Towards Hybrid Cloud-assisted Crowdsourced Live Streaming: Measurement and Analysis

TL;DR

This paper investigates the resource challenges in crowdsourced live streaming systems like Twitch, especially for unpopular channels, and proposes a hybrid cloud solution for efficient resource allocation and cost reduction.

Contribution

It introduces a hybrid cloud-assisted framework for service partitioning in CLS systems, optimizing resource usage for unpopular channels.

Findings

Hybrid cloud approach reduces costs by flexible resource allocation.

Unpopular channels consume significant system resources despite low viewership.

Trace-driven evaluation demonstrates effectiveness of the proposed solution.

Abstract

Crowdsourced Live Streaming (CLS), most notably Twitch.tv, has seen explosive growth in its popularity in the past few years. In such systems, any user can lively broadcast video content of interest to others, e.g., from a game player to many online viewers. To fulfill the demands from both massive and heterogeneous broadcasters and viewers, expensive server clusters have been deployed to provide video ingesting and transcoding services. Despite the existence of highly popular channels, a significant portion of the channels is indeed unpopular. Yet as our measurement shows, these broadcasters are consuming considerable system resources; in particular, 25% (resp. 30%) of bandwidth (resp. computation) resources are used by the broadcasters who do not have any viewers at all. In this paper, we closely examine the challenge of handling unpopular live-broadcasting channels in CLS systems and present a comprehensive solution for service partitioning on hybrid cloud. The trace-driven evaluation shows that our hybrid cloud-assisted design can smartly assign ingesting and transcoding tasks to the elastic cloud virtual machines, providing flexible system deployment cost-effectively.