Improving Optimization-Based Rate Adaptation in DASH System
Improving Optimization-Based Rate Adaptation in DASH System
复制标题
改进 DASH 系统中基于优化的速率自适应
DOI：
10.1109/icccn.2017.8038402
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Fengyuan Ren
中科院分区：
文献类型：
--
作者：
Bo Wang;Xiaohui Luo;Ping Hu;Fengyuan Ren
越来越多的商业视频播放器使用比特率自适应来根据变化的网络条件调整视频质量。基于优化的方法广泛用于HTTP动态自适应流传输（DASH）中的比特率适配。本质上，优化问题是基于缓冲器动态的预测来解决的。然而，随机块大小偏离缓冲区占用的预期值，使演变难以预测。为了消除这种影响，提高缓存占用率的预测精度，本文提出了一种基于马尔可夫决策过程的算法，该算法在决策过程中加入了块大小信息，使得决策过程只需要考虑网络容量的变化。实验结果表明，该方案能有效消除块大小变化引起的性能振荡，获得较好的QoE。
More and more commercial video players use bitrate adaptation to adjust video quality according to varying network conditions. Optimization-based approaches are widely used for bitrate adaptation in Dynamic Adaptive Streaming over HTTP (DASH). Essentially, the optimization problem is solved based on the prediction of buffer dynamics. However, stochastic chunk size deviates observably the buffer occupancy from the expected value, making the evolution hard to predict. In order to get rid of this effect and improve the prediction accuracy for buffer occupancy, we propose an algorithm based on markov decision process with incorporating chunk size information so that only the network capacity variation need to be considered in the decision-making process. Experiment results show that our solution can effectively eliminate performance oscillation induced by variable chunk size and achieve a good QoE.