An analysis of live streaming workloads on the internet

TLDR

This study uses the most extensive live‑streaming dataset on the Internet to date. The paper investigates live‑streaming workloads from a large CDN, offering a macroscopic analysis of popularity, arrival patterns, session duration, transport protocols, client diversity, and recurring‑event participation. The authors analyze 70 million requests over three months from 5,000 URLs and 200 countries, applying statistical models to characterize popularity, arrival processes, session durations, transport protocols, client diversity, and recurring‑event participation. Results reveal a two‑mode Zipf popularity, exponential short‑interval interarrivals, heavy‑tailed session durations, limited UDP reach, broad geographic audience even for small streams, and recurring users lasting at least a third of event days.

Abstract

In this paper, we study the live streaming workload from a large content delivery network. Our data, collected over a 3 month period, contains over 70 million requests for 5,000 distinct URLs from clients in over 200 countries. To our knowledge, this is the most extensive data of live streaming on the Internet that has been studied to date. Our contributions are two-fold. First, we present a macroscopic analysis of the workload, characterizing popularity, arrival process, session duration, and transport protocol use. Our results show that popularity follows a 2-mode Zipf distribution, session interarrivals within small time-windows are exponential, session durations are heavy-tailed, and that UDP is far from having universal reach on the Internet. Second, we cover two additional characteristics that are more specific to the nature of live streaming applications: the diversity of clients in comparison to traditional broadcast media like radio and TV, and the phenomena that many clients regularly join recurring events. We find that Internet streaming does reach a wide audience, often spanning hundreds of AS domains and tens of countries. More interesting is that small streams also have a diverse audience. We also find that recurring users often have lifetimes of at least as long as one-third of the days in the event.