Leveraging Machine Intelligence and Operations Analytics (2017)

By Andrew Sundelin, Guavus

Operators will benefit from the flexibility that comes with the ability to apply IT virtualization technology to CPE and network functions. However, virtualization introduces additional complexity, creating the need for an orchestration layer with more sophisticated assurance capabilities, including data center and network analysis capabilities, encompassing physical and virtual resources in real time.

This paper focuses on a valuable use-case, which leverages operations analytics (OA) and machine intelligence (MI) to drive a variety of resource allocations within virtualized networks. This resource allocation applies both within the “cloud” and in the access network.

Within the cloud, OA and MI can be utilized to predict when additional capacity is needed for services such as additional compute to maintain quality of experience (QoE) for a cloud-based guide or additional storage for a cloud-based DVR system. These technologies can also be utilized to predict unexpectedly popular content and pre-position it optimally within content distribution networks. Within the access network, OA and MI can be utilized for congestion prediction and service optimization. For example, trends in PHY performance parameters can be leveraged to predict the need to tweak OFDM/OFDMA profiles for maximal efficiency.

This paper also explores an emerging concept: “Software-Defined Operations (SDO),” which applies Software-Defined Networking’s (SDN’s) separation of data and control planes to key pieces of modern care and operations equipment. For example, if one views technical support calls as the data then the Interactive voice response (IVR) system is the equivalent of a router (and, thus, part of the data plane) and programming that IVR system is, thus, part of the control plane. With that concept established, the paper looks at the power SDO can have when combined with Operations Analytics.

Virtualization creates benefits and challenges, both of which are driven by the new dynamicity of network services, topology, inventory and hardware resources. The combined application of OA technologies and MI can help operators to assure virtualization by providing an automated, real-time approach that learns from data and autonomously adapts to new information, intuiting connections and relationships to proactively detect anomalies and prescribe solutions.

By clicking the "Download Paper" button, you are agreeing to our terms and conditions.

Similar Papers

Embracing Service Delivery Changes with Machine Learning
By Andrew Sundelin, Guavus, Inc.
2018
Predicting Service Impairments from Set-top Box Errors in Near Real-Time and What to Do About It
By Justin Watson, Comcast; Roger Brooks, Andrew Colby, Pankaj Kumar, Anant Malhotra & Mudit Jain, Guavus, Inc.
2018
Customer First: CX-Driven Augmented Operations
By Roger Brooks, Ph.D., Pankaj Kumar, Mudit Jain, Megha Vij, Nandit Jain & Andrew Colby, Guavus
2019
Applications Of Big Data Analytics To Identify New Revenue Streams & Improve Customer Experience
By Anukool Lakhina and Brennen Lynch, Guavus, Inc.
2013
Augmented Intelligence: Next Level Network and Services Intelligence
By Dr. Claudio Righetti, Mariela Fiorenzo, Omar Hurtado & Gabriel Carro, Telecom Argentina S.A.
2020
Simplifying Field Operations Using Machine Learning
By Sanjay Dorairaj, Bernard Burg & Nicholas Pinckernell, Comcast Corporation; Chris Bastian, SCTE
2017
Implement Closed-Loop Network Decisioning Now with Big Data Analytics and Fuel Future-State SDN Use Cases Through a Common Platform Deployment
By Brennen Lynch and Anukool Lakhina, Guavus, Inc.
2014
Moving from Scripted Dialogs to Automation, Omni-Channel and Predictive Analytics
By Marc Bellini, Nokia
2017
Create Data-Driven Solutions to Optimize IP Content Delivery and Identify Revenue Opportunities
By Brennen Lynch and Anukool Lakhina, Guavus, Inc.
2014
Applications of Machine Learning in Cable Access Networks
By Karthik Sundaresan, Nicolas Metts, Greg White, Albert Cabellos-Aparicio, CableLabs
2016
More Results >>