Published June 6, 2021 | Version v1
Conference paper Open

First Scalable Machine Learning Based Architecture for Cloud-native Transport SDN Controller

Creators

  • 1. Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)
  • 2. KDDI Research, Inc.

Description

We present a cloud-native architecture with a machine learning QoT predictor that enables cognitive functions in transport SDN controllers. We evaluate the QoT predictor training and auto-scaling capabilities in a real WDM/SDM testbed.

Notes

Grant numbers : AURORAS - Autonomic and disaggregated optical networks leveraging edge computing and photonic technologies (RTI2018-099178-B-I00) project.

Files

First Scalable Machine Learning Based.pdf

Files (749.6 kB)

Name Size Download all
md5:bff10719d943619abb442cc9e3d00dfe
749.6 kB Preview Download

Additional details

Funding

European Commission
TeraFlow – Secured autonomic traffic management for a Tera of SDN flows 101015857