& cplSiteName &

Unlocking Big Data for Operational Intelligence

Chris Menier
12/27/2016
50%
50%

In a competitive environment where consumers and businesses have more service providers to choose from than ever, cable companies' ability to capitalize on superior networking technology and service capabilities can only be realized to its full potential if customers are confident that their quality of experience is second to none. In this sense, the customer's overall quality of experience has become cable's most important product.

The way to meet these customer experience and operational cost challenges is to reduce the impact of service impairments through preventive action and more rapid responses to issues that directly affect customers. This requires a comprehensive, highly automated and very granular approach to gathering, correlating and analyzing data from every component that contributes to overall performance, whether in the core, the edge, transport links, customer premise equipment or personal devices for services on the go.

Fortunately, the facilities, network and device technologies underlying cable's move into this new service era have been designed to accommodate the need to generate useful performance data, ensuring that operators have plenty of data to aggregate and correlate in the analytical process. As a result, MSOs are now dealing with a big data environment that requires industrial-scale prescriptive analytics to provide actionable insight into everything pertinent to assessing service performance and ensuring superior customer experience.

Such use case-driven applications optimized for cable must be able to look across all relevant points of functionality tied to any given service in real time and put this vast amount of data into context to diagnose the causes behind emerging and customer-perceived problems with minimal human intervention.

Defining the capabilities of a cable operational intelligence framework
To adapt a service operations model, cable operators need customer-aware analytics built on top of an operational intelligence framework that leverage data mining processes aggregating useful data from every available source in real time and at massive scale. The OI framework must be equipped with interfaces that support integration with all existing data platforms, including HFC telemetry, change management events, element management system (EMS), network management system (NMS) alarms, customer-care interactions and others outside the operator's domain.

With the ability to use all these resources for aggregating performance data across the end-to-end cable infrastructure, an operational intelligence framework can provide operators with everything they need to capitalize on the cost-saving and QoE benefits of pre-emptive operational efficiency and reduced response times to outages and systemic issues. Process engines in the Operational Intelligence Framework can be categorized as follows:

  • Large-scale real-time ingest: The magnitude of the collection layer tied to all these data-generating resources is far beyond what is often claimed for cable-oriented OSS systems. It must be capable of collecting massive amounts of network streaming and enterprise stored data that can scale well beyond typical enterprise platforms.

  • Data enrichment and correlation: In preparation for applying analytics processes, all the incoming data must be instantly categorized and correlated as it applies to any use of any service underway at any given moment.

  • Machine intelligence applied to anomaly detection and diagnostics: With customer-aware analytics, cable operators can establish reference baselines of aggregate system performance from the very local service level to regional and national levels. Leveraging all the information generated through the above processes, the analytics application continually performs analysis of all anomalies needing either preventive or alarm-responsive action.

  • Connected: Through a series of APIs, the discovered anomalies and solutions must be seamlessly integrated within the existing processes and support systems.

    A Tier 1 MSO's use of operational intelligence
    One example of how a cable operator is using customer-aware analytics to boost the customer experience is the strategy of a top North American MSO that wanted to differentiate between plant and CPE-based issues to minimize truck rolls, which cost approximately $80 per roll. In this case, the application has been directed to maintain an automated real-time view of baselines and anomalies across the MSO's footprint in all its regions.

    The operator is able to instantly isolate the issue before customer call volume intensifies. Once any given anomaly crosses a machine-learned threshold (rather than a pre-set threshold) in terms of numbers of people affected, duration of the issue or other parameters, the platform can zoom in on the data pouring in over a selected period of time from the affected area to perform the correlations and analysis essential to identifying the root issue.

    The operator can also direct the analytics application, using standard APIs, to automatically interact with IVR systems to create messages that will be heard by any affected subscribers who call in to customer service. Additionally, the framework can take actions on specific devices in the home; for example, it can interact with the ACS to push new firmware, reboot the device, reset factory defaults and change the WiFi channel, etc. The subscriber can be immediately informed that the operator is taking remedial action, what the nature of the problem is and when it should be fixed.

    Based on the field experiences of this MSO and others, once the operational intelligence framework is in place, about 30 percent of the truck rolls ordered with previous procedures can be eliminated. In the first year alone, the total in annual cost savings was $70 million.

    By quickly identifying and addressing root causes to issues that are having a tangible impact on customer experience in any location, cable operators can lower the costs of service visits and call center operations while minimizing the impact of performance lapses on customer experience. With a highly automated approach to identifying, prioritizing and proactively addressing emerging problems, operators can manage maintenance operations to maximum effect and sustain and drive improvements in customer satisfaction.

    A full technical paper on this topic was presented at the SCTE Cable Tec Expo 2016 in September.

    — Chris Menier, Vice President, Products & Strategy, Guavus

    (0)  | 
    Comment  | 
    Print  | 
  • Newest First  |  Oldest First  |  Threaded View        ADD A COMMENT
    More Blogs from Column
    Mobile edge computing (MEC) and a cloud-native core are necessary ingredients for the future 5G NFV network, argues Ian Maclean of Metaswitch.
    Once pay-TV providers embrace the idea, they must take a comprehensive, company-wide approach to carry out such fundamental changes.
    5G will require a fresh look at RF characteristics as operators deploy next-gen tech on very high-band frequencies.
    MVPDs have an opportunity to make digital investments without upending their current business.
    VoLTE, in the end, becomes a cloud and NFV story, Metaswitch's Ian Maclean argues.
    Featured Video
    From The Founder
    The 'gleaming city on a hill,' Steve Saunders calls it. But who is going to take us from today's NFV componentry to the grand future of a self-driving network? Here's a look at the vendors hoping to make it happen.
    Flash Poll
    Upcoming Live Events
    September 28, 2017, Denver, CO
    October 18, 2017, Colorado Convention Center - Denver, CO
    November 1, 2017, The Royal Garden Hotel
    November 1, 2017, The Montcalm Marble Arch
    November 2, 2017, 8 Northumberland Avenue, London, UK
    November 10, 2017, The Westin Times Square, New York, NY
    November 30, 2017, The Westin Times Square
    All Upcoming Live Events
    Infographics
    With the mobile ecosystem becoming increasingly vulnerable to security threats, AdaptiveMobile has laid out some of the key considerations for the wireless community.
    Hot Topics
    Could the Connected Car Help Prevent Terrorism?
    Dan Jones, Mobile Editor, 9/15/2017
    Cities Slam FCC on Broadband Proceedings
    Mari Silbey, Senior Editor, Cable/Video, 9/15/2017
    Apple's New iPhones: No Gigabit LTE for You!
    Dan Jones, Mobile Editor, 9/14/2017
    1 Million Pirate Set-Top Boxes Sold in the UK
    Aditya Kishore, Practice Leader, Video Transformation, Telco Transformation, 9/20/2017
    Close the Loop to Automate Service Assurance
    Carol Wilson, Editor-at-large, 9/14/2017
    Animals with Phones
    Live Digital Audio

    Understanding the full experience of women in technology requires starting at the collegiate level (or sooner) and studying the technologies women are involved with, company cultures they're part of and personal experiences of individuals.

    During this WiC radio show, we will talk with Nicole Engelbert, the director of Research & Analysis for Ovum Technology and a 23-year telecom industry veteran, about her experiences and perspectives on women in tech. Engelbert covers infrastructure, applications and industries for Ovum, but she is also involved in the research firm's higher education team and has helped colleges and universities globally leverage technology as a strategy for improving recruitment, retention and graduation performance.

    She will share her unique insight into the collegiate level, where women pursuing engineering and STEM-related degrees is dwindling. Engelbert will also reveal new, original Ovum research on the topics of artificial intelligence, the Internet of Things, security and augmented reality, as well as discuss what each of those technologies might mean for women in our field. As always, we'll also leave plenty of time to answer all your questions live on the air and chat board.

    Like Us on Facebook
    Twitter Feed