Network function virtualization: Difference between revisions

Revision as of 09:46, 23 March 2022

Revision as of 16:22, 17 April 2022

Line 8:

==Background==

Product development within the telecommunication industry has traditionally followed rigorous standards for stability, protocol adherence and quality, reflected by the use of the term [[carrier grade]] to designate equipment demonstrating this high reliability and performance factor.<ref>{{cite journalmagazine|url=https://www.wired.com/insights/2013/03/how-low-cost-telecom-killed-five-9s-in-cloud-computing/ |title=How Low-Cost Telecom Killed Five 9s in Cloud Computing |journalmagazine=Wired |date= 2013-03-13|access-date=2016-06-27|last1=Stephenson |first1=Rick}}</ref> While this model worked well in the past, it inevitably led to long product cycles, a slow pace of development and reliance on proprietary or specific hardware, e.g., bespoke [[application-specific integrated circuit]]s (ASICs). This development model resulted in significant delays when rolling out new services, posed complex interoperability challenges and significant increase in CAPEX/OPEX when scaling network systems & infrastructure and enhancing network service capabilities to meet increasing network load and performance demands. Moreover, the rise of significant competition in communication service offerings from agile organizations operating at large scale on the public Internet (such as [[Google Talk]], [[Skype]], [[Netflix]]) has spurred service providers to look for innovative ways to disrupt the status quo and increase revenue streams.

==History==

Line 138:

==Performance study==

Recent performance study on NFV focused on the throughput, latency and jitter of virtualized network functions (VNFs), as well as NFV scalability in terms of the number of VNFs a single physical server can support.<ref>{{cite journal|url=https://ieeexplore.ieee.org/document/7781548|title=Toward High-Performance and Scalable Network Functions Virtualization|year=2016|doi=10.1109/MIC.2016.111|last1=Wang|first1=Chengwei|last2=Spatscheck|first2=Oliver|last3=Gopalakrishnan|first3=Vijay|last4=Xu|first4=Yang|last5=Applegate|first5=David|journal=IEEE Internet Computing|volume=20|issue=6|pages=10–20|s2cid=15518060}}</ref>

Open source NFV platforms are available, one representative is openNetVM.<ref name="OpenNetVM">{{cite journal|title=OpenNetVM: A Platform for High Performance Network Service Chains|url=http://faculty.cs.gwu.edu/timwood/papers/16-HotMiddlebox-onvm.pdf|doi=10.1145/2940147.2940155|doi-access=free|s2cid=13706879}}</ref> openNetVM is a high performance NFV platform based on DPDK and Docker containers. openNetVM provides a flexible framework for deploying network functions and interconnecting them to build service chains. openNetVM is an open source version of the NetVM platform described in NSDI 2014 and HotMiddlebox 2016 papers, released under the BSD license. The source code can be found at GitHub:openNetVM<ref>{{cite web|url=https://github.com/sdnfv/openNetVM|title=GitHub- OpenNetVM|website=[[GitHub]]}}</ref>

==Cloud-native Network Functions==