Design of a stateless low-latency router architecture for green software-defined networking

Silvia Saldaña Cercós, Ramon M. Ramos, Ana C. Ewald Eller, Magnos Martinello, Moisés R.N. Ribeiro, Anna Manolova Fagertun, Idelfonso Tafur Monroy

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Expanding software defined networking (SDN) to transport networks requires new strategies to deal with the large number of flows that future core networks will have to face. New south-bound protocols within SDN have been proposed to benefit from having control plane detached from the data plane offering a cost- and energy-efficient forwarding engine. This paper presents an overview of a new approach named KeyFlow to simultaneously reduce latency, jitter, and power consumption in core network nodes. Results on an emulation platform indicate that round trip time (RTT) can be reduced above 50% compared to the reference protocol OpenFlow, specially when flow tables are densely populated. Jitter reduction has been demonstrated experimentally on a NetFPGA-based platform, and 57.3% power consumption reduction has been achieved.

Original languageEnglish
Title of host publicationOptical Metro Networks and Short-Haul Systems VII
EditorsAtul K. Srivastava, Benjamin B. Dingel, Achyut K. Dutta
Place of PublicationBellingham
PublisherSPIE
Number of pages7
Volume9388
ISBN (Electronic)9781628414783
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes
EventOptical Metro Networks and Short-Haul Systems VII - San Francisco, United States
Duration: 10 Feb 201512 Feb 2015

Conference

ConferenceOptical Metro Networks and Short-Haul Systems VII
CountryUnited States
CitySan Francisco
Period10/02/1512/02/15

Keywords

  • Energy-efficiency
  • NetFPGA
  • OpenFlow
  • Optical networks

Fingerprint Dive into the research topics of 'Design of a stateless low-latency router architecture for green software-defined networking'. Together they form a unique fingerprint.

Cite this