ONF Connect 2018 has ended
Back To Schedule
Wednesday, December 5 • 5:30pm - 6:00pm
Using INT to Feed the ML Monster

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
This talk describes an experiment that uses network telemetry collected via P4 INT and feed to a machine learning (ML) system to predict/detect network congestion state and use closed-loop control to dynamically modifiy the network to alleviate congestion.

The purpose of this experiment it so understand the capabilities that P4 INT enables and how using P4 INT as a telemetry data source compares to traditional network polling for telemetry.
As part of this experiment, the network load attributed to telemetry gathering will be studied to understand how / if P4 INT reduces the source (network and compute) for telemetry gathering. Additionally, the impact of fine grain v course grain telemetry on ML will be investigated.

avatar for David Bainbridge

David Bainbridge

Man of the Night's Watch, Ciena
David Bainbridge is a senior software architect focusing on open source within Ciena's CTO office. David has been a member of the TSC/TST and committer on ODL, ONOS, and CORD projects. David's current focus in open source is split between SDN and machine learning (as it can be applied... Read More →
avatar for A R Karthick

A R Karthick

Developer, Ciena
Karthick is a senior software engineer working within Ciena's CTO office. Karthick focuses on the fast acquisition of domain knowledge and turning that into practical implementation artifacts. He has worked on many open source projects including CORD and ONOS.

Wednesday December 5, 2018 5:30pm - 6:00pm PST
Salon 1-2