Real-world solutions to real-world streaming latency in this panel from the Content Delivery Summit at Streaming Media East. With everyone chasing reductions in latency, many with the goal of matching traditional broadcast latencies, there are a heap of tricks and techniques at each stage of the distribution chain to get things done quicker.
The panel starts by surveying the way these companies are already serving video. Comcast, for example, are reducing latency by extending their network to edge CDNs. Anevia identified encoding as latency-introducer number 1 with packaging at number 2.
Bitmovin’s Igor Oreper talks about Periscope’s work with low-latency HLS (LHLS) explaining how Bitmovin deployed their player with Twitter and worked closely with them to ensure LHLS worked seamlessly. Periscope’s LHLS is documented in this blog post.
The panel shares techniques for avoiding latency such as keeping ABR ladders small to ensure CDNs cache all the segments. Damien from Anevia points out that low latency can quickly become pointless if you end up with a low-latency stream arriving on an iPhone before Android; relative latency is really important and can be more so than absolute latency.
The importance of HTTP and the version is next up for discussion. HTTP 1.1 is still widely used but there’s increasing interest in HTTP 2 and QUIC which both handle connections better and reduce overheads thus reducing latency, though often only slightly.
The panel finishes with a Q&A after discussing how to operate in multi-CDN environments.
Super Bowl 53 has come and gone with another victory for the New England Patriots. CBS Interactive responsible for streaming of this event built a new system to deal with all the online viewers. Previously they used one vendor for acquisition and encoding and another vendor for origin storage, service delivery and security. This time the encoders were located in CBS Broadcast Centre in New York and all other systems moved to AWS cloud. Such approach gave CBS full control over the streams.
Due to a very high volume of traffic (between 30 and 35 terabits) four different CDN vendors had to be engaged. A cloud storage service optimized for live streaming video not only provided performance, consistency, and low latency, but also allowed to manage multi-CDN delivery in effective way.
In this video Krystal presents a step-by-step approach to creating a hybrid cloud/on premise infrastructure for the Super Bowl, including ad insertion, Multi-CDN delivery, monitoring and operational visibility. She emphasizes importance of scaling infrastructure to meet audience demands, taking ownership of end to end workflow, performing rigorous testing and handling communication across multiple teams and vendors.
Brightcove, an online video hosting platform with its own video player, has a lot of experience of delivery over the CDN. We saw yesterday the principles that the player, and to an extent the server, can use to deal with changing network (and to an extent changing client CPU usage) by going up and down through the ABR ladder. However this talk focusses on how the CDN in the middle complicates matters as it tries its best to get the right chunks in the right place at the right time.
How often are there ‘cache misses’ where the right file isn’t already in place? And how can you predict what’s necessary?
Yuriy even goes in to detail about how to work out when HEVC deployment makes sense for you. After all, even if you do deploy HEVC – do you need to do it for all assets? And if you do only deploy for some assets, how do you know which? Also, when does it make sense to deploy CMAF? In this talk, we hear the answers.
Nobody wants to find out about a big play or major news event on Twitter before they see it in their video stream, so reducing latency is crucial for OTT services’ success. Likewise, ultra-low latency is crucial for interactive streaming applications. Depending on your use case, a few seconds of latency might be fine, or you might need to try to hit that sub-second target.
Learn which technologies and solutions are best for your business, and make sure your viewers get their video on time, every time. In this webinar, you’ll learn the following:
Why it’s important to evaluate and improve latency end-to-end, including software and services, encoder, platform, and player
How to decide which technology and solution is best for your use case (e.g. CMAF, HLS/DASH, WebRTC, Websocket)
How chunked CMAF offers a standards-based approach that allows latency to be decoupled from segment duration
How chunked CMAF leverages existing CDN HTTP capacity to provide low-latency solutions at high scale
How WebRTC can be used to deliver live video sub-second latency at scale, and provide rich, interactive experiences for live streaming applications
How a single misconfigured component can undo any other effort to achieve low latency
How integrated solutions create new business opportunities for low latency interactive use cases
How to achieve low latency across all platforms and devices
VP of Product Strategy,
Moderator: Eric Schumacher-Rasmussen