第二周

AMVSC: A Framework of Adaptive Mobile Video Streaming in the Cloud（2012）

• Adaptive Video Streaming
• Scalable Video Coding
• Mobile Networks
• Cloud Computing

Scalability

These substreams can be encoded by exploiting three scalability features:

(i) spatial scalability by layering image ==resolution== (screen pixels)

(ii) temporal scalability by layering the ==frame rate==

(iii) quality scalability by layering the image ==compression==.

Adaptability

Adjust the video bit rate adapting to the currently time-varying available link bandwidth of each mobile user.

Contribution

AMVSC offers the best possible streaming experiences by adaptively controlling the streaming bit rate depending on the fluctuation of the link quality. AMVSC adjusts the bit rate for each user leveraging the scalable video coding. The private agent of a user keeps track of the feedback information on the link status. Private agents of users are dynamically initiated and optimized in the cloud computing platform. ==Also the real-time SVC coding is done on the cloud computing side efficiently.==

Related work

• The Microsoft’s Smooth Streaming
• Clients dynamically request videos based on local monitoring of link quality.
• Adobe and Apple
• ==What's in Common==: maintain multiple copies
• TCP throughput of a flow is predicted as a function of packet loss rate, round trip time, and packet size
• $Bandwidth = f(loss\_rate, time, packet\_size)$
• H.264 Scalable Video Coding

Framework

分层架构，VC，subVC，VB，tempVB，subVB

这张图讲的很清楚了，如何结合SVC和adaptation

这张图是讲如何衡量Link Quality

IMPLEMENTATION AND EVALUATION

$T_{window}$越大，错误率越高

Click-Play Delay

总结

这篇文章从SVC和带宽预测两个角度入手，一方面使用SVC取得了低服务器负载，另一方面通过多种网络信息预测带宽变化，来达到Adaptive Video Streaming的效果。