Enabling Inference Inside Software Switches

Yung Sheng Lu, Ching-Ju Lin

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

1 Scopus citations

Abstract

Software Defined Networking (SDN) has been emerged to solve the problem of traditional network architectures. The ability of programmable switches renders us an opportunity to have computational tasks done in the switches. With this nice property, in this work, we investigate the potential of enabling machine learning inside a network. To this end, we propose a new architecture, Intra-Network Inference (INI), which equips each switch with a recently released component, called neural compute stick (NCS), to enable intra-switch neural network inference. Unlike conventional SDN architectures, which relay backend servers to enable inference, our INI performs inference locally at switches and, thereby, reduces the data forwarding overhead and inference latency.

Original languageEnglish
Title of host publication2019 20th Asia-Pacific Network Operations and Management Symposium
Subtitle of host publicationManagement in a Cyber-Physical World, APNOMS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9784885523205
DOIs
StatePublished - Sep 2019
Event20th Asia-Pacific Network Operations and Management Symposium, APNOMS 2019 - Matsue, Japan
Duration: 18 Sep 201920 Sep 2019

Publication series

Name2019 20th Asia-Pacific Network Operations and Management Symposium: Management in a Cyber-Physical World, APNOMS 2019

Conference

Conference20th Asia-Pacific Network Operations and Management Symposium, APNOMS 2019
CountryJapan
CityMatsue
Period18/09/1920/09/19

Keywords

  • Neural Networks
  • P4
  • SDN

Fingerprint Dive into the research topics of 'Enabling Inference Inside Software Switches'. Together they form a unique fingerprint.

Cite this