不准确网络信息下的实时流量优化  

The Traffic Engineering Algorithm of Localized Real Time Optimization under Inaccurate Network Information

作　　者：冯春燕[1] 张晨[1] 丁炜[1] 

机构地区：[1]北京邮电大学通信网络综合技术研究所,北京100876

出　　处：《北京邮电大学学报》2007年第1期14-18,共5页Journal of Beijing University of Posts and Telecommunications

基　　金：国家自然科学基金项目(60372101);博士点基金项目(2003001312)

摘　　要：研究了不准确网络信息下的流量优化.提出虚容量的概念,建立了基于本地状态信息的网络流量优化模型;提出的分布式实时无导师学习算法,根据网络流量变化的幅度和频度判断是否需要优化并行路径间的流量分配并且自适应的调整.该算法不需要统计、刷新和存储网络中的各种状态信息以及流量矩阵,仿真证明其优化效果明显.The traffic optimization under the inaccurate network information was discussed. Defining the virtual capacity, a model was made on the local state information; a distributed real-time and unsupervised learning algorithm was proposed, which can learn the range and frequency of the network traffic variation and then choose adaptively whether or not and how to adjust the traffic distribution between parallel paths. This algorithm can optimize the network traffic efficiently. It need not to make statistics, refresh and keep all kinds of state information and traffic matrix in the network.

关 键 词：流量工程 本地状态信息 不准确性 实时 无导师学习 

分 类 号：TN913.24[电子电信—通信与信息系统]