Live Streaming is the Next Big Thing

The Popularity of Streaming Video is Without Question

The popularity of streaming video is without question. More people around the world are “tuning in” to streaming services than traditional broadcast. Through “over-the-top” (OTT) services like Netflix, iFlix, Viaplay, YouTube, and others, consumers are watching the shows and videos they wish to watch, from a variety of devices, around the world. But on-demand can’t truly replace traditional TV until it provides both access to shows on-demand and live content like sports and concerts. Thankfully, many of the world’s biggest OTT services and broadcasters are moving to make their live content available in the same fashion as other video content. Unfortunately, technological limitations like network scaling to meet concurrency requirements, often prevent service operators from generating a profit for live-streamed events.

 

Part of the problem is that OTT streaming services, whether operated by stand-alone providers like Hulu or traditional broadcasters like Canal+, try to employ a traditional approach to live stream scaling by mapping their new video network architectures to legacy broadcast schemes such as content originating in a headend and being pushed to a CDN for delivery. This approach not only makes scaling difficult, but it can compromise the viewer’s Quality of Experience (QoE) as average bitrate drops in response to finite bandwidth resources. What’s needed is a joint approach, a way to combine the different elements of the delivery value chain and, ultimately, optimize delivery for the best possible QoE to the widest audience.

 

Quortex is the Answer

Quortex was founded in 2018 to enable on simple thing—allow content providers to lower their streaming costs while improving QoE. Headquartered in Rennes (France), the company is working to change live-streaming paradigms and champion a new approach that will enable a profitable way to scale delivery while maintaining quality. Quortexhas built a cloud-native solution that blurs the lines between the headend and the CDN. Our patented “Just-In-Time Everything” architecture dynamically adapts the content preparation to the audience and network variability.

 

The New Quortex Paradigm

 

A Quortex live workflow is a user-centric combination of stateless web services that process segments as independent VOD assets. These web services are only active when processing a user request for a given segment. Zero demand? Zero cost! The workflow is heavily distributed and can run across multiple machines, multiple zones, multiple regions or multiple cloud providers. Each and every segment request is load balanced and the best path is promoted to provide a real-time optimization of cost and reliability. For content distributors that employ Quortex’s technology, this gives them, amongst other advantages, the striking ability to run a live workflow on preemptible Virtual Machines, reducing the compute cost by 80%.

 

Being stateless, the Quortex cloud functions can also scale dynamically to adapt the processing to the audience, to the network conditions, or to the content provider business rules. We have implemented several feedback APIs that enable new use cases for content providers:

 

  • Profile Variability: dynamically selects the rendition ladder based on the audience, enabling an optimal customer experience during prime time while minimizing the compute cost at night
  • QoE based processing: adapts the rendition ladder to the PoP point immediate capacity,
  • Audience Aware Encoding: provides a joint optimization of the compute and CDN cost.

 

A Business Case: Audience-Aware Encoding

The result of the Quortex approach to jointly optimizing the headend and CDN costs are undeniable (as illustrated in the figure below).

 

 

If the audience is high, such as during prime time, the Quortex service will allocate more compute resources to the transcoding web service, so as to reduce the bitrate while maintaining the same visual quality. Our platform also has the ability to dynamically load balance the processing to a more powerful instance (such as the 2nd generation Intel Xeon Scalable Processors). Giving more CPU resources to the cloud-native transcoding function allows a bit-rate reduction of up to 20%.

 

This translates immediately to a 20% gain on the CDN cost while improving the Quality of Experience as it reduces the overall network traffic.

 

The Streaming Video Alliance Opportunity

We are thrilled to be part of the Streaming Video Alliance. There is no other group that combines such a mix of industry experts, focused on making concrete proposals to improve live stream delivery at scale. The great thing about the Alliance is that ISPs, software vendors, and content providers work together to provide a global solution rather than focusing on the bits and bytes. We are currently involved in the “Live Streaming” working group, which is focused on “How to scale Live Delivery”, the hottest topic of our industry!

 

About this Post

Each year, the Streaming Video Alliance opens its doors to innovative startups and small companies as part of its Membership Grant Program. For 2019, the Alliance welcomed a number of very interesting companies exploring and productizing technologies for the streaming video space. Quortex is one of those. This blog is part of a series showcasing each of our Grant Program recipients, the technical problems they hope to solve, and the value they bring to the streaming video ecosystem.

 

CEO and Co-Founder at