Live Streaming at Scale Requires Improving QoE in the Last Mile, Especially Within Smaller ISPs

Technical challenges are a current reality for live streaming events, which is magnified even further by events with a large concurrent stream count. Load testing is complex, and troubleshooting in real-time is challenging, even for the best engineering teams. I recently talked about how, on average, 5-10% of streaming subscribers are experiencing poor QoE (a conservative estimate). This number equates to unvalidated content performance metrics, or “blind spots,” most common in harder-to-reach ISP networks. These networks are typically multiple hops away from major CDNs, meaning streamed content takes a much more complex path to reach viewers while providing much less (e.g., little to no) QoE visibility. If any geographical area or subscriber demographic is more likely to experience live-streaming issues, it’s in this blind spot.

Why does this matter? Peak streaming events like live sports create high spikes in network traffic. One ISP in New York sees network traffic increase by 25% or more during average streaming-only NFL games. For smaller ISP networks, such traffic spikes can easily overload complex delivery paths and create congestion, causing a knock-on effect of buffering, slow start times, low bitrates, and dropped packets. In other words, content delivery and performance problems for 5-10% of subscribers in remote areas can suddenly trigger QoE issues at scale, which can come at a significant cost. Tackling performance issues for a small percentage of subscribers in rural ISP networks may seem counterintuitive. Still, I would argue that it’s a sensible starting point in reinforcing major live streaming events for the future. We know that networks in the last mile can have QoE blind spots that are difficult to validate, and capacity and bandwidth can quickly become constrained in these locations. We know traffic spikes in smaller ISPs can cause network congestion upstream, and subscribers with consistently poor streaming quality have a higher potential to levy complaints across social media.

While almost every content provider leverages multiple CDNs to mitigate risk around content delivery and streaming performance, ISPs in rural areas are often overlooked. These hard-to-reach networks are still interconnected with the larger streaming media landscape, and optimizing QoE for a small set of subscribers might make a big difference. Locally embedded caches are one solution to targeting smaller networks and are gaining more traction with deployments. Subscribers’ proximity to the video delivery point has shown a direct impact on streaming performance, as the content delivery path is effectively shortened.

One company, Netskrt, partners with content providers and ISPs to close the performance metrics gap and improve streaming quality, specifically in harder-to-reach areas. Their managed service pre-positions popular content and enables multiple requests for the same content to be collapsed into a single stream—a massive advantage for high-profile live streaming events. It’s a similar approach large CDNs have taken in deploying caches in the last mile but with a focus on areas where major CDNs may not be deployed.

Since I profiled Netskrt last year, they’ve grown their headcount by 30% and are actively expanding abroad in the UK, Europe, and South America. This might be a feasible solution for those looking to validate and improve QoE all the way to the last mile without redesigning network infrastructure. Netskrt is scheduled to speak at the NAB Streaming Summit on April 7th, and you can check out the details of their session here.