1. 程式人生 > >Oboe: Auto-tuning Video ABR Algorithms to Network Conditions

Oboe: Auto-tuning Video ABR Algorithms to Network Conditions

1.摘要:

BLOA,MPC的方法:引數對於網路條件比較敏感

Oboe:對於一個ABR演算法,預先計算可能的引數(對於不同的網路環境),實時的根據網路環境選擇最好的引數

ABR;(a) chop a video into chunks, each of which is encoded at a range of bitrates (or qualities); and (b) choose which
bitrate level to fetch a chunk at based on conditions such as the amount of video the client has buffered and the recent
throughput achieved by the client. 

 they do not perform uniformly well across the range of network conditions seen in practice because their parameters
are sensitive to throughput variability。

具體的演算法:分為兩種:只依據buffer的佔用情況,buffer的佔有和吞吐量的估計同時使用

one that makes bitrate switching decisions on buffer occupancy alone (BOLA) , another that uses
both throughput and buffer occupancy (HYB, a widely deployed algorithm), and a third that also optimizes decisions
across a finite lookahead horizon (RobustMPC)