Article

Next-generation routing making sense of the marketectures

September 1995

Authors:

Making the move to switched networks means bidding farewell to shared-media LANs and point-to-point WANs, but routing will remain a part of net managers' lives. They face three basic choices: maintain the status quo, migrate to distributed routing, or opt for route servers. For net managers, making the smart call, means applying some familiar yardstick to some unfamiliar technologies.

ResearchGate has not been able to resolve any citations for this publication.

ResearchGate has not been able to resolve any references for this publication.

Conference Paper

Full-text available

An Efficient Mice Flow Routing Algorithm for Data Centers Based on Software-Defined Networking

May 2019

A significant problem affecting the overall performance of Data Center Networks (DCNs) based on Software-Defined Networking (SDN) is the delay introduced to latency-sensitive small flows (i.e., mice) by the SDN controller. Current research works face this problem by compiling and installing the path for mice and elephants dynamically and individual or jointly. However, these works have ... [Show full abstract] shortcomings related to the large number of routing rules that the switches must handle, which leads to delay of mice flows. In this paper, we propose, MiceDCER, an algorithm that routes efficiently mice flows in DCNs based on SDN by assigning internal Pseudo-MAC (PMAC) addresses to the edges switches and the hosts. Aiming to reduce the number of routing rules, MiceDCER installs wildcard rules based on the information obtained by the Address Resolution Protocol (ARP) packets. Our evaluation reveals that MiceDCER significantly reduces the number of rules installed in switches and, therefore, contributes to reducing the delay in SDN-based Data Centers.

View full-text

Article

A New Concept—Repackable Networks

September 1993 · IEEE Transactions on Communications

The following classes of connecting networks, based on their combinatorial properties, have been previously defined: networks nonblocking in the strict sense, networks nonblocking in the wide sense, rearrangeable networks, and blocking networks. To these the authors add the class of repackable networks, i.e., networks in which blocking can be avoided by using call repacking control algorithms. ... [Show full abstract] The conditions under which a three-stage Clos network is repackable are formulated and proved. The numbers of middle-stage switches in all network classes are compared, and the differences between repackable and rearrangeable networks are discussed

Article

Research on QoS routing algorithm of CDN

September 2010

Liang Zhijian

The paper introduces a new method for improving quality of routing service in content delivery networks(CDN). The technology of jointing optimization of replica placement and distributed user request redirection is given. In the model, different content has different latency bound requirements. The solution is dynamic in the sense that replicas are added and removed from content delivery networks ... [Show full abstract] servers according to the dynamically changing user request traffic. The results show that the proposed solution is capable of decrease access delay and improve the quality of service.

Article

Diffusion limit of a two-class network: stationary distributions and interchange of limits.

January 2010 · ACM SIGMETRICS Performance Evaluation Review

In [11], we have established the diffusion limit for a network with two servers (both being bottlenecks) and two job classes under a proportional fair resouce control. Here, we show that the usual traffic condition is necessary and sufficient for the existence and uniqueness of the stationary distributions of both the diffusion limit and the pre-limit processes. Furthermore, the interchange of ... [Show full abstract] limits is also justified, i.e., the sequence of stationary distributions of the pre-limit networks converges to that of the diffusion limit.

Conference Paper

Full-text available

Efficient Routing Techniques for Cooperating Processors in Dataflow Computers.

January 1990

A key problem in designing a dataflow computer is to maintain a strong cooperation among the processors. This requires two types of communications among the processors which are commonly referred to as arbitration and distribution. The paper describes a family of switches, called CP networks which can be used as arbitrators and distributors in dataflow computers. The arbitration networks require ... [Show full abstract] &Ogr;(N log2 N) binary switches, and have &Ogr;(log22 N) delay, and distribution networks require &Ogr;(N log22 N) binary switches, and have &Ogr;(log22 N) delay.

View full-text

Conference Paper

Intelligent Packets For Dynamic Network Routing Using Distributed Genetic Algorithm.

January 2002

A distributed GA is designed for the packet switched network routing problem under minimal information. The requirements of such a problem mean that agents are required to possess more intelligence than was previously the case. To this end a distributed GA approach is developed and benchmarked against the AntNet algorithm under the same information constraints.

Article

Environment To Inspire Network Users (ETINU) The development of a complete online support system

August 1997 · Computer Networks and ISDN Systems

Today, with computer or network related applications pervading more and more of our lives at work and at home, 'good' user support presents a greater challenge than ever. We firmly believe that existing technology can be utilised to provide an effective online support system which: a large number of people can benefit from; can deliver all the facility of a Helpdesk efficiently; and can pool ... [Show full abstract] expertise which can then be shared widely. I. 'Just not good enough' We believe that conventional user support as offered by many organisations today is 'just not good enough' to fully address user requirements. I.A User contact points In evaluating the user support which exists today, the first point to make is that there may be many contact points with a 'user support service'. For example, the following are seven contact points which exist at Queen's University Belfast: 1 helpdesk, the main contact point for users---very often this is a face to face meeting, with queries also being raised by...

Article

Snowflake: A New-Type Network Structure of Data Center

January 2011 · Chinese Journal of Computers

The paper analyses the deficiency of traditional data center and new characteristics of current data center. Basing on the famous Koch curve, it proposes a new-type network structure of data center, called Snowflake. It takes scalability into full consideration. On the premise of low proportion of switches and servers, it can efficiently achieve routing mechanisms in shorter mean path lengths ... [Show full abstract] with less network cost.

Conference Paper

Live distributed controller migration for software-defined data center networks

April 2018

Article

Full-text available

A flexible and high-performance data center network topology

April 2017 · The Journal of Supercomputing

In order to meet the insatiable demands for cloud-based services, today’s data centers may have hundreds of thousands of servers. During the past decade, many topologies have been proposed to interconnect a large number of servers in a data center network. However, existing topologies face several challenges including the rigid structure, high network cost, and packet relay overheads on servers. ... [Show full abstract] In this paper, we propose a novel switch-centric network topology, called DCCube, which offers many desirable properties for data center networking. DCCube is a flexible structure because, given the switches degree and the network diameter, it is possible to construct different structures with different number of connected servers, bisection bandwidth and network cost. Furthermore, DCCube can accommodate a large number of servers with high bisection bandwidth, low cost, small diameter and desirable path diversity. By comparing with existing data center network topologies, we show that DCCube achieves both high performance and low network cost. We also design both minimal and non-minimal routing algorithms for the proposed topology. Simulation results reveal that non-minimal routing is preferred for unbalanced traffic patterns.

View full-text

Conference Paper

On-demand server synchronization algorithms for session guarantees

November 2008

Session guarantees define required properties of the system regarding consistency of replicas in a distributed system from a single, migrating clientpsilas point of view. This paper presents propositions of two new server synchronization algorithms. These algorithms solve two of the main problems of some earlier protocols: lack of serverpsilas history pruning and synchronous history update ... [Show full abstract] sending.

Article

Network Security Protection Measures

June 2014 · Advanced Materials Research

Yan Li

Safety is the premise of network operation, network security is not only a single point of security, but the safety of the information network, need to be done from various solid protection. Analyzed the current form and face all kinds of LAN network security threats and network security precautions, technology, this paper expounds the LAN the importance of the current network security in our ... [Show full abstract] lives.

Next-generation routing making sense of the marketectures

Abstract

No full-text available

Recommended publications

An Efficient Mice Flow Routing Algorithm for Data Centers Based on Software-Defined Networking

A New Concept—Repackable Networks

Research on QoS routing algorithm of CDN

Diffusion limit of a two-class network: stationary distributions and interchange of limits.

Efficient Routing Techniques for Cooperating Processors in Dataflow Computers.

Intelligent Packets For Dynamic Network Routing Using Distributed Genetic Algorithm.

Environment To Inspire Network Users (ETINU) The development of a complete online support system

Snowflake: A New-Type Network Structure of Data Center

Live distributed controller migration for software-defined data center networks

A flexible and high-performance data center network topology

On-demand server synchronization algorithms for session guarantees

Network Security Protection Measures