重力模型的数据中心网络流量推理算法

发布时间：2018-04-15 23:31

本文选题：数据中心网络 + 网络测量　；参考：《合肥学院学报》2016年01期

【摘要】：数据中心网络是云计算等大型分布式计算服务的基础,有效地设计与管理数据中心网络需要遵循该网络的流量特征。而目前直接对数据中心网络进行端到端地流量测量是非常困难的,间接地通过SNMP数据推理得到端到端流量的方法已在传统计算机网络中得到认可,但无法直接应用于现有的数据中心网络。为了解决以上问题,提出一种基于重力模型的数据中心网络流量推理算法,首先根据数据中心网络流量的条件独立性将网络拓扑分解为若干子集,在此基础上提出相关定理可准确地计算出网络中的粗粒度流量,最后利用重力模型和网络层析技术得到细粒度端到端流量。通过与现有的流量推理算法SRMF和ELIA在NS3搭建的不同规模的数据中心网络中做性能对比,实验结果表明新算法能有效地利用数据中心拓扑结构特点,在保证计算效率的前提下,将计算准确度大幅提升,可满足当前数据中心网络实时获取端到端流量数据的需求,为今后数据中心网络的设计和研究提供了重要参考依据。
[Abstract]:Data center network is the foundation of large-scale distributed computing services such as cloud computing. To effectively design and manage the data center network, it is necessary to follow the traffic characteristics of the network.At present, it is very difficult to measure the end-to-end flow of the data center network directly. The method of indirectly getting end-to-end flow through SNMP data reasoning has been accepted in the traditional computer network.However, it can not be directly applied to the existing data center network.In order to solve the above problems, a data center network traffic reasoning algorithm based on gravity model is proposed. Firstly, the network topology is decomposed into several subsets according to the conditional independence of the data center network traffic.The coarse-grained flow in the network can be accurately calculated by using the correlation theorem, and the fine-grained end-to-end flow can be obtained by using the gravity model and the network chromatography technique.Compared with the existing traffic reasoning algorithms SRMF and ELIA in the different scale data center network built by NS3, the experimental results show that the new algorithm can effectively utilize the topological characteristics of the data center and ensure the computing efficiency.The accuracy of calculation is greatly improved, which can meet the demand of the current data center network to obtain end-to-end traffic data in real time. It provides an important reference for the design and research of the data center network in the future.
【作者单位】：安徽农业大学信息与计算机学院;
【基金】：国家自然科学基金项目(61402013;61203217) 安徽省教育厅自然科学基金项目(KJ2014A074) 安徽省科技厅国际合作项目(1403062031) 安徽省经信委财政专项资金项目(财企(2013)1162)资助
【分类号】：TP308;TP393.06

【相似文献】