Modeling of Clos Switching Structures with Dynamically Variable Number of Active Switches in the Spine Stage

Author:

Głąbowski MariuszORCID,Sobieraj MaciejORCID,Stasiak MaciejORCID,Dominik Stasiak MichałORCID

Abstract

This article proposes a new analytical model of a switching structure using a Clos network topology. The assumption is that, in the structure under consideration, it is possible to switch off temporarily a certain number of spine switches (those in the middle stage of the switching fabric) depending on the current intensity of the offered traffic to reduce power consumption. The solution presented in the article can be used in present-day multiservice switching fabrics and in networks connecting servers in data centers. The developed analytical model allows the value of blocking probabilities for different stream classes of multiservice traffic to be evaluated in switching structures (switching fabrics) with a variable number of switches in the middle stage. The results obtained on the basis of the analytical model are compared with the results obtained as a result of relevant simulation experiments for a selected structure of the switching fabric. The study confirms high accuracy of the proposed model. This model can be used in further works to evaluate the effectiveness of energy-saving switching fabrics and the networks of data centers, as well as to construct energy-saving control algorithms that would control these switching structures, that is, algorithms that would change the topology of the switching fabric depending on changes in the offered traffic.

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering

Cited by 8 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3