个人云存储体验质量测量工具的设计与实现

随着用户日益增长的网络存储需求,涌现出了大量个人云存储（PCS）服务平台。个人云存储终端用户使用过程中体验质量（QoE）的测量是终端用户和服务提供商所共同关注的问题。通过从控制流与数据流之间的不同特性方面分析了影响个人云存储体验质量的因素,从终端用户的角度提出了能合理评估个人云存储体验质量的指标,设计了精确测量体验质量评估指标的方法。利用被动测量技术,实现了一个面向终端用户的个人云存储服务体验质量测量工具,同时给出了工具实现中的进程抓包、网络流分类等问题的解决方案。实验结果表明,测量工具运行健壮,测量数据准确,可以用于从用户终端测量个人云存储服务QoE。     

Effect of the FDT transmission frequency for an optimum content delivery using the FLUTE protocol

File Delivery over Unidirectional Transport (FLUTE) is the standard protocol used in unidirectional environments to provide reliability in the transmission of multimedia files. The key element of this protocol is the use of the File Delivery Table (FDT), which is the in-band mechanism used by FLUTE to inform clients about the files (and their characteristics) transmitted within a FLUTE session. Clients need to receive the FDT in order to start downloading files. Thus, the delivery of FDT packets and the proper configuration of their parameters have a great impact on the Quality of Experience perceived by the users of FLUTE content download services. This paper presents a complete analysis about how the FDT transmission frequency affects the download time of files. Moreover, results show which are the optimum values that minimize this download time. An appropriate configuration of the FDT transmission frequency as well as the use of AL-FEC mechanisms provides an optimum content delivery using the FLUTE protocol.     

基于QoE的LTE多业务资源分配算法

高效地利用无线频谱资源和保证用户体验质量是未来无线网络的主要目标。基于此,提出一种基于QoE的LTE多业务资源分配算法。在考虑信道信息、QoS要求及公平性的基础上,引入QoE来计算的用户优先级。特别的,引入最小QoE约束来保证RT用户QoE要求;提出一种次优资源块(Resource Block,RB)分配算法来解决复杂的资源分配优化问题,该算法主要分为两步:保证RT用户最小QoE要求;最大化系统加权和速率。仿真结果表明,相较现有的RT/NRT资源分配算法,该算法在用户分组丢失率、平均QoE和小区频谱效率方面性能都有所提升。     

Satisfiability and trustworthiness of acquaintances in peer-to-peer overlay networks

Various types of applications access to objects distributed in peer-to-peer (P2P) overlay networks. Even if the locations of target objects are detected by some algorithms like flooding and distributed hash table (DHT) ones, applications cannot manipulate the target objects without access requests. It is critical to discover which peer can manipulate an object in which method, i.e. only a peer with an access right is allowed to manipulate an object. Hence, the application rather has to find target peers which can manipulate a target object than detecting the location of a target object. Due to the scalability and variety of peers, it is difficult, possibly impossible to maintain a centralized directory showing in which peer each object is distributed. An acquaintance peer of a peer p is a peer whose service the peer p knows and with which the peer p can directly communicate. We discuss types of acquaintance relations of peers with respect to what objects each peer holds, is allowed to manipulate, and can grant access rights on. Acquaintance peers of a peer may notify the peer of different information on target peers due to communication and propagation delay. Here, it is critical to discuss how much a peer trusts each acquaintance peer. We first define the satisfiability, i.e. how much a peer is satisfied by issuing an access request to another peer. For example, if a peer locally manipulates a target object o and sends a response, a peer p i is mostly satisfied. On the other hand, if has to ask another peer to manipulate the object o, p _i is less satisfied. We define the trustworthiness of an acquaintance peer of a peer from the satisfiability and the ranking factor.

基于QoE感知的中继卫星带宽资源分配方法研究

为改善数据中继卫星的带宽分配对负载传输效率的影响;提出了一种基于用户体验质量QoE感知的中继卫星带宽资源分配方法。考虑到空间信息网络高动态链路情况下传输的可靠性;建立基于多个静止同步轨道卫星协同接入模型;研究了低轨道用户卫星进行多路数据上传的优势特点。通过设置链路效能函数;其将用户QoE满意度量化为链路反馈和链路成本;并用库恩塔克方法求解;实现最大化系统效能和带宽公平分配。研究结果表明;与Load-Balancing和Best-SNR-First方法相比;该方法不仅保证了用户QoE满意度;还提升了网络的接入性能。     

基于缓存补偿的视频码率自适应算法

针对基于超文本传输协议（HTTP）的动态自适应流（DASH）码率自适应算法未能充分利用视频缓存以及平均码率偏低的问题,提出一种DASH标准的基于缓存补偿的码率自适应切换（BASBC）算法。首先,根据最近下载分片的下载速率分析带宽波动程度并得到预估带宽;其次,依据预估带宽和当前码率等级在缓存区设置码率上切阈值和码率下切阈值,并利用动态上切阈值控制码率向上切换,消耗缓存时长,而利用动态下切阈值控制码率向下逐级切换,累积缓存时长,从而在缓存区形成累积-消耗的缓存状态循环。BASBC算法在视频播放平均码率上高于动态自适应的HTTP流码率渐进切换（DASBS）算法,有效提高了带宽利用率;虽然所提算法的平均码率稍低于基于DASH标准的码率平滑切换（RSS）算法,但所提算法的码率切换更为平滑,整体切换稳定性表现更优。实验结果表明,所提算法在动态网络环境中具有高带宽利用、切换平滑且稳定的良好表现,能够有效提高用户的体验质量（QoE）。     

基于搜索式地址队列的漏斗形ATM交换

为了适应多媒体通信从实验室走向社会的需要,网络传输速度越来越快,交换机也必须以更快的速度、更大的规模进行交换。然而由于当前微电子技术水平的限制,ATM交换中缓冲器的访问速度成为主要的瓶颈。为了在现有的技术条件下实现高性能的交换,文章提出了一种称为“漏斗形多缓冲的ATM交换结构”。并行处理技术在该结构中得到充分的体现:(1)通过把多个较小规模的交换单元(NxM)平行放置,实现较大规模的交换系统(NxN);(2)将单一缓冲结构变为多缓冲结构,使在一信元周期内由一个缓冲器完成多次读/写操作变为由多个缓冲器来分担,从而使每个缓冲器的访问速度大大降低。在缓冲器控制方面,该交换系统采用了基于搜索式的地址队列,它具有在满足所需的服务质量的前提下,易于实现诸如多点广播和基于优先级服务等高级功能。     

基于双向强化学习与动态码率调节的无线mesh网络协议

针对现有无线mesh网络协议的用户体验质量(QoE)较差的问题,提出一种基于双向强化学习与动态码率调节的无线mesh网络协议。首先,设计了兼容不同服务类型的无线mesh网络QoE度量框架;然后,设计了基于双向强化学习的无线mesh网络路由协议;最终,结合QoE感知的差异化报文调度策略与数据流源节点码率动态调节算法进一步优化终端用户的QoE质量。基于NS-2仿真平台的对比实验结果显示,本协议可明显地提高无线mesh网络的QoE指标,同时具有较低的控制开销。     

Architecture and Performance Evaluation for Redundant Multicast Transmission Supporting Adaptive QoS

In this paper we describe the architecture of an application that was developed for the transmission of multimedia data, using the multicast mechanism, over the Internet. There are two major issues that have to be considered when designing and implementing such a service, the fairness and the adaptation schemes. The fairness problem results from the fact that Clients with different capabilities have to be served. In our application we use a mechanism that categorizes the Clients into a number of groups according to each Client's capabilities and (the mechanism) serves each group of Clients with a different multicast stream. With the term capabilities we do not only mean the processing power of the Client, but also the capacity and the condition of the network path towards that Client. Because of today's Internet heterogeneity and the lack of Quality of Service (QoS) support, the Server cannot assume that the Clients will permanently be able to handle a specific bit rate. We have therefore implemented an additional mechanism for the intra-stream bit rate adaptation. The proposed mechanism uses a friendly to the network users congestion control policy to control the transmission of the data. We evaluate the adaptive multicast transmission mechanism through a number of experiments and a number of simulations in order to examine its behaviour to a heterogeneous group of Clients and its behaviour against TCP and UDP data streams.     

基于DASH标准的码率平滑切换算法

针对现有的基于超文本传输协议的动态自适应流(DASH)码率自适应算法在无线网络环境中码率切换频繁以及平均码率偏低的问题,提出一种基于DASH标准的码率平滑切换(RSS)算法。首先,算法的带宽检测机制利用滑动窗口对历史下载速率进行取样以计算带宽偏移系数,根据带宽偏移系数的大小初步判断带宽的波动情况,并对波动较大的情况进一步确定是否存在一致性变化趋势,从而区分出带宽的持续变化和短暂抖动,同时计算出相应情况下的带宽预测值;其次,算法的码率决策模型综合考虑带宽波动情况、缓存占用和变化情况及带宽预测值等,并且分别采取快速缓冲(FB)、缓慢切换(SS)、快速上升(FR)、约束下降(LD)、稳定保持(SH)策略和休眠机制对码率选择过程进行动态控制。实验结果表明,与基于模糊逻辑的码率自适应算法以及吞吐量调节驱动的码率自适应算法相比,该算法在播放开始时能够在最短时间内将视频码率提升到最佳水平,提高视频播放过程中的平均码率,在播放过程中带宽骤变和交替性频繁波动情况下都能够很好地维持视频码率的稳定,将切换次数降到最低,从而获得良好的无线端视频体验质量。     

How to charge for network services – flat-rate or usage-based?

Currently, the Internet service provider market offers two different types of pricing plans. In the USA, the predominant pricing plan is a flat-rate plan. In Europe and Asia, the predominant one is a per-minute pricing plan. Enrolled in such a pricing plan, users have to pay for the connect time to the Internet. Although Internet Service Providers (ISPs) have competed heavily for users in these last few years, they only have focused on trying to offer the lowest price within such pricing plans. A potentially more profitable and sustainable method of doing business would be for ISPs to differentiate themselves by offering more customized pricing plans for certain user groups. An important question then is whether a pricing plan exists that is attractive to users, but also allows ISPs to build a sustainable business. Based on empirical results of the INternet Demand EXperiment (INDEX) project, we discuss a pricing plan for Internet access that appears to be appreciated by Internet users as well as by ISPs. This pricing plan combines the advantages of flat-rate pricing and usage-based pricing. Users will benefit by receiving unlimited access to a basic service with the choice of higher quality of service (QoS) whenever they demand. From the ISPs' perspective, such a pricing plan will help any ISP to focus on certain user groups and to reduce peak network load.     

基于博弈论的多媒体传感器网络MAC协议

IEEE802.1 le媒体接入控制(MAC)协议不能较好地满足无线多媒体传感器网络不同类型业务节点间的公平性要求.为解决该问题,提出一种基于博弈论的无线多媒体传感器网络MAC协议.将节点间的信道竞争过程建模为非完全信息动态博弈,在不同的负载情况下,通过改变普通业务的权重提高不同业务间的公平性.仿真结果表明,该协议能在保证多媒体业务服务质量的同时,增加普通业务数据流接入信道的机率,提高整个网络的平均吞吐量.     

云存储内容分发网络中的能耗优化方法

针对云存储内容分发网络(CCDN)中的高能耗问题,研究CCDN的能耗优化管理方法。首先,分析CCDN运行原理,给出每台云服务器和每条网络链路的能耗计算公式,利用加权图刻画整个网络系统;然后,基于加权图,给出满足CCDN系统服务质量(QoS)和网络系统数据分发的能耗优化图(MEG)算法。通过模拟实验将该算法与贪心站点(GS)算法和优化静态放置和路由(OSPR)算法进行比较,结果显示:在系统可扩展实验中,MEG 能耗比GS和OSPR能耗分别少6.6%和30%;在保证用户QoS的实验中,MEG能耗比GS和OSPR能耗分别少28.9%和60.2%;在网络拓扑密度实验中,MEG的能耗比GS和OSPR能耗分别少32.2%和89.3%。实验结果表明,所提算法能够大幅度降低CCDN的能耗开销。     

基于网络流量预测的DASH系统优化

近年来基于超文本传输协议(HTTP)的自适应视频流量大幅上升,传统HTTP动态自适应流(DASH)速率算法无法准确预测网络吞吐量,导致网络带宽波动,使传输控制协议慢启动并触发抛弃规则,从而降低视频质量.提出一种基于网络流量预测的改进DASH速率算法.将DASH算法分为视频质量选择阶段、视频下载阶段和请求等待阶段,在视频...     

基于CAPWAP协议的WLAN集中管理系统的研究与实现

针对大规模部署无线局域网（WLAN）存在的维护困难,成本高等问题,就应用于接入控制器(AC)和无线终端（WTP）间通信交互的CAPWAP协议进行了研究与实现。在Linux系统下实现了CAPWAP协议主要功能,如状态机管理、WTP集中配置等;搭建了本地转发架构下的WLAN集中管理系统的实现平台,并采用了Wireshark抓包工具,Chariot和Iperf软件进行测试。抓包结果验证了该架构的可行性,吞吐量和用户数据协议(UDP)测试结果表明网络性能高效稳定。     

基于指标相关性的网络运维质量评估模型

传统网络运维评估方法存在两方面的问题：一是在指标选取、权重指定等关键步骤过于依赖领域专家经验,难以得到精确全面的评估结果;二是通信设备用户数量不断增加带来了海量的数据,数据又来自多个厂家以及多种设备,传统方法处理此类海量异构数据的效率较低。为了解决这些问题,提出基于指标间互相关性的指标选取方法。该方法着眼于评估过程中指标选取步骤,通过比较指标数据序列间的相关性强弱,对原始指标集进行分类,在各个簇中选择代表性指标完成关键指标体系的构建;另外,结合无人工参与的数据处理方法、权重确定方法建立了网络运维质量评估模型。在实验中,所提方法选取的指标对人工指标的覆盖率为72.2%,并且比人工指标的信息重叠率少31%。所提方法能够有效减少人力参与,且评估结果对告警有较好的预测准确率。     

Predictable service overlay networks: Predictability through adaptive monitoring and efficient overlay construction and management

Providing bounded communication among participating nodes is significant for distributed systems. Internet-based applications suffer with lower performance due to absence of bounded latency. We describe PSON, an overlay network solution to this challenging problem. PSON has two components. The monitoring component, SyncProbe, utilizes efficient and adaptive monitoring techniques to measure latency, detect packet loss, and provide real-time estimates of maximum expected latency along paths of an Internet substrate. The QoSMap component constructs and manages overlay such that it yields application-level QoS and provides resilience against network failures. A distinctive feature of QoSMap is construction of QoS-compliant backup paths which facilitate in overlay management and operation during the period when primary overlay paths violate QoS. We evaluate PSON on PlanetLab to provide predictable communication for applications with different topology and QoS requirement. Our experiments confirm the effectiveness of PSON in providing an inexpensive and efficient application-layer solution to Internet’s unpredictable behavior.