PDF

导出

摘要提出了一种基于贝叶斯算法的XG-PON业务感知机制,该机制采用贝叶斯算法对业务进行分类,以实现高效的业务感知。在此基础上通过OLT与ONU的交互,优化XG-PON的资源分配。对基于贝叶斯算法的XG-PON业务感知机制进行仿真,仿真结果表明该机制能有效降低丢包率并缩短时延,提高了系统对多业务的支持能力。 The paper proposes a Bayesian algorithm Enabled Service-Aware mechanism in XG-PON, the mechanism uses the Bayesian algorithm to classify services, in order to match services requirements with better efficiency. Thus, resources allocation optimization is enabled through cooperation between OLT and ONUs. Simulation of the scheme is conducted, the results show that this proposed approach can greatly improve the supporting ability for multiple services, effectively reduces the packet loss rate and shortens the time delay.

作者沈高峰马欢褚玉晓

机构地区郑州轻工业学院计算机与通信工程学院郑州轻工业学院软件学院郑州大学西亚斯国际学院电子信息工程学院

出处《光通信技术》 CSCD 北大核心 2014年第8期23-25,共3页 Optical Communication Technology

基金河南省科技厅2013年重点科技攻关项目(132102210111)资助

关键词以太无源光网络业务感知贝叶斯算法 ethemet passive optical network service-aware Bayesian algorithm

分类号 TN929.11 [电子电信—通信与信息系统]

引文网络
相关文献

参考文献7

1TANAKA K, AGATA A, HORIUCHI Y, et al. IEEE 802.3av 10G-E- PON Standardization and Its Research and Development Status [J]. Journal of Lightwave Technology,2010, 28(4): 651-661.
2PAXSON V. Empirically derived analytic models of wide-area TCP connections[J]. IEEE/ACM Trans Netw, 1994, 2(4):316-336.
3PAXSON V, FLOYD S. Wide area traffic: the failure of Poisson model- ing[J]. IEEE/ACM Trans Netw, 1995, 3(3): 226-244.
4ROUGHAN M, SEN S, SPATSCHECK O,et al. Class-of-service map- ping for QoS: a statistical signature-based approach to IP traffic classifica- tion[C]. Proc the 4th ACM SIGCOMM, New York, 2004.
5CROTTI M, GRINGOLI F, PELOSATO P, et al. A statistical approach to IP-level classification of network traffic [C]. Proc IEEE International Conference on Communications,Istanbul, 2006.
6MOORE W, ZUEV D. Intemet traffic classification using Bayesian analysis techniques [C]. Proceedings ofACM SIGMETRICS, Banff, 2005.
7BOUCKAERT R. Bayesian Network Classifiers in Weka [R]. Depart- ment of Computer Science, Waikato University, Hamilton, 2005.