当前位置: X-MOL 学术J. Netw. Comput. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An expandable and cost-effective data center network
Journal of Network and Computer Applications ( IF 7.7 ) Pub Date : 2024-08-22 , DOI: 10.1016/j.jnca.2024.104001
Mengjie Lv , Xuanli Liu , Hui Dong , Weibei Fan

With the rapid growth of data volume, the escalating complexity of data businesses, and the increasing reliance on the Internet for daily life and production, the scale of data centers is constantly expanding. The data center network (DCN) is a bridge connecting large-scale servers in data centers for large-scale distributed computing. How to build a DCN structure that is flexible and cost-effective, while maintaining its topological properties unchanged during network expansion has become a challenging issue. In this paper, we propose an expandable and cost-effective DCN, namely HHCube, which is based on the half hypercube structure. Further, we analyze some characteristics of HHCube, including connectivity, diameter, and bisection bandwidth of the HHCube. We also design an efficient algorithm to find the shortest path between any two distinct nodes and present a fault-tolerant routing scheme to obtain a fault-tolerant path between any two distinct fault-free nodes in HHCube. Meanwhile, we present two local diagnosis algorithms to determine the status of nodes in HHCube under the PMC model and MM* model, respectively. Our results demonstrate that despite the presence of up to 25% faulty nodes in HHCube, both algorithms achieve a correct diagnosis rate exceeding 90%. Finally, we compare HHCube with state-of-the-art DCNs including Fat-Tree, DCell, BCube, Ficonn, and HSDC, and the experimental results indicate that the HHCube is an excellent candidate for constructing expandable and cost-effective DCNs.

中文翻译:


可扩展且经济高效的数据中心网络



随着数据量的快速增长、数据业务复杂性的不断升级以及日常生活和生产对互联网的日益依赖,数据中心的规模不断扩大。数据中心网络 (DCN) 是连接数据中心内大型服务器的桥梁,用于大规模分布式计算。如何在网络扩展过程中构建灵活且具有成本效益的 DCN 结构,同时保持其拓扑特性不变已成为一个具有挑战性的问题。在本文中,我们提出了一种可扩展且具有成本效益的 DCN,即 HHCube,它基于半超立方体结构。此外,我们分析了 HHCube 的一些特性,包括 HHCube 的连通性、直径和等分带宽。我们还设计了一种高效的算法来找到任意两个不同节点之间的最短路径,并提出了一种容错路由方案,以获得 HHCube 中任意两个不同无故障节点之间的容错路径。同时,我们提出了两种局部诊断算法,分别在 PMC 模型和 MM* 模型下确定 HHCube 中节点的状态。我们的结果表明,尽管 HHCube 中存在高达 25% 的故障节点,但两种算法的正确诊断率都超过 90%。最后,我们将 HHCube 与最先进的 DCN 进行了比较,包括 Fat-Tree、DCell、BCube、Ficonn 和 HSDC,实验结果表明 HHCube 是构建可扩展且具有成本效益的 DCN 的绝佳候选者。
更新日期:2024-08-22
down
wechat
bug