Utilizing Massive Viewers for Video Transcoding in Crowdsourced Live Streaming

Qiyun He, Cong Zhang, Jiangchuan Liu

Abstract: Driven by the advances in personal computing devices and the prevalence of broadband network and wireless mobile network accesses, Crowdsourced Live Streaming (CLS) platforms have emerged in recent years, through which numerous broadcasters lively stream their video content, e.g., live events or online game scenes, to fellow viewers. Compared to professional video producers and broadcasters, these new generation broadcasters are highly heterogenous in terms of the network/system configurations and therefore the generated video quality, which calls for massive encoding and transcoding in order to unify the video sources and serve multiple quality versions to viewers with different configurations. On the other hand, with the rapid evolution in the hardware industry, high performance processors (e.g., Intel Core i7-4790K CPU) become mainstream in personal computer market. More end devices can easily transcode high quality videos in realtime. We witness huge computational resource among the massive fellow viewers that could potentially be used for transcoding. In this paper, inspired by fog computing, we propose Crowd-Transcoding, a novel framework for CLS systems that offloads the transcoding assignment to the massive viewers. We identify that the key challenges in CrowdTranscoding are to detect qualified stable viewers and to properly assign them to the source channels. We put forward Viewer Crowdsourcing Transcode Scheduler (VCTS) to smartly schedule the workload assignment. Our solution has been evaluated under diverse viewer/channel conditions as well as different parameter settings. The trace-driven simulation confirms the superiority of CrowdTranscoder, while our PlanetLab-based and real world end-viewer experiments show the practical performance of our approach, which also give hint to the further enhancement.

External IDs:dblp:conf/IEEEcloud/HeZL16