On peer-to-peer (P2P) content delivery

In both academia and industry, peer-to-peer (P2P) applications have attracted great attentions. P2P applications such as Napster, Gnutella, FastTrack, BitTorrent, Skype and PPLive, have witnessed tremendous success among the end users. Unlike a client-server based system, peers bring with them serving capacity. Therefore, as the demand of a P2P system grows, the capacity of the network grows, too. This enables a P2P application to be cheap to build and superb in scalability. In this paper, we survey the state of the art of the research and the development of P2P content delivery application. Using examples of the deployed P2P applications and research prototypes, we survey the best practices in P2P overlay building and P2P scheduling. We hope that the information may help the readers to build a reliable, robust P2P content delivery application.

Query-driven indexing for scalable peer-to-peer text retrieval

In this paper, we present a query-driven indexing/retrieval strategy for efficient full text retrieval from large document collections distributed within a structured P2P network. Our indexing strategy is based on two important properties: (1) the generated distributed index stores posting lists for carefully chosen indexing term combinations that are frequently present in user queries, and (2) the posting lists containing too many document references are truncated to a bounded number of their top-ranked elements. These two properties guarantee acceptable latency and bandwidth requirements, essentially because the number of indexing term combinations remains scalable and the posting lists transmitted during retrieval never exceed a constant size. A novel index update mechanism efficiently handles adding of new documents to the document collection. Thus, the generated distributed index corresponds to a constantly evolving query-driven indexing structure that efficiently follows current information needs of the users and changes in the document collection.We show that the size of the index and the generated indexing/retrieval traffic remains manageable even for Web-size document collections at the price of a marginal loss in precision for rare queries. Our theoretical analysis and experimental results provide convincing evidence about the feasibility of the query-driven indexing strategy for large scale P2P text retrieval.     

对等网联下NAT穿越问题的研究

采用"打洞"穿越锥型NAT与使用端口预测穿越对称型NAT相结合的方法,成功穿越了各种NAT,解决了对等联网下NAT的穿越问题。该方案既无需改变现有网络设备,又能确保内网的安全性,同时还解决了目前穿越方式存在的只能穿越部分类型的NAT、丢包、延时的问题。     

Improving robustness of P2P applications in mobile environments

Mobile P2P networks possess particular characteristics which make accessibility of services deployed on peers a challenge. This has to be taken into account when considering robustness of applications that depend on successfully accessing a set of services. While ensuring robustness is traditionally handled through replication or redundancy, those solutions are not readily applicable to decentralized and dynamic networks. Instead, current solutions are based on efficient P2P structure maintenance or unstructured network search algorithms. A novel and alternative method proposed in this paper is based on the observation that some redundancy may exist between services offered on the network, a fact which could be used to recreate an unavailable service from services accessible to a peer. Instead of adding redundancy to the system, our solution exploits the already existing redundancy to improve robustness of mobile P2P applications. We model the interaction with services as finite-state transducers and propose a heuristic to obtain redundancy between any pair of services. Then, a set of algorithms that uses this inter-service redundancy to recreate the interaction with one service from the other is discussed. The computational cost is polynomial with respect to services’ size, and in practice, the non-redundant functionality and related control need to be implemented locally.

A novel DRM framework for peer-to-peer music content delivery

Due to rapid advances in the network communications field in recent years, the distribution of large-scale music contents has become easier and more efficient than ever before. However, the unauthorized distribution of copyright-protected content has emerged as a major concern. Accordingly, this paper presents a content distribution framework with a DRM capability for P2P networks. The robustness of the content distribution is ensured by using a network coding approach based on the Lagrange polynomial interpolation method. When the downloading peer within the network receives sufficient coded pieces, it not only reconstructs the associated blocks using a finite field Gaussian elimination method, but also creates its own copies of the coded pieces within these blocks and shares these copies amongst the other peers in the network. As a result, the distribution overhead imposed on the music provider is substantially reduced and the number of coded pieces within the network is significantly increased, thereby overcoming the “last piece problem” inherent in existing P2P schemes. In the DRM module of the framework, the RSA public-key cryptosystem is used to generate a unique digital fingerprint for every user within the network. The fingerprint is embedded within the music file in a protected form such that the music provider can establish the identification of any user performing an unauthorized distribution of the file. The experimental results confirm that the proposed framework provides an efficient and secure means of distributing large-scale copyright-protected music contents with no discernible degradation in the audio quality.     

基于CDN和P2P技术的流媒体系统设计

分析基于CDN和P2P技术的流媒体系统设计方案,指出它们的优缺点,给出了一种结合CDN和P2P技术的流媒体系统设计方案,提出了CDN内容路由的负载均衡算法,对P2P技术在CDN网络中的应用进行了研究,提出一种应用于CDN边缘节点P2P网络的拓扑结构并给出了节点失效恢复策略.     

移动P2P网络超级节点选取机制研究

针对半分布式结构的移动P2P网络超级节点选取问题,提出一种新颖的超级节点选取机制,全面分析影响超级节点选取的各种因素,按着其特点和类型不同将其分为效益型属性和成本型属性,并在此基础上建立了超级节点选取的带约束多目标优化模型.采用新的约束处理方法,利用免疫克隆算法对超级节点选取问题进行求解.实验结果表明,该机制可以有效降低超级节点的失效率,提高系统查询效率,算法收敛速度快,有较好的可扩展性.     

Demaq/Transscale: Automated distribution and scalability for declarative applications

The goal of the Demaq/TransScale system is to automate the distribution of applications to multiple hosts. Today, in order to create highly scalable architectures, developers have to manually restructure the application logic, creating balanced application fragments and data partitions to distribute across the available host machines. Our approach automates much of this manual work. We show how a novel, messaging-based programming model allows to implement distribution as a source-level transformation that turns a non-distributed application specification into a set of programs that can be executed on the various machines of a cluster. The challenge is the identification of application fragments that can be executed independently of each other, such that each fragment can be executed using only local transactions. Further, our method allows developers to increase scalability (i.e. the number of possible fragments) by choosing from a library of automatically applicable rewrites. As a running example, and for the reported experimental results, we use TPC-App as a benchmark application.     

高性能可伸缩Web应用系统编程策略

性能和伸缩性是Web应用系统两个重要的质量属性,两者从不同方面反映了Web应用系统为客户提供响应时间的能力.创建高性能可伸缩的Web应用系统,以有效地减少系统更新换代的次数,满足企业不断增长的客户规模,并最大限度地保护企业投资,是一个复杂的系统工程,也是当前系统开发者亟待解决的一个问题,涉及系统的分析、设计、编码、部署等方面.基于J2EE平台,基于实践,给出创建高性能可伸缩Web应用系统的编程策略.     

IPTV与P2P的结合

针对IPTV所面临的技术瓶颈,阐述了IPTV与P2P技术结合的优势,并描述了相关工作流程。     

P2P和CDN中MDC流媒体的性能对比

文中检测并对比了基于多重描述编码（慨）的流媒体在对等网（P2P）和内容分发网络（CDN）中的性能。多个服务器同时为一个客户请求提供相同的描述，这样提高了网络传输的可靠性，并增加了服务器的数据传输率。用ns-2网络模拟器实现了这两种方法，实验结果表明：虽然P2P网络存在高度不稳定的情况，但是基于P2P的MDC流视频的质量明显比CDN上的好。     

创建高性能与高伸缩性的J2EE应用

对于J2EE应用来说 ,性能和伸缩性问题是必须考虑的一个重要问题。将从J2EE应用程序体系结构出发 ,探究产生这些性能问题的根源 ,并提出一些原则来提高J2EE应用的性能和伸缩性。     

高效内容分布网络设计与实现

结合CDN和P2P两种不同网络结构的优点，改善传统内容分布网络拓扑结构，使用基于无比率限制纠错码技术改进Swarming传输协议，给出了一种高效内容分布网络设计。介绍了该内容分布网络的系统结构及相关关键技术等方面内容，以及这种新内容分布网络的特性。     

An analysis of peer-to-peer networks with altruistic peers

We develop a new model of the interaction of rational peers in a Peer-to-Peer (P2P) network that has at its heart altruism, an intrinsic parameter reflecting peers’ inherent willingness to contribute. Two different approaches for modelling altruistic behavior and its attendant benefit are introduced. With either approach, we use Game Theoretic analysis to calculate Nash equilibria and predict peer behavior in terms of individual contribution. We consider the cases of P2P networks of peers that (i) have homogeneous altruism levels or (ii) have heterogeneous altruism levels, but with known probability distributions. We find that, under the effects of altruism, a substantial fraction of peers will contribute when altruism levels are within certain intervals, even though no incentive mechanism is used. Our results corroborate empirical evidence of large P2P networks surviving or even flourishing without or with barely functioning incentive mechanisms. We also enhance the model with a simple but powerful incentive scheme to limit free-riding and increase contribution to the network, and show that the particular incentive scheme on networks with altruistic peers achieves its goal.

Design, optimization and performance evaluation of a content distribution overlay for streaming

As an evolution of peer-to-peer (p2p) file-sharing applications, overlay-based networks are also adopted to efficiently distribute content with real-time constraints to a wide user population. In addition, they can be utilized to exploit application level strategies to overcome limitations imposed by the underlying network infrastructure, e.g., the lack of multicast support.In this perspective, the paper introduces an overlay Content Distribution Network (CDN) able to sustain the real-time delivery of data streams. To better use resources, and to face the churn affecting users, the control and optimization of the CDN are performed through a model predictive control scheme. Simulations of two use cases are provided to show the effectiveness of the proposed solution. In particular, the stream of multimedia and interactive grid data are considered.     

P2P和CDN中MDC流媒体的性能对比

文中检测并对比了基于多重描述编码(MDC)的流媒体在对等网(P2P)和内容分发网络(CDN)中的性能。多个服务器同时为一个客户请求提供相同的描述,这样提高了网络传输的可靠性,并增加了服务器的数据传输率。用ns-2网络模拟器实现了这两种方法,实验结果表明:虽然P2P网络存在高度不稳定的情况,但是基于P2P的MDC流视频的质量明显比CDN上的好。     

基于边缘缓存的下载加速方案设计与实现

针对传统网络拥塞导致网络下载速度过慢等一系列问题,文章通过对内容分发网络和P2P技术的研究,提出了一种基于边缘缓存的下载加速方案。该方案将P2P技术引入内容分发网络,利用各自优点,构建一个新型资源下载服务系统。将中心服务器上的资源推送至网络边缘,缩短了用户和资源的距离。同时,让边缘缓存服务器与邻近用户自发组建P2P下载网络,将资源更加边缘化,通过就近获取资源,提高下栽速度。实验表明,该方案不仅可以有效提高下栽速度,而且可以有效控制骨干网的网络流量。     

Attraction, stability and robustness for stochastic functional differential equations with infinite delay

This paper establishes the stochastic LaSalle theorem to locate limit sets for stochastic functional differential equations with infinite delay, from which some criteria on attraction, boundedness, stability and robustness are obtained. To illustrate the applications of our results clearly, this paper considers a scalar stochastic integro-differential equation with infinite delay as an example.     

通信网络设计:传输容量、设计代价和可扩展性

虽然目前围绕复杂网络的流量动力学研究日益增多,但这类研究尚存在一些共性问题.例如:所采用的网络流模型过于简单;没有考虑网络设计的代价和可扩展性.本文建立在一个更为真实的网络流模型之上,同时为网络设计问题提供了更全面的视角.本文在广为研究的传输容量之外又引入了另外两个设计目标:网络设计代价和可扩展性.通过引入笛卡尔坐标系统,本文量化分析了不同的网络设计因素是如何独立地影响以及通过相互作用共同影响这些网络设计目标的.结果表明,不同的网络拓扑结构呈现出不同的网络设计可行解空间形状,并在实现高效费比和可扩展的网络设计目标上表现出不同的能力.特别地,文章指出现有的经验性网络设计背后隐藏的理念不能满足高效费比和可扩展的网络设计需求,并提出了针对BA网络的一种高效费比和可扩展的设计方案,即有效路由结合基于有效介数的链路带宽分配方案.而如果从头开始设计一个全新的网络,则随机网络是达成上述目标的最佳选择.     

Gap-metric-based robustness analysis of nonlinear systems with full and partial feedback linearisation

This paper uses gap metric analysis to derive robustness and performance margins for feedback linearising controllers. Distinct from previous robustness analysis, it incorporates the case of output unstructured uncertainties, and is shown to yield general stability conditions which can be applied to both stable and unstable plants. It then expands on existing feedback linearising control schemes by introducing a more general robust feedback linearising control design which classifies the system nonlinearity into stable and unstable components and cancels only the unstable plant nonlinearities. This is done in order to preserve the stabilising action of the inherently stabilising nonlinearities. Robustness and performance margins are derived for this control scheme, and are expressed in terms of bounds on the plant nonlinearities and the accuracy of the cancellation of the unstable plant nonlinearity by the controller. Case studies then confirm reduced conservatism compared with standard methods.