High Performance On-Demand Video Transcoding Using Cloud Service

Video streams usually have to be transcoded to match the characteristics of viewers' devices. Transcoding is a computationally expensive and time-consuming task. Streaming service providers have to store numerous transcoded versions of a given video to serve various display devices, which becomes cost-prohibitive while the video streaming demands increase significantly. Given the fact that viewers' access pattern to video streams follows a long tail distribution, we propose to transcode video streams with low access rate in an on-demand manner using cloud computing services. The challenge in utilizing cloud services for on-demand video transcoding is to maintain a robust QoS for viewers and cost-efficiency for streaming service providers. To address this challenge, in this dissertation, we present a Cloud-based Video Streaming Service (CVSS) architecture which includes a QoS-aware scheduling method to efficiently map video streams to cloud resources. With a detailed study and anlysis of the performance affinity of the transcoding operations on different types of Virtual Machines (VMs), we proposed self-configurable VM provisioning policies to transcode video in a more cost-efficient way. Simulation results demonstrate that with the policies, CVSS architecture maintains a robust QoS for viewers while reducing the incurred cost of the streaming service provider by up to 85%. This dissertation also presents a Cloud-based Video Live Streaming (VLSC) architecture that facilitates transcoding for live video streaming while considering QoS.