首页> 外文会议>IEEE Globecom Workshops >Case for caching and Model Predictive Control quality decision algorithm for HTTP Adaptive Streaming: is cache-awareness actually needed?
【24h】

Case for caching and Model Predictive Control quality decision algorithm for HTTP Adaptive Streaming: is cache-awareness actually needed?

机译:用于缓存和模型预测控制质量决策算法的缓存和模型预测控制质量决策算法:实际需要缓存意识吗?

获取原文

摘要

Presence of in-network opportunistic cache is known to cause undesirable effects on Quality of Experience when using HTTP Adaptive Streaming (HAS). While these effects on rate-based and buffer-based HAS algorithms have been studied, the recent near-optimal Model Predictive Control (MPC) has not yet been considered. We evaluate the impact of cache presence on MPC and show that caches may cause instabilities in common set-ups. To tackle this issue, we consider an idealized cache-aware extension to MPC and discuss its implementation. Our simulations show that overall cacheunaware MPC benefits from in-network caching with only video quality instability being increased, while cache-awareness brings noticeable improvement in this regard.
机译:已知网络的存在会对使用HTTP自适应流(具有)时对经验质量产生不希望的影响。虽然已经研究了这些对基于速率和缓冲的基于缓冲的算法,但尚未考虑最近近最佳的模型预测控制(MPC)。我们评估缓存在MPC上的影响并显示缓存可能导致常见设置中的不稳定性。为了解决这个问题,我们将理想化的缓存感知扩展视为MPC并讨论其实现。我们的模拟表明,整体Cacheunaware MPC从网络中缓存只有视频质量不稳定增加,而缓存意识会在这方面带来明显的改进。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号