Artificial intelligence - Based video traffic policing for next generation networks
参考中译:基于人工智能的下一代网络视频流量管制


          

刊名：Simulation Modelling Practice and Theory
作者：Khandu Om（Discipline of Information Technology, Media and Communications, Murdoch University）
Randeep Singh（Discipline of Information Technology, Media and Communications, Murdoch University）
Snehdeep（Discipline of Information Technology, Media and Communications, Murdoch University）
Amandeep Kaur（Discipline of Information Technology, Media and Communications, Murdoch University）
Deepika（Discipline of Information Technology, Media and Communications, Murdoch University）
Anureet Kaur（Discipline of Information Technology, Media and Communications, Murdoch University）
Tanya McGill（Discipline of Information Technology, Media and Communications, Murdoch University）
Michael Dixon（Discipline of Information Technology, Media and Communications, Murdoch University）
Kok Wai Wong（Discipline of Information Technology, Media and Communications, Murdoch University）
Polychronis Koutsakis（Discipline of Information Technology, Media and Communications, Murdoch University）
刊号：738LB025
ISSN：1569-190X
出版年：2022
年卷期：2022, vol.121
页码：102650-1--102650-13
总页数：13
分类号：TP34
关键词：Video traffic；Traffic policing；Artificial intelligence；Neural networks；Performance evaluation；H.264；H.265
参考中译：视频流量；流量管制；人工智能；神经网络；性能评估；H.264；H.265
语种：eng
文摘：The constant increase in users' bandwidth needs, through a large variety of multimedia applications, creates the need for highly effective network traffic control. This need is imperative in wireless networks, where the available bandwidth is limited, but is very important for wired networks as well. In this work we focus on the problem of policing video traffic from sources encoded with H.264 and H.265, given that these are the major state-of-the-art standards currently in the market. Building on work that has shown that classic traffic policing schemes can lead to unnecessarily strict policing for conforming video sources, we propose the use of Artificial Intelligence (AI) - based traffic policing schemes for video traffic. We conduct a performance evaluation of several AI - based schemes with the classic token bucket and we show that our proposed Frame Size Predictor and Policer scheme improve the performance of the classic token bucket by around 90% for conforming users, while providing only slightly worse policing results for non-conforming users.
参考中译：通过各种多媒体应用，用户带宽需求的不断增加，产生了对高效网络流量控制的需求。这一需求在可用带宽有限的无线网络中势在必行，但对于有线网络也非常重要。在这项工作中，鉴于H.264和H.265是目前市场上最先进的主要标准，我们将重点关注来自H.264和H.265编码源的视频流量的监管问题。基于经典流量管制方案可能导致对符合视频源的不必要的严格管制的工作，我们建议使用基于人工智能(AI)的视频流量管制方案。我们使用经典令牌桶对几种基于人工智能的方案进行了性能评估，结果表明，对于符合条件的用户，我们提出的帧大小预测器和策略器方案将传统令牌桶的性能提高了约90%，而对于不符合令牌桶的用户，仅提供了略差的监管结果。



国家科技图书文献中心  全球文献资源网  京ICP备05055788号-26  京公网安备11010202008970号  机械工业信息研究院 2018-2024