IP网络中视频流QoE评价模型

网络视频业务的兴起使网络运营商和服务提供商更加关注视频的用户体验（QoE）,然而视频用户体验（QoE）值由于其主观性且评价过程复杂,难以在视频流传输中实时获取。通过实验分析了视频传输过程中服务质量（QoS）参数变化对视频QoE的影响,建立了客观、可测量的QoS参数与视频QoE之间映射模型,用可量化的QoS参数来评定视频QoE受网络性能的影响程度,以评估网络视频质量,该模型形式简单,能够实时监测视频质量。实验结果表明,该模型的评价结果能较好反映视频QoE。     

服务功能链中基于机器学习的QoE评估与预测

在软件定义网络与网络功能虚拟化协同的网络架构下,只考虑单个服务质量（QoS）指标的服务功能链部署无法满足用户的多业务体验需求。提出一种基于机器学习的服务功能链部署模型。基于层次分析法构造MPNQ2算法以建立QoS与体验质量（QoE）的映射关系,得出影响QoE的网络参数并评估其影响权重。在此基础上,利用具备较强综合学习和泛化能力的随机森林模型对服务功能链的QoE进行预测。实验结果表明,与梯度提升决策树、线性判别分析等机器学习模型相比,随机森林模型为预测QoE的最佳模型,同时在影响QoE的网络参数中,丢包率对服务功能链的部署影响最大。     

一种视频质量监测系统的设计与实现

网络服务提供商希望能从用户的角度了解目前网络所提供的服务质量,而用户也希望获得定量的指标来评价当前网络服务质量。为此,以视频质量监测为研究对象,提出一种面向用户体验质量的网络监测系统。通过实验分析了网络传输过程中QoS参数对视频QoE的影响;提出一种将视频流转化为测试序列的视频丢包测量方法,该方法能低入侵、准确测量视频传输过程中的丢包情况;基于以上的研究成果,通过对MIB库的扩展和对MIB库轮询机制的研究,构建了面向QoE的视频服务监测系统,该监测系统结构简单、可行性强,实验表明可实时对网络中的视频服务质量进行监测。     

移动视频业务QoE自适应测量工具

针对不同无线环境（3G、WiFi）下获取用户体验质量（Quality of Experience,QoE）数据困难和不精确的问题,提出一种基于安卓（Android）移动终端视频业务QoE的自适应测量方法.通过实时测量并评估用户在线视频业务体验质量,提高用户体验质量评价的准确性和实用性.为此开发了能自动测量视频QoE的工具,测量服务质量（Quality of Service,QoS）客观参数,通过效用函数映射到主观QoE（MOS值）.通过对理论QoE评价模型（取自文献）与用户实际反馈相关性研究改进理论模型.结果表明,无线环境下改进的模型测量结果更接近用户实际反馈,可以更好地评价QoE.     

移动流媒体用户QoE评估模型

HAS(HTTP Adaptive Streaming)能够实现流畅播放和视频质量的平衡,为用户提供更好的服务质量体验。大多数基于HAS的流媒体用户体验质量(Quality of Experience,QoE)模型考虑了当前系统或网络条件,但对用户所处环境的客观影响、用户心理因素的考虑较少。面向移动流媒体客户端的应用场景,从客观感知影响参数和心理效应影响参数两个方面来考虑移动端流媒体的QoE影响因素,设计用户QoE评估模型。提出移动设备抖动状态检测和用户观看位置检测方法,并将设备抖动状态、用户观看位置与流媒体服务质量相结合,再根据心理学系列位置效应来综合评估用户的质量体验情况。最后通过实验证明了所提的用户QoE模型能够提供准确有效且符合用户实际体验的QoE评估结果。     

非均衡IPTV数据集下的用户报障预测

针对传统算法在非均衡交互式网络电视(Internet protocol television,IPTV)数据集下用户报障预测效果不理想的问题,本文将影响网络服务质量(Quality of service,QoS)的传统网络参数和主观反映用户体验质量(Quality of experience,QoE)的MOS评分结合来预测用户是否报障。本文在已有的ODR-BSMOTE-SVM 算法基础上,针对过采样算法产生噪声以及核参数没有进行优化的缺陷,提出了一种改进型算法。该改进算法首先采用欠采样、过采样算法及数据清洗算法对原始非均衡数据进行处理,然后通过自适应变核参数寻找近似最优值,最终实现提升分类效果。实验结果表明,较传统标准支持向量机(Support vector machine, SVM)算法和ODR-BSMOTE-SVM 算法,本文算法能获得更佳的预测效果。     

MMS业务的QoE定义与测量

用户体验质量已成为移动通信中的一个热门话题,为了有效地测量多媒体短信业务（MMS）的用户体验质量,分析了QoE的定义以及它与传统QoS的区别,介绍了QoE的KQI和KPI之间的相互关系并建立起QoE的映射模型;然后,结合MMS业务的实现流程以及所涉及的网元设备详细定义了MMS业务中的KQIs与KPIs,最后,针对MMS业务提出了一种基于统计样本的QoE测量方案,通过测量明确KPIs与QoE之间的关系以及影响用户体验质量的因素,这对于提高用户的体验质量有重要意义。     

基于用户体验评价模型的最优路由选择算法

网络视音频业务的兴起使网络运营商和服务提供商更加关注视音频的用户体验（QoE）,而传统的路由算法只能保证所选路径的服务质量（QoS）参数,如延迟、抖动等满足QoS约束的需求,并不能直接反映QoE的信息,从而不能保证所选路径满足QoE需求。基于QoE评价模型,给出以QoE为目标的最优路由选择算法。通过分析QoE表征参数与传统QoS参数的关系,利用QoE表征参数可分解性和QoE表征值非递减性两个性质,给出多项式时间复杂度为O(V log V+E)的QoE_DSP算法。实验和分析表明,该算法能保证所得路径满足QoE需求,同时具有良好的计算扩展性。     

MMS业务的QoE定义与测量

用户体验质量已成为移动通信中的一个热门话题,为了有效地测量多媒体短信业务(MMS)的用户体验质量,分析了QoE的定义以及它与传统QoS的区别,介绍了QoE的KQI和KPI之间的相互关系并建立起QoE的映射模型;然后,结合MMS业务的实现流程以及所涉及的网元设备详细定义了MMS业务中的KQIs与KPIs,最后,针对MMS业务提出了一种基于统计样本的QoE测量方案,通过测量明确KPIs与QoE之间的关系以及影响用户体验质量的因素,这对于提高用户的体验质量有重要意义.     

基于QoS量化用户体验质量的评价模型

针对网络环境中业务供应商提供的业务不能很好的满足用户需求的问题,引入用户体验质量（QoE）并结合服务质量（QoS）参数,通过仿真网络得到相应数据,使用matlab工具分别建立用户体验质量与比特率、用户体验质量与丢包率的评价模型.运用统计分析方法对评价模型进行数据分析,并与史蒂文斯幂定律、韦伯-费希纳定律等模型进行对比验证.结果表明,构建的评价模型能更精确的体现用户体验质量与服务质量的关系,为供应商提供了重要的参考依据,并指明了服务方向.     

IPTV业务质量指标研究

随着电信多媒体业务的快速发展,交互式电视（IPTV）为代表的视讯业务已经越来越成为关注的焦点。文章首先简要概述了IPTV的几种常见的QoE业务质量指标,接着详细阐述了视频传输质量评估指标MDI,主要对其两个主要参数进行了较为详尽的分析,并且简单地分析了实际的IPTV网络测试时序失真以及对视频质量的影响。最后提出了如何更好的提高网络业务质量各项指标是一项值得研究的课题。     

QoE assessment model for multimedia streaming services using QoS parameters

This paper proposes a video QoE (Quality of Experience) assessment model which can assess video quality of experience with only QoS (Quality of Service) parameters and their relative importance at network layer. Since network or service providers can forecast whether to provide multimedia services above a certain level of service quality using the proposed model, they can offer and maintain optimum network environment for multimedia service such as IPTV. Through an experiment of video quality comparison we show that our QoS/QoE correlation model is closely related with video quality degradation patterns to network environmental change.     

Zebroid: using IPTV data to support STB-assisted VoD content delivery

IPTV, unlike Internet TV, delivers digital TV and multimedia services over IP-based networks with the required level of quality of service (QoS) and quality of experience (QoE). Linear programming channels in IPTV are delivered through multicast, which is highly scalable with the number of subscribers. Video-on-demand (VoD) content, on the other hand, is typically delivered using unicast, which places a heavy load on the VoD servers and all the network components leading to the end-user set-top boxes (STBs) as the demand increases. With the rapid growth of IPTV subscribers and the shift in video viewing habits, the need to efficiently disseminate large volumes of VoD content has prompted IPTV service providers to consider the use of STBs to assist in video content delivery. This paper describes our current research work on Zebroid, a potential VoD solution for fiber-to-the-node (FTTN) networks, which uses IPTV data on a recurring basis to determine how to select, stripe, and preposition popular content in selected STBs during idle hours. A STB requesting VoD content during the peak hours can then receive necessary stripes from participating STBs in the neighborhood. Recent VoD request access patterns, STB availability data, and capacity data on network components are taken into consideration in determining the parameters used in the striping algorithm of Zebroid. We show both by simulation and emulation on a realistic IPTV testbed that the VoD server load can be reduced by more than 70% during peak hours by allocating only 8 GB of storage on each STB. The savings achieved through Zebroid would also allow IPTV service providers to add more linear programming channels without expensive infrastructure upgrades.     

基于MPQM模型的IPTV视频质量实时评估算法

针对实时测量和评估IPTV视频质量的迫切需求以及当前主要商用测量方案的不足,通过分析影响IPTV视频质量的主要因素,提出以MPQM模型为评估基础,综合运用Markov模型分别为网络信息包丢失概率、图像复杂程度以及视频流传输位速率进行建模和评测的实时评估算法,并依据所建模型推导出相关估算公式。商用测试结果表明该算法能够在实时环境中较准确地评估IPTV视频质量。     

Modeling and evaluating IPTV applications in WiMAX networks

Internet Protocol-based Television (IPTV) is a digital television service which delivers television content via an IP network. The rapid growth of wireless network technology in recent years has changed, the way people access the Internet. Adding mobility to IPTV can create a truly compelling ubiquitous service which spans different network domains and varied IP-enabled terminals and devices, such as set-top boxes, PCs and cell phones. However, extending IPTV service to wireless networks requires overcoming bandwidth bottlenecks and high packet loss rates. Following the IEEE 802.16 standard, worldwide interoperability for microwave access (WiMAX) features high data rates and large service coverage, offering a wireless broadband solution for IPTV services. While previous research has focused on creating a broadband IPTV service few studies have practically evaluated IPTV applications in a wireless broadband network environment. In this paper, we model and evaluate a common constant bit rate (CBR)¹ based IPTV application and an IPTV live streaming (PPStreaming)² application while retrieving IPTV content via a WiMAX network. We also use the NS2 simulation tool to evaluate the performance of these two IPTV applications. The evaluation metrics include latency, packet loss, data rate and throughput statistics when the two IPTV applications are run in the WiMAX network. ¹The simplest IPTV solution is to convey video content by CBR. IPTV operators and content delivery networks relay CBR streaming content to control the demand for network capacity. Broadcasters prefer CBR video as it conserves bandwidth resources, but CBR delivery can degrade video quality result in higher overall demand on network capacity. ²PPStreaming (also referred to as P2P streaming Internet TV) is a network for live media streaming. In principle it’s similar to BitTorrent (BT) in that it provides stable and smooth broadcast of TV programs to broadband users. Unlike traditional streaming media, PPStreaming adopts P2P-streaming technology and supports full-scale visits with tens of thousands of simultaneous users. Its client software can be used in the browser or as a standalone executable.