The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Deep learning is a sub-set of machine learning practice employing models based on various learning network architectures and algorithms in the field of artificial intelligence. Businesses planning to adopt a deep learning solution should comprehend a set of complex choices in hardware, software, configuration and optimizations to setup a functional deep learning solution. This paper will describe...
Data centers play an important role with the fast growth of cloud computing used in our daily life. Traditional data center networks based on the fat-tree topology have their own drawbacks and limitations which prevent them from providing high performance to satisfy the increasing demand for cloud services. In this paper, we first design a new flexible network fabric for data center networks based...
Ethernet is the predominant layer-2 networking technology in the datacenter, and it is evolving into an economical alternative for high-performance computing clusters. Ethernet traditionally drops packets in the event of congestion, but IEEE introduced lossless class services to enable the convergence of storage and IP networks. Losslessness is a simple, well-known concept, but its application in...
This paper describes the architecture, use-case, and evaluation of a software-defined interconnect. Interconnects at Internet Exchange Points (IXPs) today comprise a layer-2 data-plane and BGP control-plane. We architect, implement, and deploy an SDN-based IXP using ONOS that provides equivalent functionality, while additionally supporting better ARP hygiene and enhanced traffic telemetry. Our system...
Network Function Virtualization (NFV) is an attempt to help operators more effectively manage their networks by implementing traditional network functions embedded in specialized hardware platforms in term of virtualized software instances. And, existing NFV infrastructure solutions are always architected on a general-purpose x86 server, which makes the performance of NFs limited by the hosted single...
A modern virtualized data center is highly multifarious environment shared among hundreds of co-located tenants hosting heterogeneous applications. The tenants' virtual machines generate a subset of elephants or mice flows (different in terms of rate, size, duration, and burstiness) based on the type of application they are running. Virtual traffic generated from the tenant's virtual machines traverses...
Big data make drastic changes in patterns of data center traffic. In traditional applications, which are based on client-server architectures, data center traffic are in northern-southern mode. While, as applications of big data developed, so-called eastern-western traffic patterns were widely used in data center networks. Moreover, applications of cloud computing technology in processing infrastructures...
With the rapid development of Internet technology and the explosive growth of data, the storage system designed by tightly coupled hardware and software is limiting the development of storage technology severely, and unable to meet the fast changing needs in the mobile Internet and exploding big data era. Software Defined Storage (SDS) as a new storage system architecture is more suitable for the...
High speed routers in Internet are becoming increasingly more powerful, as well as more energy hungry. However, they always show power-inefficient property due to we unilaterally in pursuit of high speed before. In response to this problem, we present a power-efficient router architecture named GreenRouter in this paper. GreenRouter separates a line card into two parts physically: the network interface...
In this paper, we study the problem of resource allocation in the setting of multitier data centers. Our main motivation and objective is to provide applications hosted in the data center with different service levels. In such centers, there are several mechanisms the designer can use to achieve such objectives. We restrict our attention to CPU time at the service tier as the resource; the objective...
Disasters have been causing huge damages to infrastructure as well as human life from a long time. One of the key problems faced when disaster hits an area is efficient distribution of resources such as medicine, food, water etc. In this paper, we propose a solution particularly for distribution of food. We have proposed a solution in which a big disaster region is divided into smaller areas (regions)...
Management of a switch fabric security configuration, a core component of Storage Area Networks, is complex and error prone. As a consequence, misconfiguration of and/or a poor understanding of a switch fabric may unnecessarily expose an enterprise to known threats. A formal model of a switch security configuration is presented. This model is reasoned over to help manage complex switch fabric security...
We introduce the concept of zoning in order to solve the problems of security and stability in storage area networks. We will have different zoning strategies from different perspectives. When we implement zoning at the switch fabric level, we can implement name server-based zoning and hardware enforced zoning. However, both of the implementations have their drawbacks. According to Brocade zoning...
As computation and storage continues to move from desktops to large internet services, computing platforms running such services are transforming into warehouse-scale computers. 100 Gigabit Ethernet and beyond will be instrumental in scaling the interconnection within and between these ubiquitous warehouse-scale computing infrastructures. In this paper, we describe the drivers for such interfaces...
The server virtualization architecture, encompassing the sharing of data storage subsystems among the virtual servers or operating systems on a single host server using I/O channel sharing capabilities in fibre channel fabrics, was pioneered by IBM through their system z9 mainframe and its predecessors. The implementations of I/O channel sharing capabilities were based on the fibre connectivity channel...
Multistage Interconnection Networks (MINs) provide efficient communication resources between network components in an appealing cost/performance relation. Consequently, they have been widely used on Internet connections such as ATM and gigabit Ethernet switches, terabit routers as well as for interconnecting parallel systems. In this paper a novel analytical method for providing performance evaluation...
There is an increasing need for improved node density and better power efficiency in telecommunication market. In addition, the telecommunication server environment also requires rugged high system performance systems with compliance to rigorous standards. Hence, the design of telecommunication blade servers presents several conflicting electrical and mechanical parameters in terms of desired transmission...
The high end of high performance computing (HPC) systems is now moving toward petascale deployments, delivering petaflops of computational capacity and petabytes of storage capacity. Interconnection of the sheer number of server nodes in an HPC system plays a vital role in the developments. InfiniBand has emerged as a compelling interconnect technology, and provides more scalability and significantly...
In this research, the performance evaluation of two class priority Delta Multistage Interconnection Networks (MINs) is analyzed, using a discrete priority queuing model. All Delta Networks are constructed by special switching elements (SEs) based on an architecture which natively supports two classes of routing traffic. The proposed analytical method which was developed for performance metrics investigation...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.