Existe um interesse crescente do mercado por aplicações de multimídia em streaming via rede. Particularmente, as aplicações de live streaming que utilizam a tecnologia de redes P2P para a disseminação de conteúdo têm sido alvo de grande atenção. Aplicações como PPLive e PPStream provam que as aplicações de live streaming em redes P2P são uma realidade com relação à tecnologia atual. Os sistemas de live streaming fornecem um serviço de multicast no nível de aplicação para transmissões ao vivo na Internet. Essas aplicações de live streaming, quando executadas em redes P2P, têm potencial para serem altamente robustas, escaláveis e adaptativas devido à redundância e não dependência de recursos particulares dentre os nodos participantes. Porém, para fazer uso de todas as vantagens disponíveis, a aplicação deve contornar alguns desafios: i) manter a qualidade de playback mesmo com a inerente dinamicidade das redes P2P; ii) impedir que nodos incorretos escondam ações maliciosas atrás do anonimato que existe em P2P; iii) manter a taxa de upload dos nodos participantes da aplicação em um nível aceitável. A taxa de upload dos nodos é muito importante porque a aplicação de live streaming em P2P é uma aplicação cooperativa. Desta forma, esperase que todo novo usuário ajude a aplicação retransmitindo pacotes para outros usuários, mantendo, desta forma, a capacidade global de upload do sistema. Infelizmente, manter a cooperação em live streaming não é uma tarefa trivial, visto que cada nodo enfrenta o dilema social do interesse próprio (individualmente é melhor explorar a cooperação dos outros usuários sem reciprocidade) versus a cooperação para com o grupo. A principal contribuição deste trabalho consiste na apresentação de um modelo matemático baseado em Teoria dos Jogos Evolucionários, cujo objetivo é ajudar a compreender as aplicações de live streaming em redes P2P e os fatores que influenciam o seu correto funcionamento. Como contribuição secundária, este trabalho fornece uma análise estatística do comportamento do download e upload observado nestas aplicações. A análise estatística mostra que existe um decaimento da variância temporal de download e upload nas aplicações de live streaming, e que tal decaimento segue uma lei de potência. Os resultados evolucionários do modelo indicam que, se a queda do índice de satisfação dos usuários com a taxa de download for suave, e se a redução da satisfação devido ao custo de upload for insignificante, então existe um ambiente propício para que a cooperação entre os nodos cresça. De forma inversa, se a queda do índice de satisfação dos usuários com a taxa de download for abrupta, e a redução da satisfação devido ao custo de upload for significativa, então existe um ambiente propício para proliferação de nodos oportunistas. A realização e descrição desta pesquisa é composta de quatro etapas principais: i) a delimitação do cenário de live streaming e a definição do jogo para modelagem; ii) a definição do conjunto de estratégias e da função de utilidade; iii) a criação do modelo; iv) a análise do modelo e a apresentação dos resultados de simulação. A análise do modelo abrange três fases: i) análise estatística e comparação das características de download e upload dos dois simuladores utilizados; ii) avaliação do modelo de Teoria dos Jogos Evolucionários através de simulações; e iii) análise dos resultados evolucionários gerados pelo simulador de Teoria dos Jogos Evolucionários. / There is a growing interest in the market for networked multimedia applications. Live streaming applications that use the technology of P2P networks for distribution of live content have specially been the subject of great attention. Applications such as PPLive and PPStrem demonstrate that P2P live streaming applications are already possible with our present technology. Live streaming systems provide a multicast service in the application level for live broadcasts to users through the Internet. These systems executing in P2P networks have the potential to be highly robust, scalable and adaptive due to the characteristics of these scenarios. However, to take advantage of these potential properties, they must overcome some challenges: i) to maintain the playback quality even with the inherent dynamics of P2P networks; ii) to prevent that incorrect peers hide malicious behavior behind their anonymity; iii) to maintain the upload contribution of peers at acceptable levels. The upload contribution of peers is highly important because live streaming applications are cooperative applications. Therefore, every new user must help the application forwarding packets to other users, thereby maintaining the global upload capacity of the system. Unfortunately, the maintenance of cooperation in live streaming system is not a trivial task, since each node faces the social dilemma of self-interest (individually is always better to explore the cooperation of other users without reciprocity) versus cooperation to the group. The main contribution of this dissertation is the presentation of a mathematical model based on Evolutionary Game Theory, whose goal is to help understanding live streaming P2P applications and the factors that influence their correct operation. As a secondary contribution, this work provides a statistical analysis of download and upload behaviors of peers in live streaming P2P systems. The statistical analysis indicates that there is a decay in the download and upload variances, and that this decay follows a power law. The evolutionary results of the model indicate that, if the satisfaction of users with the download rate is smooth, and the reduction of satisfaction due to the upload cost is negligible, then there is a favorable environment for the growth of cooperation. Conversely, if the satisfaction of users with the download rate is abrupt, and the reduction of satisfaction due to the upload cost is significant, then there is a favorable environment to the proliferation of opportunistic nodes. The realization and description of this research is composed of four main steps: i) the definition of the live streaming scenario and the definition of the game to model this scenario; ii) the definition of the strategy set and of the utility function; iii) the suggestion of a model; iv) the analysis of the proposed model and the presentation of obtained results. The model analysis comprehends three phases: i) the statistical analysis and the comparison of the characteristics of download and upload of the two simulators used in this work; ii) the evaluation of the Evolutionary Game Theory model through simulation; and iii) the analysis of the results generated by the Evolutionary Game Theory simulator.

Sistemas corporativos modernos cada vez mais dependentes da rede e a integração de serviços entorno do modelo TCP/IP elevam a exigência de Qualidade de Serviço da infraestrutura de TI. Neste cenário, o dinamismo das redes atuais em conjunto com os novos requisitos de QoS exigem que a infra-estrutura de TI seja mais autônoma e confiável. Para tratar esta questão, o modelo de Gerenciamento de Redes Baseado em Políticas, proposto pelo IETF, vem se consolidando como uma abordagem para controlar o comportamento da rede através do controle das configurações dos seus dispositivos. Porém, o foco deste modelo é o gerenciamento de políticas internas a um domínio administrativo. Esta característica faz com que o modelo possua algumas limitações, tais como a incapacidade de estabelecer qualquer tipo de coordenação entre diferentes PDPs e a impossibilidade de reagir a eventos externos. Visando agregar autonomia ao modelo de gerenciamento baseado em políticas, este trabalho propõe uma arquitetura em camadas que empregue os conceitos de Autonomic Computing relacionados a: i) adaptação dinâmica dos recursos gerenciados em resposta às mudanças no ambiente, ii) integração com sistemas de gerenciamento de outros domínios através do recebimento de notificações destes, iii) capacidade de planejar ações de gerenciamento e iv) promoção de ações de gerenciamento que envolvam mais de um domínio administrativo, estabelecendo uma espécie de coordenação entre PDPs. Para a implementação destes conceitos, a arquitetura prevê o uso de uma camada peerto- peer (P2P) sobre a plataforma de políticas. Desta forma, a partir de uma notificação recebida, a camada P2P planeja ações visando adaptar o comportamento da rede aos eventos ocorridos na infra-estrutura de TI. As ações planejadas traduzem-se em inclusões ou remoções de políticas da plataforma de políticas responsável por gerenciar a configuração dos dispositivos de rede. Para notificações que envolvam recursos de mais de um domínio administrativo, os peers de gerenciamento agem de forma coordenada para implantar as devidas ações em cada domínio. A arquitetura proposta foi projetada com foco em prover QoS em uma rede com suporte à DiffServ, embora acredite-se que a sua estrutura seja genérica o bastante para ser aplicada a outros contextos. Como estudo de caso, foi analisado o emprego da arquitetura em resposta a eventos gerados por uma grade computacional. Foi elaborado ainda um protótipo da arquitetura utilizando o Globus Toolkit 4 como fonte de eventos. / Modern corporative systems becoming more dependent of the network and the integration of services around the TCP/IP model increase the requirement of Quality of Service (QoS) of the IT infrastructure. In this scene, the dynamism of current networks together with the new requirements of QoS demands a more autonomous and reliable IT infrastructure. To address this issue, the model of Police Based Network Management, proposed by IETF, has been consolidated as an approach to control the behavior of the network through the control of the configurations of its devices. However, the focus of this model is the management of the policies internal to an administrative domain. This feature brings some limitations to the model, such as the incapacity to establish any kind of coordination between different PDPs and the impossibility to react to external events. Aiming at to add autonomy to the model of Policy Based Network Management, this work proposes a layered architecture based on the concepts of Autonomic Computing related to: i) the dynamic adaptation of the managed resources in response to changes in the environment, ii) integration with management systems of other domains through the reception of notifications of these systems, iii) ability of planning the management actions and iv) execution of multi-domain management actions, establishing a kind of coordination between PDPs. To implement these concepts, the architecture was designed with a peer-to-peer layer above the policy platform. Thus, from a received notification, the P2P layer plans actions aiming to adapt the network behavior in response to the events occurred in the IT infrastructure. The planned actions are, actually, inclusions or removals of policies in the policy platform responsible for the management of the network devices configuration. For notifications related with resources of more than one administrative domain, the management peers act in a coordinated way in order to establish the suitable actions in each domain. The proposed architecture was designed with focus in providing QoS in a network with support to DiffServ, although we believe that its structure is generic enough to be applied to other contexts. As case study, it was analyzed the use of the architecture in response to events generated by a computational grid. Additionally, a prototype of the architecture was build making use of Globus Toolkit 4 as an event source.

Concepts like peer-to-peer networks and distributed computing are not new. They have been available in different forms for a long time. This thesis examines the possibility of merging these concepts. The assumption is that non-centralized peer-to-peer networks can be used for effective sharing of computing resources. While most peer-to-peer systems today concentrate on sharing of data in various forms, this thesis concentrates on sharing of clock cycles instead of files.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2015-12-01T11:18:53Z No. of bitstreams: 1 vitorfreitasesouza.pdf: 4838221 bytes, checksum: 593f759949de45c0b044f62ba94f9a1a (MD5) / Made available in DSpace on 2015-12-01T11:18:53Z (GMT). No. of bitstreams: 1 vitorfreitasesouza.pdf: 4838221 bytes, checksum: 593f759949de45c0b044f62ba94f9a1a (MD5) Previous issue date: 2015-02-27 / A concepção de workflows científicos é uma abordagem amplamente utilizada no contexto de e-Science e experimentação científica. Existem muitas pesquisas voltadas para o gerenciamento e execução de experimentos baseados em workflows. No entanto, experimentos complexos envolvem interações entre pesquisadores geograficamente distribuídos, demandando utilização de grandes volumes de dados, serviços e recursos computacionais distribuídos. Este cenário categoriza um ecossistema de experimentação científica. Para conduzir experimentos neste contexto, cientistas precisam de uma arquitetura flexível, extensível e escalável. Durante o processo de experimentação, informações valiosas podem ser perdidas e oportunidades de reutilização de recursos e serviços desperdiçadas, caso a arquitetura de ecossistema para e-Science não considere estes aspectos. Com o objetivo de tratar a flexibilidade, a extensibilidade e a escalabilidade de plataformas de ecossistemas, este trabalho apresenta uma arquitetura orientada a serviços apoiada por uma rede ponto a ponto, desenvolvida para tratar as etapas do ciclo de vida de um experimento científico. Este trabalho apresenta como contribuições uma arquitetura para ecossistemas de software científico, a implementação desta arquitetura, bem como a sua avaliação. / The conception of scientific workflows is a widely used approach in the context of e- Science and scientific experimentation. There are many researches about the management and execution of experiments based on workflows. However, scientific experiments involve complex interactions between geographically distributed researchers, requiring the usage of large amount of data, services and distributed computing resources. This scenario categorizes a scientific experimentation ecosystem. In order to carry out experiments in this context researchers need an architecture for e-Science that supports flexibility, extensibility and scalability. During the experimentation process, valuable information can be unexploited and reusing opportunities of resources and services could be lost if the ecosystem architecture for e-Science does not consider previous mentioned requirements. In order to address the flexibility, extensibility and scalability of ecosystems platforms, this dissertation presents a service-oriented architecture supported by a peer-to-peer network. It was developed to support life-cycle stages of a scientific experiment. This work also presents, as contributions, an architecture to support experiments execution of scientific software ecosystems, the implementation of this architecture, as well as its evaluation.

Avec l’émergence de plates-formes distribuées très hétérogènes, dynamiques et à large-échelle, la nécessité d’un moyen de les programmer efficacement et de les gérer a surgi. Le concept de l’informatique autonomique propose de créer des systèmes autogérables — des systèmes qui sont conscients de leurs composants et de leur environnement, et peuvent se configurer, s’optimiser, se guérir et se protéger. Dans le cadre de la réalisation de tels systèmes, la programmation déclarative, dont l’objectif est de faciliter la tâche du programmeur en séparant le contrôle de la logique du calcul, a retrouvé beaucoup d’intérêt ce dernier temps. En particulier, la programmation à base de des règles est considérée comme un modèle prometteur dans cette quête pour des abstractions de programmation adéquates pour ces plates-formes. Cependant, bien que ces modèles gagnent beaucoup d’attention, ils créent une demande pour des outils génériques capables de les exécuter à large échelle. Le modèle de programmation chimique, qui a été conçu suite à la métaphore chimique, est un modéle de programmation à bas de règles et d’ordre supérieur, avec une exécution non-déterministe modèle, où les règles sont appliquées simultanément sur un multi-ensemble de données. Dans cette thèse, nous proposons la conception, le développement et l’expérimentation d’un intergiciel distribué pour l’exécution de programmes chimique sur des plates-formes à large échelle et génériques. L’architecture proposée combine une couche de communication pair-à-pair avec un protocole de capture atomique d’objets sur lesquels les règles doivent être appliquées, et un système efficace de détection de terminaison. Nous décrivons le prototype d’intergiciel mettant en œuvre cette architecture. Basé sur son déploiement dans un banc d’essai réel, nous présentons les résultats de performance, qui confirment les complexités analytiques obtenues et montrons expérimentalement la viabilité d’un tel modèle de programmation. / With the emergence of highly heterogeneous, dynamic and large distributed platforms, the need for a way to efficiently program and manage them has arisen. The concept of autonomic computing proposes to create self-manageable systems — systems which are aware of their components and their environment, and can configure, optimise, heal and protect themselves. In the context of realisation of such systems, declarative programming, whose goal is to ease the programmer’s task by separating the control from the logic of a computation, has regained a lot of interest recently. In particular, rule-based programming is regarded as a promising model in this quest for adequate programming abstractions for these platforms. However, while these models are gaining a lot of attention, there is a demand for generic tools able to run such models at large scale. The chemical programming model, which was designed following the chemical metaphor, is a higher-order, rule-based programming model, with a non-deterministic execution model, where rules are applied concurrently on a multiset of data. In this thesis, we propose the design, development, and experimentation of a distributed chemical runtime for generic, largely-distributed platforms. The architecture proposed combines a peer-to-peer communication layer with an adaptive protocol for atomically capturing objects on which rules should be applied, and an efficient termination-detection scheme. We describe the software prototype implementing this architecture. Based on its deployment over a real-world test-bed, we present its performance results, which confirm analytically obtained complexities, and experimentally show the sustainability of such a programming model.

Bandwidth and resource constraints at the server side is a limitation for deployment of streaming media applications. Resource constraints at the server side often leads to saturation of resources during sudden increase in requests. End System Multicast (ESM) is used to overcome the problem of resource saturation. Resources such as storage, bandwidth available at the end systems are utilized to deliver streaming media. In ESM, the end-systems (also known as peers) form a network which is commonly known as Peer-to-Peer (P2P) network. These peers that receive the stream in turn act as routable components and forward the stream to other requests. These peers do not possess server like characteristics. The peers differ from the server in the following ways: (a) they join and exit the system at will (b) unlike servers, they are not reliable source of media. This induces instability in the network. Therefore, streaming media solution over such unstable peer network is a challenging task. Two kinds of media streaming is supported by ESM, namely, live streaming media and on-demand streaming media. ESM is well studied to support live streaming media. In this thesis we explore the effectiveness of using ESM to support on-demand streaming media over P2P network. There are two major issues to support on-demand streaming video.They are: (a)unlike live streaming, every request should be served from the beginning of the stream and (b) instability in the network due to peer characteristics (particularly transience of peers). In our work, late arriving peers can join the existing stream if the initial segments can be served to these peers. In this scheme, a single stream is used to serve multiple requests and therefore the throughput increases. We propose patching mechanism in which the initial segments of media are temporarily cached in the peers as patches. The peers as they join, contribute storage and this storage space is used to cache the initial segments. The patching mechanism is controlled by Expanding Window Control Protocol (EWCP). EWCP defines a “virtual window” that logically represents the aggregated cache contributed by the peers. The window expands as the peer contribute more resources. Larger the window size more is the number of clients that can be served by a single stream. GAP is formed when contiguous segments of media is lost. GAP limits the expansion of the virtual window. We explore the conditions that lead to the formation of GAP. GAP is formed due to the transience and non-cooperation of peers. Transience of peers coupled with real time nature of the application requires fast failure recovery algorithms and methods to overcome loss of media segments. We propose an efficient peer management protocol that provides constant failure recovery time. We explore several redundancy techniques to overcome the problem of loss of video segments during transience of peers. Peer characteristics (duration, resource contribution etc.) have significant impact on performance.The design of peer management protocol must include peer characteristics to increase its effectiveness. In this thesis we present detailed analysis of the relationship between the peer characteristics and performance. Our results indicate that peer characteristics and realtime nature of the application control the performance of the system. Based on our study, we propose algorithms that considers these parameters and increase the performance of the system. Finally, we bring all the pieces of our work together into a comprehensive system architecture for streaming media over P2P networks. We have implemented a prototype Black-Board System (BBS), a distance program utility that reflects the main concepts of our work. We show that algorithms that exploit peer characteristics performs well in P2P networks.

<p>Abstrakt (svenska)</p><p>Bakgrund: Piratkopieringen bara ökar och ökar. Program-, spel- och musikbranschen har idag stora problem. En i stort sett okunnig användare kan fixa en nyutgiven skiva innan den nått butikerna på grund av piratkopieringen. Detta problem möjliggörs genom att ingen bra lösning finns i form av fungerande kopieringsskydd samt att fildelningstjänsterna får stort spelrum. Vi går in specifikt och undersöker musikbranschen.</p><p>Syfte: Fördjupa oss i begreppet piratkopiering. Vidare vill vi upplysa och informera såväl musikbranschen som användare om problemet och dess framtid. Vi hoppas att det resultat vi kommer fram till kan ge underlag för vidare forskning.</p><p>Metod: Vår information har tagits från artiklar på Internet samt från litteratur vi ansett vara aktuell. Telefonintervjuer har skett med Magnus Mårtensson, IFPI (International Federation of the Phonographic Industry), programjuristen Anna Burén på Sveriges Radio, Per Sandin,</p><p>General manager EMI marketing samt ett flertal Internetleverantörer. Vi har dessutom sammanställt en enkät som besvarats av en mängd personer.</p><p>Resultat: Många av gårdagens skivköpare anser att priset för en CD-skiva är för dyrt idag. Man har upptäckt piratkopieringen med dess obegränsade funktioner samt insett hur lätt det är att få tag på gratis musik utan repressalier, vilket beror på den idag vaga och ej alltför avskräckande lagstiftningen. Musikbolagen förlorar pengar och höjer därmed priserna för skivorna samtidigt som de aktivt arbetar för att hitta det perfekta kopieringsskyddet eller för att komma på någon annan strålande lösning. Framtiden ser oviss ut och för tillfället har</p><p>piratkopierarna och fildelningstjänsterna trumf på hand.</p><p>Nyckelord: Mp3, CD, Kopieringsskydd, Fildelningstjänster, Upphovsrätt och Musikintressenter.</p> / <p>Abstract (English)</p><p>Background: Illegal copying increases rapidly. Software-, game- and music industry are experiencing troubled times at the moment. Today, a practically ignorant person would have no problems to get hold of a newly published record before it reaches the stores because of the</p><p>illegal copying. This problem is made possible due to that no good solution exists. Copy protection isn’t good enough and peer-to-peer-networks are bigger than ever. In this work we will examine specifically the music industry.</p><p>Purpose: We will specialize in the term of illegal copying. Further we want to enlight and inform the music industry as well as the users of the problem and it´s future. We hope the result we will achieve can be a foundation for further research.</p><p>Realization: We have gathered our information from articles on the Internet and also from updated literature. Interviews were made over the phone with Magnus Mårtensson, IFPI (International Federation of the Phonographic Industry), Anna Burén, lawyer of copyright at</p><p>Swedish Radio, Per Sandin, General manager EMI marketing and also a lot of Internetsuppliers. We have also compilated an inquiry which has been replied to by many people.</p><p>Conclusion: Many of the buyers from the past consider the cost of a CD far too high. Instead they have discovered the illegal copying and its unlimited functions. They have also realized how easy you can get new music without reprisals, which mostly depends on the vague and</p><p>not to scary laws. Music companies are losing money and therefore they raise the prize of a single CD, simultaneously as they work to find the perfect copy protection. The future looks uncertain and for the moment, those who are copying along with peer-to-peer-networks have</p><p>all the trumps.</p><p>Keywords: mp3, CD, copy-protection, peer-to-peer-networks, copyright, illegal copying, music companies.</p>

推薦系統目的在於收集大眾對於資源的評價，經過推薦機制的整理，呈現給符合偏好的使用者，但是Supernode架構與傳統主從架構的不同，增加推薦系統收集、統計推薦指標的困難。在本篇論文中，將利用RDF(S)建置與Supernode、Peer、MP3相關的本體論，同時，依據Supernode與Peer在推薦系統中所扮演的功能與角色的不同，將不同的結構藍圖分別放置在Supernode與Peer之中，並且藉由Supernode與Peer中所描述的資源、屬性以及資源和資源之間的關係來解決在Supernode架構中推薦指標的收集、統計與更新等問題，以及降低推薦系統中"Cold Start"與"Spamming"這兩個問題所產生的影響。 / The purpose of recommendation system is to collect public opinions and provide synthetic recommended result for users. Using our proposed recommended mechanism, the recommendation system presents personal music recommended list for each user in peer node to match his preference. Because the complexity difference of network structure, we found that the rating collection and computation process will be more complex in supernode P2P network than in client-server WWW network. In this thesis, firstly we use RDF(S) to construct associated ontology schema for supernode, peer node, and MP3 music. Then, we put respective ontology schema in the suprenode and peer node based on their roles and functions within the recommendation system. The resources and attributes relationships between supernode and peer nodes provide the capacity to solve the rating collection, analysis, and updating problems. We also propose possible solutions for reducing the side effects of cold start and spamming problems in the recommendation system.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Peer-to-peer networks provide an efficient way for sharing computer resources. The transport layer underlies these networks. On the Internet, TCP and UDP are the mostly used protocols in this layer. SCTP is another transport layer protocol: related to TCP and UDP, SCTP offers additional functionalities that makes it more suitable to certain kinds of applications. This work aims to show the viability of the use of SCTP as the transport layer protocol for peer-to-peer file sharing applications, using the peculiar functionalities of this protocol to satisfy the needs of these applications in a more efficient way. / As redes peer-to-peer oferecem uma forma eficaz para o compartilhamento de recursos dos computadores. Sob essas redes está a camada de transporte. Na Internet, os protocolos mais utilizados nessa camada são o TCP e o UDP. Outro protocolo da camada de transporte e o SCTP, que oferece funcionalidades adicionais em relação ao TCP e ao UDP que o tornam mais apropriado a determinados tipos de aplicações. Este trabalho tem como objetivo mostrar a viabilidade da utiliza¸são do SCTP como protocolo da camada de transporte em aplicativos peer-to-peer de compartilhamento de arquivos, fazendo uso das funcionalidades peculiares a esse protocolo para satisfazer de forma mais eficaz as necessidades destes aplicativos. / Mestre em Ciência da Computação

Made available in DSpace on 2015-04-11T14:03:13Z (GMT). No. of bitstreams: 1 DISSERTACAO JOAO DA MATA.pdf: 5833486 bytes, checksum: fd81987d9b1e9ac8f9bb648058db273b (MD5) Previous issue date: 2012-03-22 / Fundação de Amparo à Pesquisa do Estado do Amazonas / Scalability and high demand for resources are the main challenges that content providers face to deploy Video-on-Demand applications. The most popular site for sharing videos, YouTube, has over 4 billion videos viewed a day and 60 hours of video are uploaded every minute. Hybrid systems (CDN-P2P) have been proposed as a scalable and cost effective solution for VoD distribution. In these systems, peers share their resources decreasing demand on the content distribution network infrastructure (CDN). On the other hand, the CDN s servers guarantee the availability of content when peers contributions are limited by churn. However, in these systems, the content distributed must be managed so that the CDN servers workload is minimized. An issue to be investigated is the impact of churn, i.e the effect of cycle of peers join and leave, on management policies. Carried studies showed that the performance of policies improves as the storage capacity of peers increases. However, this increasement does not impact proportionately the performance of policies. Later on, we proposed, implemented and evaluated four object management policies derived from data in YouTube video collections. These policies use information left by users or generated by the video distribution system to measure the value of objects. We found that the proposed policies were able to improve the availability of content in more than 70%, compared to the LFU policy, and more than 50% compared to GDSP policy. / A escalabilidade e a alta demanda por recursos s ao os principais desafios que os provedores de conte´udo enfrentam na viabiliza¸c ao de aplica¸c oes de v´ıdeos sob demanda (VoD). O site mais popular de compartilhamento de v´ıdeos, o YouTube, tem mais de 4 bilh oes de visualiza¸c oes por dia e 60 horas de v´ıdeo s ao armazenadas a cada minuto em seus servidores. Sistemas h´ıbridos (CDN-P2P) t em sido apresentado como uma solu¸c ao escal´avel para distribui¸c ao de VoD. Nesses sistemas, pares compartilham seus recursos diminuindo a demanda sobre a infraestrutura da rede de distribui¸c ao de conte´udo (CDN). Por outro lado, os servidores da CDN garantem a disponibilidade de conte´udo quando as contribui¸c oes dos pares s ao limitadas pelo churn, ou quando o conte´udo for in´edito aos pares da rede par a par (P2P). No entanto, o conte´udo distribu´ıdo nesses sistemas precisa ser gerenciado, de forma que a carga de trabalho submetida aos servidores da CDN seja minimizada. Uma quest ao a ser investigada nesse sistema ´e o impacto do churn, isto ´e, o efeito criado pelo ciclo de entrada e sa´ıda dos pares sobre os mecanismos de ger encia do conte´udo distribu´ıdo pelo sistema. Nesta disserta¸c ao avalia-se o impacto do churn no desempenho de pol´ıticas de gerenciamento de objetos em sistemas CDN-P2P; verificou-se que o impacto no desempenho das pol´ıticas diminui com o aumento da capacidade de armazenamento dos pares, no entanto, esse aumento n ao impacta proporcionalmente a performance das pol´ıticas. Em seguida, s ao propostas, implementadas e avaliadas quatro pol´ıticas de gerenciamento de objetos derivadas a partir de dados reais obtidos de cole¸c oes de v´ıdeos do YouTube. Essas pol´ıticas exploram informa¸c oes deixadas pelos usu´arios ou geradas pelo sistema de distribui¸c ao dos v´ıdeos para mensurar o valor de um objeto. A suposi¸c ao acerca da efetividade dessas informa¸c oes na valora¸c ao dos objetos ´e devido `a influ encia do sistema de recomenda¸c ao do YouTube no acesso a seu conte´udo, pois esse sistema utiliza-se dessas informa¸c oes para indicar v´ıdeos aos usu´arios. As pol´ıticas propostas foram capazes de melhorar a disponibilidade do conte´udo em mais de 70%, comparada `a disponibilidade proporcionada pela pol´ıtica LFU e mais de 50%, comparada `a pol´ıtica GDSP.