Semi-Fluid content distribution model for fast data dissemination in heterogeneous overlay networks

Overlay networks and peer-to-peer networking have emerged as alternative solutions to solve many problems related to massive information distribution and processing tasks by providing enhanced services in the application layer. For instance, overlay networks can improve data dissemination in P2P file sharing overlays and Content Distribution Networks (CDNs). In such overlay networks, delay is considered as a critical performance metric. A viable content distribution model could considerably minimize the completion time and would lead to efficient utilization of resources such as network bandwidth. The main objective of this paper is to design a new flexible content distribution model for fast data dissemination in overlay networks with heterogeneous nodes. The proposed “Semi-Fluid” content distribution model is a hybrid model that enables fast data dissemination in overlay networks by combining Chunk and Fluid content distribution models. In this new content distribution model, the chunk content is distributed into heterogeneous overlay nodes in a fluid manner. The proposed hybrid content distribution model eliminates both a backpressure problem caused by the Fluid content distribution model, as well as a chunk transition delay caused by the Chunk content distribution model. The performance of the proposed Semi-Fluid content distribution model has been evaluated by mathematical analysis as well as by real implementation over the “PlanetLab” platform, and the obtained results show that the Semi-Fluid content distribution model efficiently reduces the total download time of the clients. Hence, the Semi-Fluid content distribution model can be deployed as a promising solution for fast data dissemination in heterogeneous overlay networks.     

Context- and social-aware middleware for opportunistic networks

Opportunistic networks are multi-hop ad hoc networks in which nodes opportunistically exploit any pair-wise contact to share and forward content, without requiring any pre-existing Internet infrastructure. Opportunistic networks tolerate partitions, long disconnections, and topology instability in general. In this challenging environment, leveraging users’ mobility represents the most effective way to deliver content to interested users. In this paper we propose a context- and social-aware middleware that autonomically learns context and social information on the users of the network, and that uses this information in order to predict users’ future movements. In order to evaluate the proposed middleware on a realistic scenario, we have designed and implemented a context- and social-aware content sharing service, exploiting the functionality of the middleware. Both the middleware and the content sharing service have been integrated with an existing data-centric architecture (the Haggle architecture) for opportunistic networks. Finally, we have validated the proposed content sharing application on a small-scale testbed and, on a larger scale, we have investigated the advantages provided by context- and social-aware sharing strategies by means of extensive simulations. The main result of this paper is the definition and implementation of a context- and social-aware middleware able to share context information with all the interested components improving the efficiency and performances of services and protocols in opportunistic networks. With respect to content sharing strategies that do not exploit context and social information, we have obtained up to 200% improvements in terms of hit rate (probability that users receive the content they request) and 99% reduction in resource consumption in terms of traffic generated on the network.     

移动对等网络体系结构的研究与设计

随着科学技术的进步,移动用户的日渐增多和移动网络应用环境的逐渐成熟,人们对移动网络的速度要求越来越高,使得无线网络上P2P技术的需求日渐强烈。众所周知,无线网络通信和终端的移动性使得网络在带宽、延迟、连接可靠性、连接维持可预期性等通信性能上与有线网络相比相差很远。可以利用移动P2P方式提供的视频点播、资源共享和移动协同计算等,提高网络的性能。     

一种新型主动式网络体系结构模型

主动网是一种允许用户“按需”定制自己的服务的可编程网络。由于允许用户编程,主动网不但应具有较好的可编程性,而且应具有较好的性能和安全性。文章基于组件和安全语言技术提出了一种新的主动网体系结构模型----Ac-tiveWare。它包括网络基础设施、协议件和主动包三个层次。基于这一模型,用户可以利用协议件安全、方便地在主动网上构建自己的服务。     

W-Grid: A scalable and efficient self-organizing infrastructure for multi-dimensional data management,querying and routing in wireless data-centric sensor networks

Data-centric sensor networks are advanced ad hoc networks that act like a distributed database managing and indexing sensed data in order to efficiently perform advanced in-network tasks, such as routings, searches, data processing, fusion and analysis. The supplied distributed services, such as routing, content location and information sharing should be provided anywhere and at any time optimizing energy consumptions, computational resources, memory occupation and radio transmissions. Moreover, the network traffic should be equally balanced among participants in order to avoid premature discharge of some devices that may partition the network. This work describes a fully decentralized infrastructure able to self-organize nodes in ad hoc networks by exploiting local interactions and topology learning among devices. In this solution all nodes are peers and nothing prevent the approach to be used in wireless mesh networks as well. Differently from existing solutions, our proposal does not require global information or external help, such as the Global Positioning System, which works only outdoor with a precision and an efficacy both limited by weather conditions and obstacles. The infrastructure natively enables devices to perform routing and data management without using message broadcast/flooding operations. The work introduces also a feature, called full learning, that improves routing performances while balancing the traffic among devices. We report an extensive number of simulations comparing the new solution results with four existing proposals, two of which deriving from preceding versions of the infrastructure.     

构造基于信任机制的自组织资源拓扑

利用P2P覆盖网络(P2P overlay networks)进行资源组织是当前研究的热点,如何保证资源获取的可靠性是研究人员面临的一个主要问题.利用节点的动态自组织属性,基于节点物理位置的拓扑构造可以提高P2P网络的性能,但没有关注P2P网络中恶意节点的问题;基于偏好的拓扑构造可以有效地提高资源共享和搜索的效率,但没有考虑节点实际提供服务的能力和节点行为的可靠性.提出了一个基于信任机制的自组织资源拓扑构造方案,利用Bayesian方法根据节点的行为来评估节点的信任度,通过节点间基于信任关系的链路更新,构造出新的自组织拓扑结构.仿真实验表明,该拓扑结构不仅有利于节点发现资源的效率,提高整个P2P网络的交互性能,还能使节点聚集在服务能力较强的可信节点周围,保证资源选取的可靠性.     

Interworking wireless mesh networks: Problems,performance characterization,and perspectives

Wireless broadband networks based on the IEEE 802.11 technology are being increasingly deployed as mesh networks to provide users with extended coverage for wireless Internet access. These wireless mesh networks, however, may be deployed by different authorities without any coordination a priori, and hence it is possible that they overlap partially or even entirely in service area, resulting in contention of radio resources among them. In this paper, we investigate the artifacts that result from the uncoordinated deployment of wireless mesh networks. We use a network optimization approach to model the problem as resource sharing among nodes belonging to one or different networks. Based on the proposed LP formulation, we then conduct simulations to characterize the performance of overlaying wireless mesh networks, with the goal to provide perspectives for addressing the problems. We find that in a system with multiple overlaying wireless mesh networks, if no form of inter-domain coordination is present, individual mesh networks could suffer from capacity degradation due to increased network contention. One solution toward addressing the performance degradation is to “interwork” these wireless mesh networks by allowing inter-domain traffic relay through provisioning of “bridge” nodes. However, if such bridge nodes are chosen arbitrarily, the problems of throughput sub-optimality and unfairness may arise. We profile the impact of bridge node selection and show the importance in controlling network unfairness for wireless mesh network interworking. We conclude that mesh network interworking is a promising direction to address the artifacts due to uncoordinated deployment of wireless mesh networks if it is supplemented with appropriate mechanisms.     

P2P流媒体网络的关键节点识别算法

P2P流媒体网络中普遍存在一些关键节点,关键节点对网络的安全和通信性能起着重要作用,识别网络中的关键节点尤为重要,而传统方法对于大规模网络的关键节点识别时间开销很大,无法保证实时性。提出P2P流媒体网络中的关键节点识别算法,结合混合模式的网络结构特点,采用分区域的计算模型解决网络规模过大造成的巨大时间开销问题,根据节点的贡献度和传播能力差异定量化描述节点的重要性程度。仿真结果表明,所提算法可以快速获得节点重要性排序,有效识别P2P流媒体网络中的关键节点。     

结构化对等网络中面向信誉机制的资源共享平台

针对目前因特网上提高空闲网络资源利用率的需求,提出并描述了结构化对等网络中一种面向信誉机制的资源共享平台NRSP。NRSP系统可以把因特网上用户提交的各种作业高效地映射到平台中合适的网络资源上运行,充分共享空闲处理器的周期。该系统具有非集中性、可移植性、统计性与公平性的优点,使用分布式哈希表的Pastry网络来组织节点。同时提出一种新型的分布式信誉机制,支持资源的消费者与提供者之间交换信誉信息,完成信誉信息的统计。最后实现了NRSP的原型系统,通过对各种作业场景下的应用进行测试,性能分析表明NRSP采用公平的信誉机制可以更快、更多地共享其他节点的处理器周期。     

基于网络嵌入与局部合力的复杂网络社区划分算法

社区划分可以揭示复杂网络中的内在结构和行为动态特点,是当前的研究热点。文中提出了一种基于网络嵌入和局部合力的社区划分算法。该算法将网络的拓扑空间转化成欧氏空间,把网络节点转换成向量表示的数据点,首先基于重力模型和网络拓扑结构,提出局部合力和局部合力余弦中心性指标(Local Resultant Force Cosine Centrality,LFC),通过节点的LFC和节点间的距离来确定各个初始小社区的中心节点,然后将网络中其他的非中心节点划入与其最近的中心节点所在的初始小社区内,最后通过优化模块度的方法来合并初始小社区并找到最优的网络社区结构。在6个现实世界网络和可调参数人工网络上与6种知名社区划分方法进行比较,比较结果表明了新算法良好的社区划分的性能。     

基于iOS的自组网协同处理模型设计与实现

针对移动智能设备在没有网络基础设施的偏远区域,或是自然灾害破坏了网络基础设施,或是网络信号差的区域,无法进行即时通信和资源文件的共享等问题,本文提出了一种基于iOS的自组网协同处理模型。该模型利用iOS的多点连接框架,实现移动终端在中等距离下即时通信、数据文件共享以及信息协同处理。实验结果表明,该协同处理模型使得自组网内的节点能够充分利用其他节点的资源,协同计算、协同存储、共享数据文件,使得自组网整体性能得到较大增强。     

Personalization on a peer-to-peer television system

We introduce personalization on Tribler, a peer-to-peer (P2P) television system. Personalization allows users to browse programs much more efficiently according to their taste. It also enables to build social networks that can improve the performance of current P2P systems considerably, by increasing content availability, trust and the realization of proper incentives to exchange content. This paper presents a novel scheme, called BuddyCast, that builds such a social network for a user by exchanging user interest profiles using exploitation and exploration principles. Additionally, we show how the interest of a user in TV programs can be predicted from the zapping behavior by the introduced user-item relevance models, thereby avoiding the explicit rating of TV programs. Further, we present how the social network of a user can be used to realize a truly distributed recommendation of TV programs. Finally, we demonstrate a novel user interface for the personalized peer-to-peer television system that encompasses a personalized tag-based navigation to browse the available distributed content. The user interface also visualizes the social network of a user, thereby increasing community feeling which increases trust amongst users and within available content and creates incentives of to exchange content within the community.     

基于LDA的结构-内容联合社团发现模型

在社会网络中,根据已有的连接关系和文本信息发掘社会网络中的社团不但可以将相似的用户划分在一个社团,还可以用来预测网络中潜在的连接关系。为了提高社会网络中社团发现的性能,本文提出了一种基于LDA的结构-内容联合社团发现模型。首先,对社会网络的图论描述进行转化,使其适用于LDA模型。其次,对LDA模型描述进行扩充,使其包含了用户间交互的文本信息。最后,通过Gibbs采样方法对模型的参数进行估计。实验表明,本文提出的社团发现模型与其它相关方法相比较,社团发现得到的社团不仅用户间连接的紧密度和用户共享兴趣爱好的强度高,而且可以更好地用于社会网络中潜在连接的预测。     

Algorithms and performance of load-balancing with multiple hash functions in massive content distribution

We consider a two-tier content distribution system for distributing massive content, consisting of an infrastructure content distribution network (CDN) and a large number of ordinary clients. The nodes of the infrastructure network form a structured, distributed-hash-table-based (DHT) peer-to-peer (P2P) network. Each file is first placed in the CDN, and possibly, is replicated among the infrastructure nodes depending on its popularity. In such a system, it is particularly pressing to have proper load-balancing mechanisms to relieve server or network overload. The subject of the paper is on popularity-based file replication techniques within the CDN using multiple hash functions. Our strategy is to set aside a large number of hash functions. When the demand for a file exceeds the overall capacity of the current servers, a previously unused hash function is used to obtain a new node ID where the file will be replicated. The central problems are how to choose an unused hash function when replicating a file and how to choose a used hash function when requesting the file. Our solution to the file replication problem is to choose the unused hash function with the smallest index, and our solution to the file request problem is to choose a used hash function uniformly at random. Our main contribution is that we have developed a set of distributed, robust algorithms to implement the above solutions and we have evaluated their performance. In particular, we have analyzed a random binary search algorithm for file request and a random gap removal algorithm for failure recovery.     

P2P系统中非扫描型蠕虫研究

数以百万计的网络用户使用P2P网络来共享文件。但在P2P网络中,蠕虫则感染了大量的漏洞主机,并对信息设施和终端系统带来巨大的破坏。该文分析了P2P体系结构内在的风险,阐明了P2P蠕虫所带来的威胁,并且列举了威胁P2P网络的3种非扫描类型的螭虫:被动式蠕虫,反应式蠕虫和主动式蠕虫。鉴于这种情况,该文提出了一种能够减轻P2P蠕虫威胁的对策。     

基于活动的社交网络中的群组推荐算法设计

在基于活动的社交网络（EBSN）中,群组中聚集了具有相似兴趣的用户,并为用户组织并举办线下活动,在社区的发展中起到了至关重要的作用,因而理解用户加入群组的原因和群组形成的过程在社交网络的研究中是一个重要的议题.本文通过基于活动的社交网络中的一些相关内容信息,比如社交网络中的标签信息和地理位置信息,来辅助推荐系统更好地为用户预测对于群组的偏好.本文提出了SEGELER （pair-wiSE Geo-social Event-based LatEnt factoR）模型,并使用这些社交网络中的信息,来为用户的兴趣进行预测.通过在真实的EBSN数据集上进行实验与验证,本文的模型不仅可以有效提升对于用户偏好的预测,也可以缓解冷启动问题.     

Leveraging deployment models on low-resource devices for cloud services in community networks

Community networks are crowd-sourced IP networks that evolved into regional-scale computing platforms. This has led to adapting the cloud computing model for services that can operate and use computing resources inside a community network. The network and computing infrastructure is contributed by individuals, companies, organizations and maintained by its members. Community cloud devices are often low-capacity computing devices, such as home gateways or cabinet servers, with limited capabilities. These devices are used to install and operate specific personal or community services, but can be turned into multi-purpose execution environments applying machine or operating system (container) virtualization. However that requires addressing the problems of resource sharing in low-capacity devices, related to predictable performance and isolation. Our comparative analysis with the current infrastructure in community networks gives evidence about how devices can concurrently run multiple services, the trade offs between the number and resource requirements of services and the degradation of quality that services may suffer.     

支持访问控制的P2P大规模遥感数据分发系统

遥感数据日益增长,大规模遥感数据分发对集中分发服务器构成了巨大压力。充分利用参与下载节点的网络资源,提出并实现了一种支持访问控制的P2P大规模遥感数据分发系统。遥感数据分发系统分为遥感数据管理平台和遥感数据客户端两部分,遥感数据管理平台包含共享分发平台网站、云存储、种子资源服务器和跟踪服务器4个组件,遥感数据各客户端和种子资源服务器构成P2P网络。设计了包括共享分片、分片选择、跟踪器通信等的P2P协议,实现的遥感数据分发系统能够上传遥感数据并自动做种,支持对用户的访问控制。根据用户权限进行下载,各下载节点共享分片,然后基于类Bittorrent协议来加速遥感数据的分发。实验结果表明,实现的大规模遥感数据分发系统的功能完善,在多节点下载时具备良好的并发性能,能够满足大规模遥感数据分发的需要。     

Building a peer-to-peer content distribution network with high performance,scalability and robustness

Content distribution networks (CDN) are fundamental, yet expensive technologies for distributing the content of web-servers to large audiences. The P2P model is a perfect match to build a low-cost and scalable CDN infrastructure for popular websites by exploiting the underutilized resources of their user communities. However, building a P2P-based CDN is not a straightforward endeavor. In contrast to traditional CDNs, peers are autonomous and volunteer participants with their own heterogeneous interests that should be taken into account in the design of the P2P system. Moreover, churn rate is much higher than in dedicated CDN infrastructures, which can easily destabilize the system and severely degrade the performance. Finally and foremostly, while many P2P systems abstract any topological information about the underlying network, a top priority of a CDN is to incorporate locality-awareness in query routing in order to locate close-by content. This paper aims at building a P2P CDN with high performance, scalability and robustness. Our proposed protocols combine DHT efficiency with gossip robustness and take into account the interests and localities of peers. In short, Flower-CDN provides a hybrid and locality-aware routing infrastructure for user queries. PetalUp-CDN is a highly scalable version of Flower-CDN that dynamically adapts to variable rates of participation and prevent overload situations. In addition, we ensure the robustness of our P2P CDN via low-cost maintenance protocols that can detect and recover from churn and dynamicity. Our extensive performance evaluation shows that our protocols yield high performance gains under both static and highly dynamic environments. Furthermore, they incur acceptable and tunable overhead. Finally we provide main guidelines to deploy Flower-CDN for the public use.