Operational Transformation Via Machine Learning (2018)

By Shamil Assylbekov, PhD. & Devin Levy, Charter Communications

In the current paradigm of Operations acting in a reactive, post hoc manner, something has got to give. MSOs cannot continue to throw bodies at problems in efforts to remediate outages, customer impacting events and impairments. Instead, a data-driven Machine Learning (ML) approach needs to be utilized to change the tide for the better. Cable operators have the ability to merge heterogeneous data from various sources in efforts to qualify and classify problem areas. This will ultimately lead to ML-driven operations which will result in a better sustained customer experience and afford the opportunity for the MSO to work under a lean operations model while employing top engineers to do the work of what would have previously taken dozens of engineers to handle in a post-hoc world. Operational problems go past operations expenditure. Customer impacting events is the name of the game, and by utilizing different ML approaches for different issues, one can classify various events that occurred, provide actionable intelligence and network automation to curtail outages, reduce the mean time to resolution (MTTR) of events in the end providing a better customer experience. Initial efforts of our group have yielded a reduced MTTR for outages and impairments, less escaped defects for feature enhancements, actionable intelligence that affords us the opportunity to make data driven decisions rather than gut reactions or best efforts. This result was mainly achieved via the Deep Learning approach for the purposes of anomaly detection, and a mixture of ML approaches for the purposes of escaped software defect categorizations.

At Charter, ML has made Operations a more intelligent organization. Some of the decisions are now made with real time actionable intelligence via our own plethora of analytics; we now have ability to improve the customer experience on a daily basis. And, we encourage the adoption of this new operational transformation, for the betterment of our industry.

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

Similar Papers

Simplifying Field Operations Using Machine Learning
By Sanjay Dorairaj, Bernard Burg & Nicholas Pinckernell, Comcast Corporation; Chris Bastian, SCTE
2017
Applications of Machine Learning in Cable Access Networks
By Karthik Sundaresan, Nicolas Metts, Greg White, Albert Cabellos-Aparicio, CableLabs
2016
Network Capacity and Machine Learning
By Dr. Claudio Righetti, Emilia Gibellini, Florencia De Arca, Carlos Germán Carreño Romano, Mariela Fiorenzo, Gabriel Carro & Fernando Rodrigo Ochoa, Cablevisión S.A.
2017
Machine Learning: The Past, Present and the Future
By Narayan Srinivasa, Intel Corporation
2016
Embracing Service Delivery Changes with Machine Learning
By Andrew Sundelin, Guavus, Inc.
2018
Toward Automated Intelligent Resource Optimization for vCMTS Using Machine Learning
By Kieran Mulqueen, Michael O’Hanlon, Marcin Spoczynski, Brendan Ryan, Thijs Metsch, Leonard Feehan & Ruth Quinn, Intel
2018
Cloud-DVR Real-Time Splunk-Based Monitoring and Alerting System
By Shlomo Ovadia, Ph.D. & Jenson Thottian, Charter Communications
2017
Data Communications Via CATV Systems
By Thomas Chuang, Vilma, Inc.
1970
A 4.5 KM Operational Fiber Optic Communications System
By Frederic N. Wilkenloh, Comm/Scope Company & Dr. Marshall C. Hudson, Valtec Corporation
1978
CATV Via Satellite
By Frederick W. Ford, G. Norman Penwell, Louis B. Early, Robert D. Briskman, Irving A. Kahn, Frank W. Norwood, Nathaniel E. Feldman,
1969
More Results >>