KREONET-S: Software-Defined Wide Area Network Design and Deployment on KREONET.

Saved in:

Bibliographic Details
Title:	KREONET-S: Software-Defined Wide Area Network Design and Deployment on KREONET.
Authors:	Dongkyun Kim¹ mirr@kisti.re.kr, Yong-Hwan Kim² yhkim.086@kisti.re.kr, Chanjin Park² pcj0722@kisti.re.kr, Kyu-Il Kim² kisados@kisti.re.kr
Source:	IAENG International Journal of Computer Science. Feb2018, Vol. 45 Issue 1, p100-106. 7p.
Subjects:	Software-defined networking, Computer network software, Big data, Internet of things, Quality of service
Abstract:	Software-defined networking (SDN) has emerged to achieve open, programmable, virtualized and dynamic network environment for innovative applications and services which are totally apart from traditional hardware-oriented, fixed, closed network infrastructure. This paper indicates development and deployment of KREONET-S infrastructure which is designed to realize software-defined wide area network (SD-WAN) in Korea. The principal components of KREONET-S include SDN data plane networks (core and edge network devices), distributed control platform for SD-WAN based on Open Network Operating System (ONOS), and ONOS-based applications/ services. Each control instance is geographically distributed in distant locations in Korea to gain SDN scalability, sustainability, performance in particular. New SD-WAN service scenarios and use-cases are developed based on the KREONET-S design, development, and deployment in this paper. Three service scenarios are uniquely categorized as pure SDN services, SDN-IP services and federated SDN services where virtual network provisioning and SDN-to-Internet extended connectivity are considered principal use cases. In addition, we setup a network performance evaluation environment in conjunction with the distributed control platform of KREONET-S which is a 7-node ONOS cluster centering on international data paths between Korea and USA. Since the data plane network of KREONET-S provides multiple bi-directional links between distant locations, required flow rules or intents have been installed at the SDN core and edge network devices to situate end-to-end (host-to-host) paths in place for each network performance evaluation. In this test, we gained the desired network throughput, minimal delay and constant jitter which are massively demanded by advanced data-intensive science researchers and experimenters. The performance is measured and presented through a-first-of-itskind international deployment of SD-WAN infrastructure in Korea and USA under geographically distributed control platform. KREONET-S has been advanced to provide end-toend production SD-WAN environment for those demanding time-to-research and time-to-collaboration in high-end research areas such as Supercomputing, Data-intensive Science, and Big Data/IoT. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Software-defined networking (SDN) has emerged to achieve open, programmable, virtualized and dynamic network environment for innovative applications and services which are totally apart from traditional hardware-oriented, fixed, closed network infrastructure. This paper indicates development and deployment of KREONET-S infrastructure which is designed to realize software-defined wide area network (SD-WAN) in Korea. The principal components of KREONET-S include SDN data plane networks (core and edge network devices), distributed control platform for SD-WAN based on Open Network Operating System (ONOS), and ONOS-based applications/ services. Each control instance is geographically distributed in distant locations in Korea to gain SDN scalability, sustainability, performance in particular. New SD-WAN service scenarios and use-cases are developed based on the KREONET-S design, development, and deployment in this paper. Three service scenarios are uniquely categorized as pure SDN services, SDN-IP services and federated SDN services where virtual network provisioning and SDN-to-Internet extended connectivity are considered principal use cases. In addition, we setup a network performance evaluation environment in conjunction with the distributed control platform of KREONET-S which is a 7-node ONOS cluster centering on international data paths between Korea and USA. Since the data plane network of KREONET-S provides multiple bi-directional links between distant locations, required flow rules or intents have been installed at the SDN core and edge network devices to situate end-to-end (host-to-host) paths in place for each network performance evaluation. In this test, we gained the desired network throughput, minimal delay and constant jitter which are massively demanded by advanced data-intensive science researchers and experimenters. The performance is measured and presented through a-first-of-itskind international deployment of SD-WAN infrastructure in Korea and USA under geographically distributed control platform. KREONET-S has been advanced to provide end-toend production SD-WAN environment for those demanding time-to-research and time-to-collaboration in high-end research areas such as Supercomputing, Data-intensive Science, and Big Data/IoT. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X