Streaming Media

 
Streaming Media on Facebook Streaming Media on Twitter Streaming Media on LinkedIn Streaming Media on YouTube
Sponsors

Video: How Video QoE Metrics Complement Network and Operational Metrics
Comcast Technical Solutions Architect Ribal Najjar discusses how operationalizing commonalities between QoE and QoS metrics to deliver a "super-powerful" dataset in this clip from Streaming Media East 2018.

Learn more about real-world video metrics at Streaming Media's next event.

Watch the complete video of this panel, AI103: Video AI: Mapping Consumer Streaming Experience Onto Network Operations & Decisioning, in the Streaming Media Conference Video Portal.

Read the complete transcript of this clip:

Ribal Najjar: So now that we know what Quality of Experience (QoE) metrics are, in contrast to these Quality of Service (QoS) metrics or these network metrics that we looked at, signal-to-noise ratio let's say, or retransmission, error retransmission rates and things like that, at first when we started looking at this, we're like, "There's nothing in common." One thing is doing the quality, the network telemetry is measuring at specific components' performance. It's very rigorous.

We pull these metrics every minute, every five minutes, they're always there. They're independent of the consumers. If you're not using your internet, these metrics are still being pulled and analyzed and alerted on if they go out of bound or whatever, and they're service agnostic, right? We build a network to accommodate for a whole bunch of used cases. It's not only video, a video of high-speed data (HSD), your internet experience, your experience uploading your images to the cloud, your experience in downloading movies, watching YouTube, this and that, Skype calls and so on.

And so the network has to be, to some degree, service-agnostic and work across different services. These quality of experience metrics are not. They're like, “How do I feel about watching this video?” to five seconds later I might be uploading my pictures and everything is perfect. I don't ... and so they're very service-agnostic. They're harder to quantify and qualify and they measure things end to end.

So if you're having a bad video experience, that could be anything. It could be anything in your pipeline. It could be your phone, your laptop. It could be the network. It could be your wireless network, your router. It could be from the source. It could be so many different things versus the other very focused metric telemetry.

And so when we started looking at this we're like, "You know, this is somewhat orthogonal but that's a great thing. This is really complementary to with what we really do on a day in and day out. And it works, but maybe this can bring something new to the picture along with a bunch of challenges that we have to solve for.”

So at a very high level, if we start thinking about millions of people starting and watching different video sessions, that's pretty powerful. You have now a million transactions testing your end-to-end pipeline and giving you data. So that's a super-powerful dataset that if we can operationalize, that's a big win.

Related Articles
Citrix' Josh Gray provides tips on AI model development and Reality Software's Nadine Krefetz and IBM's David Clevinger speculate on the possibilities of metadata-as-a-service in this clip from Streaming Media East 2018.
IBM Watson Media's David Clevinger discusses how media entities are currently using video AI in this clip from Streaming Media East 2018.
ZoneTV's Tom Sauer describes how machine learning can be used to overhaul the TV world and deliver more individualized experiences in this clip from Streaming Media East 2018.
IRIS.TV CEO & Co-Founder breaks down discusses IRIS.TV's approach to helping traditional media companies capture and leverage audience data and machine learning in this clip from Streaming Media East 2018.
Comcast Technical Solutions Architect Ribal Najjar defines video QoE both in terms of subjective experience and qualitative measurement in this clip from Streaming Media East 2018.
Google's Leonidas Kantothanassis explores the vast range of applications for machine learning in the media workflow and supply change in this clip from his Content Delivery Summit keynote.
Limelight VP of Architecture Jason Hofmann discusses how AI impacts content delivery optimization in this clip from Streaming Media East 2018.
Citrix Principal Architect Josh Gray explains how video enables higher-acuity metrics analysis in this clip from Streaming Media East 2018.
REELY CEO Cullen Gallagher makes the business-growth case for content owners developing an AI strategy in this clip from Streaming Media East 2018.
Gannett Senior Director Kara Chiles discusses how USA Today leveraged IRIS.TV and data to localize and personalize their Winter Olympics 2018 coverage in this clip from Streaming Media East 2018.