SDN data center performance evaluation of torus and hypercube interconnecting schemes

Andrus, Bogdan; Olmos, J. J. Vegas; Mehmeri, Victor; Monroy, Idelfonso Tafur; Spolītis, Sandis; Bobrovs, Vjačeslavs

doi:10.1109/rtuwo.2015.7365731

Cited by 7 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, all networking architectures employ software (IP-version: 6, BGP-version: 4, MPLS-version: 3, VMware-version: 17.5.0, etc.) for data management and transformation [5]. All protocols mentioned above can be easily manipulated in an SDN virtual environment; with this flexibility, SDN is becoming a vital networking force [6,7].…”

Section: Introductionmentioning

confidence: 99%

Enhancing QoS of Telecom Networks through Server Load Management in Software-Defined Networking (SDN)

Mehmood,

Atiq,

Hussain

2023

Sensors

View full text Add to dashboard Cite

In the modern era, with the emergence of the Internet of Things (IoT), big data applications, cloud computing, and the ever-increasing demand for high-speed internet with the aid of upgraded telecom network resources, users now require virtualization of the network for smart handling of modern-day challenges to obtain better services (in terms of security, reliability, scalability, etc.). These requirements can be fulfilled by using software-defined networking (SDN). This research article emphasizes one of the major aspects of the practical implementation of SDN to enhance the QoS of a virtual network through the load management of network servers. In an SDN-based network, several servers are available to fulfill users’ hypertext transfer protocol (HTTP) requests to ensure dynamic routing under the influence of the SDN controller. However, if the number of requests is directed to a specific server, the controller is bound to follow the user-programmed instructions, and the load on that server is increased, which results in (a) an increase in end-to-end user delay, (b) a decrease in the data transfer rate, and (c) a decrease in the available bandwidth of the targeted server. All of the above-mentioned factors will result in the degradation of network QoS. With the implementation of the proposed algorithm, dynamic active sensing server load management (DASLM), on the SDN controller, the load on the server is shared based on QoS control parameters (throughput, response time, round trip time, etc.). The overall delay is reduced, and the bandwidth utilization along with throughput is also increased.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing QoS of Telecom Networks through Server Load Management in Software-Defined Networking (SDN)

Mehmood,

Atiq,

Hussain

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…For example, in the networking field, we find HyperCuP [14], which suggests a Hypercube-based peer-to-peer network introducing an efficient method for broadcasting and searching, or BlueCube [15], which offers a Bluetooth network based on a Hypercube, to support parallel computing and ensure fault tolerance. The Hypercube has been proposed in the context of SDN to connect between nodes in the underlying network [16], which is not the case in this paper.…”

mentioning

confidence: 99%

OMCH-SDN: An Overlay multi-controller Hypercube-based topology for Softwaredefined Networks

Blial¹,

Mamoun²,

Benaini³

2018

IJET

View full text Add to dashboard Cite

Multi-controller architectures have become very necessary for software-defined networks to provide more efficiency, scalability, flexibility and security. However, the controllers must be interconnected in a way that aims to improve the overall performance. In this paper, we propose the OMCH-SDN, an Overlay Multi-Controller Hypercube-based topology to interconnect controllers by using a Hypercube pattern to take advantage of its various mathematical characteristics. The proposal for this research is evaluated through simulations of a real overlay network. The results show that the OMCH-SDN model shows better results concerning the synchronization delay, the throughput as well as the end-to-end latency comparing to a flat-based SDN multi-controller topology. Keyword-SDN, Multi-controller architecture, Hypercube-based topology I. INTRODUCTION The networking field knows recently a big revolution with the introduction of new concepts like, network automation, network function virtualization and software-defined networking, which aim to shape the network and improve its productivity. Software-defined networking (SDN) [1], which is a new concept that separates the control plane from the data plane in network nodes, like switches and routers, mainly to limit the complexity and to enable the programmability in the network throughout all types of APIs, to make it more agile and flexible, especially the integration of new functionalities and services. An SDN network in general has three layers: the infrastructure layer, the control layer, and the management layer, each layer has its own characteristics as well as its own components. Southbound APIs (SB-APIs) like OpenFlow [2] for example, which the most recognized and used Southbound API in the SDN community. They allow communication between the infrastructure layer and the control layer, by giving the end user more power over the network, to adjust and configure smoothly the different components inside the forwarding plane. OpenFlow is supported and maintained by the Open Network Foundation (ONF) [3], and backed by many IT big enterprises, like Facebook and Google. There are many other SB-APIs, for instance OpFlex [4] from the worldwide networking leader, Cisco. While, northbound APIs (NB-APIs) permit interaction between the controller and the management layer. They give a big opportunity to enable programmability inside the network, and automate many repetitive networking tasks. NB-APIs can be integrated with all sort of orchestration platforms like emerging and fast growing solution OpenStack [5] or automation stacks like Puppet [6], Chef [7], Ansible [8] and others. The control layer, or the control plane is the most important piece and the smartest of an SDN network. Once it is configured by a network engineer or administrator, it takes care of all the rest of its own, from pushing policies to the different devices in the network to observing everything happening in the network and reporting it in the form of logs that can be very useful in the future to analyze the b...

show abstract

QoS for SDN-Based Fat-Tree Networks

Ghalwash

Huang

2019

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

SDN data center performance evaluation of torus and hypercube interconnecting schemes

Cited by 7 publications

References 6 publications

Enhancing QoS of Telecom Networks through Server Load Management in Software-Defined Networking (SDN)

Enhancing QoS of Telecom Networks through Server Load Management in Software-Defined Networking (SDN)

OMCH-SDN: An Overlay multi-controller Hypercube-based topology for Softwaredefined Networks

QoS for SDN-Based Fat-Tree Networks

Contact Info

Product

Resources

About