Quality of Experience Experimentation Prediction Framework through Programmable Network Management
Quality of Experience Experimentation Prediction Framework through Programmable Network Management
复制标题
DOI：
10.3390/network2040030
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Ahmed Osama Basil Al-Mashhadani;Mu Mu-Mu;Ali Al-Sharbaz
中科院分区：
文献类型：
--
作者：
Ahmed Osama Basil Al-Mashhadani;Mu Mu-Mu;Ali Al-Sharbaz
体验质量 (QoE) 指标可用于评估用户对通过互联网交付的数据服务应用程序的感知和满意度。端到端指标的形成是因为 QoE 取决于用户的感知和所使用的服务。传统上，网络优化侧重于提高服务质量 (QoS) 等网络属性。在本文中，我们研究了软件定义网络环境中的自适应流。我们的目的是评估和研究媒体流、影响流的方面以及网络。这样做的目的是最终达到分析网络特征及其与感知 QoE 的直接关系的阶段。然后，我们使用机器学习根据主观用户实验构建预测模型。这将有助于消除未来的物理实验并自动化预测 QoE 的过程。
Quality of experience (QoE) metrics can be used to assess user perception and satisfaction in data services applications delivered over the Internet. End-to-end metrics are formed because QoE is dependent on both the users’ perception and the service used. Traditionally, network optimization has focused on improving network properties such as the quality of service (QoS). In this paper we examine adaptive streaming over a software-defined network environment. We aimed to evaluate and study the media streams, aspects affecting the stream, and the network. This was undertaken to eventually reach a stage of analysing the network’s features and their direct relationship with the perceived QoE. We then use machine learning to build a prediction model based on subjective user experiments. This will help to eliminate future physical experiments and automate the process of predicting QoE.