一个提供Overlay QOS的端到端接纳控制系统

叠置网络也必须与IP一样,为其扩展业务提供QOS支持。论文提出了一个提供OverlayQOS的端到端接纳控制系统———EAC接纳控制系统,并从叠置网的概念、叠置QOS节点的形成、EAC接纳控制技术、系统架构、模型实现和模拟性能评价等角度出发,对EAC接纳控制系统进行了较为全面的分析和阐述。     

无线传感器网络中一种分布式安全存储方案

对无线传感器网络的数据存储进行分析和研究,提出了一种以数据为中心的无线传感器网络中的分布式数据存储方案.该方案可有效解决集中式数据存储方案造成的中心节点的高负荷瓶颈问题,同时也避免了由于中心节点失效导致的数据丢失或泄漏问题.相对于现有的分布式数据存储方案,该方案运用Reed Solomon Code对数据进行加密,并且...     

基于OSGi的分布式系统集中日志管理方案

目前分布式业务应用的日志多存储在各分布式服务器节点本地日志文件中,没有集中存储和管理,导致业务系统问题定位速度慢,解决问题效率低.本文提供一种基于OSGi的分布式日志收集与分析技术方案.该方案单独设计了集中的日志存储服务器用于存储日志,并提供一套通用日志模型,业务应用分布式节点向该设备发送基于该模型的日志数据,日志存储服务器接收到各节点的日志数据后进行统一存储和界面化分析展示,帮助开发人员快速定位和分析问题.该方案以OSGi插件形式部署到应用系统,应用卸载该插件后则以原有方式存储日志.应用结果表明,采用该日志管理方案对1000并发下记录日志的业务应用访问性能平均提升2秒,并且没有日志数据丢失.开发人员反馈,错误日志更加一目了然,定位问题的时间明显短于普通的日志存储方式.     

大规模流媒体直播系统扰动性研究*

在基于P2P技术的大规模流媒体直播系统中,节点频繁地加入和退出,形成扰动问题,严重影响了系统设计和整体性能。通过分析对等网络节点会话时间概率分布理论,在充分利用会话时间长的节点基础上,提出了抗扰动节点选择机制来增强系统稳定性。通过对比实验证明,该方案降低了扰动问题对流媒体直播系统的影响。     

网络存储性能改进的文件系统实现方法

在多个存储节点构成的集群存储系统中，结合应用提高网络存储性能的目标就是利用文件系统方案来实现的．本文在相关研究的基础上重新讨论改进网络存储性能的文件系统方案．这个方案同时利用网络分布文件系统和网络分带文件系统的优点，采用非分带和分带文件数据分布混合应用．我们讨论了对应该方案的不同两级存储分配策略和相关参数的选择，并以HP97560性能参数为基础，进行理论分析．应用文件大小分布的对比以及模拟测试结果显示两级存储分配策略和相关参数选择的合理性．     

基于数据生命周期管理的ARP系统优化设计

随着管理信息化系统中业务数据量的日益增加,使得系统性能下降和物理磁盘空间的增长。本文介绍了一种数据生命周期管理解决方案ADLM(Academia Resource Planning System Data Lifecycle Manage,简称ADLM),在不增加硬件成本情况下,使用程序控制方法,达到系统性能优化和实现历史数据归档保存的目的。主要解决了具有时间周期特性的业务数据的分类管理、在线归档、离线存储等问题,对业务数据归档策略、分级存储实现和归档数据查询等关键问题进行了分析,最后通过实际应用,证明本技术方案可以方便快捷地实现业务处理性能的提升和对磁盘空间使用需求无限增长的有效控制。     

无线传感器网络密钥管理方案前向安全性研究

对现有的基于椭圆曲线的无线传感器网络密钥管理方案进行了分析研究,针对现有密钥管理算法不具备前向安全性的问题,以相对简单及较为经典的两个方案为基础,将前向安全的概念引入到密钥管理方案之中,实现了前向安全在椭圆曲线无线传感器网络密钥管理方案中的应用。在此基础上,应用硬件节点MICAz进行硬件模拟,分析了方案的安全性、存储消耗、运行时间,验证了方案的适用性。     

分簇无线传感器网络密钥预分配管理方案

针对无线传感器网络节点计算和存储能力有限,能量受限等特点,提出了一种新的分簇传感器网络密钥预分配管理方案KDNKPD。该方案借助于Blundo二元多项式函数和密钥分发节点建立节点与簇头间的安全通信,能够适应簇首节点的按轮选举并解决了Blundo方案的安全问题。通过安全分析与性能分析比较和仿真实验表明,该方案提高了网络的安全性,减少了传感器节点的存储开销和计算开销。     

基于分簇无线传感器网络密钥预分配管理方案研究

针对无线传感器网络节点计算和存储能力有限,能量受限等特点,提出了一种新的分簇传感器网络密钥预分配管理方案KDNKPD。该方案借助于Blundo二元多项式函数和密钥分发节点建立节点与簇头间的安全通信,能够适应簇首节点的按轮选举并解决了Blundo方案的安全问题。通过安全分析与性能分析比较和仿真实验表明,该方案提高了网络的安全性,减少了传感器节点的存储开销和计算开销。     

基于网络编码的P2P流媒体直播系统研究

针对目前存在的P2P流媒体直播系统不能充分利用网络资源的问题,提出了一种基于网络编码的P2P流媒体直播方案。该方案充分利用了Peer节点的计算能力,即在对媒体数据进行存储转发前先进行网络编码,以提高数据块的下载速率以及节省网络带宽资源。实验结果表明,在同等网络状况下,利用了网络编码后节点的播放质量有了明显的改善,尤其是在网络状况不好的情况下改善更为明显。     

Direct push–pull or assisted push–pull? Toward optimal video content delivery using shared storage-based cloud CDN (SS-CCDN)

Video content delivery networks face many challenges such as scalability, quality of service and flexibility. Video suppliers address them through CDN. Cloud computing and Video content Delivery as a Service (VDaaS) plays a key role in improving the content delivery standard and makes the work of content providers, easier. By hosting video contents in the cloud, the content delivery costs are minimized and the overall content delivery performance enhanced by optimization of cloud CDN. Cost optimization of the cloud-based content delivery network requires a focus on delay or throughput, the overall performance and content delivery. The content placement and content access, the QoS and the QoE in CDN can be improved by enhancing the video content delivery performance. In this paper, a unique model for video content delivery, cloud-based is developed, titled as shared storage-based cloud CDN (SS-CCDN) to achieve the objective. This design optimizes through algorithms, the effective placement of video data and dynamic update of video data. For analysis, GA, PSO, and ACO algorithms are used. The proposed model uses direct and assisted push–pull content delivery schemes for cost-efficient content delivery. The low-cost VDaaS model reduces the storage cost, keeps the latency and the traffic cost. Experimental results validate that this model, with regard to storage, traffic, and latency generate higher performance with lower price and satisfy the QoS and QoE aspects in content delivery.

     

用遗传算法解决有时延约束选播路由问题的综述

选播QoS路由问题是一个NP-完全问题,而解决此问题的一个有效方法就是遗传算法,本文针对delay,bandwidth,cost等QoS因子的约束,介绍了三种比较新的遗传算法,并提出了以后值得进一步研究的问题。     

Petri网与蚁群算法在CDN网络路由中的应用

CDN让用户以最快的速度从最近的地方获得所需的信息,它对QoS路由提出了更高的要求,单纯的采用蚁群算法或是依靠Petri网模型中变迁发生寻径的方法都不能较好的解决CDN路由问题。基于稳定的CDN网络构建图状拓扑结构,提出了一种将Petri网与蚁群算法相结合,考虑多个路由限制的优化QoS路由算法。实验仿真表明,该算法能有效地求解CDN网络中的路由问题。     

Exact algorithms for the joint object placement and request routing problem in content distribution networks

This paper describes two exact algorithms for the joint problem of object placement and request routing in a content distribution network (CDN). A CDN is a technology used to efficiently distribute electronic content throughout an existing Internet Protocol network. The problem consists of replicating content on the proxy servers and routing the requests for the content to a suitable proxy server in a CDN such that the total cost of distribution is minimized. An upper bound on end-to-end object transfer time is also taken into account. The problem is formulated as a nonlinear integer programming formulation which is linearized in three different ways. Two algorithms, one based on Benders decomposition and the other based on Lagrangean relaxation and decomposition, are described for the solution of the problem. Computational experiments are conducted by comparing the proposed linearizations and the two algorithms on randomly generated Internet topologies.     

Ant colony-based algorithm for constructing broadcasting tree with degree and delay constraints

Heterogeneous ISP router policies prevent multimedia QoS applications, such as real-time media streaming, video conferencing, and distance learning, that require IP layer multicasting from wide deployment on the Internet. Thus, recent efforts have applied application layer multicast to implement such applications by organizing the multicast group in an overlay (virtual), peer-to-peer network. Such a communication scheme can be regarded as a broadcasting problem with degree and delay constraints in the overlay network. The degree and delay-constrained broadcasting problem with minimum-cost appears to be NP-complete. This study proposes an ant colony-based algorithm to solve the difficult broadcasting problem and compares it with some related methods. The results of a series of simulations show the efficiency and effectiveness of the proposed algorithm.     

基于流媒体服务的IP网络内容分发系统的设计

IP网络中数据量巨大的流媒体内容使服务器和骨干网络承受的压力越来越大。内容分发系统对保证流媒体QoS起到至关重要的作用。该文通过分析内容分发网络(CDN)和P2P两种新型内容分发技术，提出了多源网状散列式P2P模型和一种改进的内容缓存算法，设计了基于CDN和P2P技术的内容分发系统。系统可同时满足请求多和请求少的情况，提高了流媒体QoS。     

Designing content distribution networks for optimal cost and performance

One strategy for alleviating excess latency (delay) in the Internet is the caching of web content at multiple locations. This reduces the number of hops necessary to reach the desired content. This strategy is used for web content such as html pages, images, streaming video, and Internet radio. The network of servers which store this content, and the collections of objects stored on each server, is called a content distribution network (CDN). In order to optimally design a CDN, given a network topology with available server storage capacity at various points in the network, one must decide which object collections to place on each server in order to achieve performance or cost objectives. The placements must be within the storage limits of the servers and must reflect the request patterns for each collection of objects to be cached. Researchers have suggested formulations for the CDN problem which address performance by minimizing latency (the average number of hops is a commonly accepted measure of latency) from client to content, or formulations that focus on minimizing cost of storage and/or bandwidth. In this research, we develop a model which allows for the simultaneous treatment of performance and cost, present examples to illustrate the application of the model and perform a detailed designed experiment to gain insights into cost/hops tradeoff for a variety of network parameters.     

基于移动Ad hoc网络的服务管理研究

本文基于移动Ad hoc网络的广播特性、分簇的普遍性等特点,在分析分布式服务发现协议GSD等的基础上,提出了新的服务发现机制,该机制考虑了各节点处理能力、存储能力以及所提供的服务种类等不可能完全相同的特性,克服了GSD同等对待所有节点的缺欠;另外,文中提出了基于优先级和两步资源预约的服务调度和QoS分配方式,依据服务所请求的QoS级别和资源情况来确定合适的端到端QoS级别,保证资源的充分利用,并给出了算法的一个实际应用的例子,该算法考虑了资源的抢占和两步方式的资源预约,比普通的确定QoS级别的算法具有更高的预约成功率,而比仅依据优先级的算法具有更高的资源利用率。     

混合内容分发网络及其性能分析模型

在大规模数字内容网络分发方面,占主导地位的CDN(Content Delivery Network)和P2P(Peer-to-Peer)网络具有显著互补优势.CDN网络可降低数据传输延迟,提高用户体验;P2P网络的部署成本低,可扩展性强.文章提出一种基于CDN和PZP技术的混合内容分发网络(Hybrid Content Distribution Network,HCDN),在骨干网部署CDN系统,在接入网构建P2P区域化网络,终端用户可同时通过CDN和P2P网络获取数据;阐述了HCDN网络模型及其内容分发处理流程,包括内容路由、副本放置和数据下载;给出了基于流模型的混合网络性能模型,并从节点数量变化、下载时间、服务能力和传输开销等方面进行综合性能评价.实验结果表明,HCDN能提高下载速率、降低服务器负载以及减小骨干网传输流量,既可克服CDN网络部署成本高的缺点,也可避免P2P网络在节点数量稀缺时的低性能.     

Designing cost-effective content distribution networks

In this paper, we present a novel technique for the problem of designing a Content Distribution Network (CDN), which is a technology used to efficiently distribute electronic content throughout an existing IP network. Our design proposal consists of jointly deciding on (i) the number and placement of proxy servers on a given set of potential nodes, (ii) replicating content on the proxy servers, and (iii) routing the requests for the content to a suitable proxy server such that the total cost of distribution is minimized. We model the problem using a nonlinear integer programming formulation. The novelty of the proposed formulation lies in simultaneously addressing three interdependent problems in this context as well as explicitly representing the distribution structure of a CDN through the objective function. We offer a linearization for the model, develop an exact solution procedure based on Benders’ decomposition and also utilize a variant of this procedure to accelerate the algorithm. In addition, we provide a fast and efficient heuristic that can be used to obtain near-optimal solutions to the problem. Finally, the paper concludes with computational results showing the performance of the decomposition procedure and the heuristic algorithm on randomly generated Internet topologies.