Understanding Video Management Planes

Abstract

While Internet video control and data planes have received much research attention, little is known about the video management plane. In this paper, using data from more than a hundred video publishers spanning two years, we characterize the video management plane and its evolution. The management plane shows significant diversity with respect to video packaging, playback device support, and CDN use, and current trends suggest increasing diversity in some of these dimensions. This diversity adds complexity to management, and we show that the complexity of many management tasks is sub-linearly correlated with the number of hours a publisher's content is viewed. Moreover, today each publisher runs an independent management plane, and this practice can lead to sub-optimal outcomes for syndicated content, such as redundancies in CDN storage and loss of control for content owners over delivery quality.

Towards a traffic map of the Internet

“…How can we infer client-to-server mappings for services that do not rely on DNS redirection or do not support ECS?. DNS cache probing enables discovery of the client-to-server mapping for services that rely on DNSbased redirection and support ECS, but some lack ECS support or use anycast [14] or customized URLs to direct a user to a site [5]. How to account for such services in the Internet traffic map remains an open question.…”

Building Reproducible Video Streaming Traffic Generators

“…We focus on Dynamic Adaptive Streaming over HTTP (DASH), HTTP Live Streaming (HLS), and basic HTML5 video as our representative streaming protocols. While there are many different streaming protocols available, prior work [1] has found that DASH and HLS accounted for 83 % of video playback time (2018), thus making the inclusion of both protocols in our initial work a straightforward choice.…”

“…2). We have considered other protocols like RTMP, but leave its support for future work: prior work found that RTMP and others [1] are not widely deployed today.…”

“…Delivering video across the Internet is supported by a diverse set of infrastructure, client/server software, encoding algorithms, and network protocols. Although many parts of the end-to-end video delivery on the Internet has been studied in great detail [1,3,9,11], there are no readily available tools for video traffic to support testbedbased experiments. Prior work in traffic generation and simulation typically focus on maximizing throughput for benchmarks and stress testing [12] or on simulating the behavior of the underlying protocols (TCP, UDP, and others) [2,15,16].…”

Evaluating the Real-World Performance of 5G Fixed Wireless Broadband in Rural Areas

“…Despite the fact that Internet video streaming has grown tremendously over the last decade, it is still considered one of the most challenging applications in modern networks [16]. Video streaming requires the steady flow of information and delivery of packets in a timely manner.…”