TY - GEN
T1 - Impact of multiple video representations in live streaming
T2 - 2017 IEEE International Conference on Cloud Engineering, IC2E 2017
AU - Bilal, Kashif
AU - Erbad, Aiman
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/5/9
Y1 - 2017/5/9
N2 - Video streaming is one of the most popular and highest bandwidth consumers within the Internet today. Cloud's elastic and pay-per-use model offers viable solution to varying demands of heterogeneous viewers for large-scale video providers. Video providers are heavily exploiting cloud's elastic nature to cater the scalability and heterogeneity of video steaming related tasks. For instance, Netflix moved its whole infrastructure to Amazon cloud, and Twitch, one of the largest game streaming providers is owned by Amazon and now using Amazon's cloud. Video representations refer to multiple copies of same video transcoded in multiple bitrates, such as 240, 360, 720, 1080 etc. Viewers with varying bandwidth capacities are served with matching representations based on the available bandwidth to minimize buffering time and latency. However, video transcoding is a computation and communication intensive task, therefore, not all of the live videos are transcoded to different representations. For instance, Twitch transcodes only the video streams of premium member (which have 500+ regular viewers). All of the non-premium channels are broadcasted in source stream. A fundamental question therefore is: which channels should be considered to be transcoded to multiple representations to minimize the overall cloud leased resources cost and bandwidth, and to maximize user satisfaction. In this paper, we seek answer to this question by analyzing the impact of multiple representations on cost (based on leasing cloud resources), bandwidth, and Quality of Experience (QoE, measured in terms of user satisfaction). We use Twitch workload traces captured in 2015, to conduct the experimentation, and use latest real-world broadband and representation data rate statistics from Akamai and YouTube Live, and cost from Amazon EC2 and CloudFront to validate our results. Our analysis reveals that using cloud's resources to transcode channels with more than 40 average viewers per hour with a data rate of 720p or higher, leads to low cost and bandwidth consumption, and higher QoE, as compared to streaming source video without multiple representations.
AB - Video streaming is one of the most popular and highest bandwidth consumers within the Internet today. Cloud's elastic and pay-per-use model offers viable solution to varying demands of heterogeneous viewers for large-scale video providers. Video providers are heavily exploiting cloud's elastic nature to cater the scalability and heterogeneity of video steaming related tasks. For instance, Netflix moved its whole infrastructure to Amazon cloud, and Twitch, one of the largest game streaming providers is owned by Amazon and now using Amazon's cloud. Video representations refer to multiple copies of same video transcoded in multiple bitrates, such as 240, 360, 720, 1080 etc. Viewers with varying bandwidth capacities are served with matching representations based on the available bandwidth to minimize buffering time and latency. However, video transcoding is a computation and communication intensive task, therefore, not all of the live videos are transcoded to different representations. For instance, Twitch transcodes only the video streams of premium member (which have 500+ regular viewers). All of the non-premium channels are broadcasted in source stream. A fundamental question therefore is: which channels should be considered to be transcoded to multiple representations to minimize the overall cloud leased resources cost and bandwidth, and to maximize user satisfaction. In this paper, we seek answer to this question by analyzing the impact of multiple representations on cost (based on leasing cloud resources), bandwidth, and Quality of Experience (QoE, measured in terms of user satisfaction). We use Twitch workload traces captured in 2015, to conduct the experimentation, and use latest real-world broadband and representation data rate statistics from Akamai and YouTube Live, and cost from Amazon EC2 and CloudFront to validate our results. Our analysis reveals that using cloud's resources to transcode channels with more than 40 average viewers per hour with a data rate of 720p or higher, leads to low cost and bandwidth consumption, and higher QoE, as compared to streaming source video without multiple representations.
KW - Cloud
KW - Live streaming
KW - QoE
KW - Video Representations
KW - Video Transcoding
UR - http://www.scopus.com/inward/record.url?scp=85020167603&partnerID=8YFLogxK
U2 - 10.1109/IC2E.2017.20
DO - 10.1109/IC2E.2017.20
M3 - Conference contribution
AN - SCOPUS:85020167603
T3 - Proceedings - 2017 IEEE International Conference on Cloud Engineering, IC2E 2017
SP - 88
EP - 94
BT - Proceedings - 2017 IEEE International Conference on Cloud Engineering, IC2E 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 April 2017 through 7 April 2017
ER -