Chat iconGet in touch

Applying machine learning to intent-based networking and NFV scaling strategies

By June 20, 2016 No Comments

Previous Openet blogs have commented on the importance of real-time automation intelligence to enable new technologies like Network Functions Virtualization (NFV) to deliver a programmable network that can rapidly automatically scale and adapt to changing needs. The adoption of such technologies promises a new generation of device innovation and improved quality of experience for subscribers. 

However, the “operationalization” of networks based on NFV demands a revolutionary change in how networks are deployed and managed and presents operators with multiple new challenges, not made any easier by the impending move to 5G architectures and the rise of IoT. 

Machine learning comes to the rescue by enabling service providers employ closed loop control to automate the life cycle of network-based services. Using Machine learning algorithms to build a model from example inputs and make automated data-driven predictions or decisions. This will ultimately provide intelligent intent-driven networks where services requests need only specify communications requirements, independent from the underlying network details.

The industry is collaborating on making this a reality. For example the OPNFV project is supported by a growing group of 55+ member companies committed to advancing a flexible, open source framework for NFV.  Openet is a silver member of OPNFV and a participant in its “Predict” project.  This aims to develop a failure prediction system for NFV deployments.

Openet is delighted in joining Telefonica at the upcoming OPNFV summit in Berlin to present on the topic of Applying Machine Learning to Intent-based Networking and NFV Scaling Strategies.

Venue:                 InterContinental Hotel, Berlin, Germany, Room: Potsdam III

Time:                    Thursday, June 23 11:50 AM – 12:20

Speakers:             Diego R. Lopez Senior Technology Expert, Telefonica

Glen Lockhart Principal Engineer, Openet

The talk will highlight how Machine Learning techniques can be used to address different aspects of the operation and control of NFV and propose future OPNFV activities in this area. First, Diego will introduce how Machine Learning is being applied by the CogNet project to address intent-based networking, and discuss the architecture defined there as a potential framework for future ML integration.

Glen will demonstrate a policy-based system for automating VNF scaling using performance data collection and analytics with machine learning (ML), based on OPNFV Brahmaputra and the underlying OpenStack telemetry system (Ceilometer), as well as the open-source Apache Kafka, Apache Zookeeper and Apache Spark streaming and MLlib libraries. Available as open-source, it combines predictive and reactive inputs to make the VNF scaling decision and trigger action in the MANO stack. The presentation will provide an overview of the system, demonstrate the VNF auto-scaling use case and discuss how this system will fit into a future OPNFV release.