Network infrastructures often need to stage content so that it is accessible to consumers. The standard solution, deploying the content on a centralised server, can be inadequate in several situations. Our thesis is that information encoded in social networks can be used to tailor content staging decisions to the user base and thereby build better data delivery infrastructures. This claim is supported by two case studies, which apply social information in challenging situations where traditional content staging is infeasible. Our approach works by examining empirical traces to identify relevant social properties, and then exploits them. The first study looks at cost-effectively serving the ``Long Tail'' of rich-media user-generated content, which need to be staged close to viewers to control latency and jitter. Our traces show that a preference for the unpopular tail items often spreads virally and is localised to some part of the social network. Exploiting this, we propose Buzztraq, which decreases replication costs by selectively copying items to locations favoured by viral spread. We also design SpinThrift, which separates popular and unpopular content based on the relative proportion of viral accesses, and opportunistically spins down disks containing unpopular content, thereby saving energy. The second study examines whether human face-to-face contacts can efficiently create paths over time between arbitrary users. Here, content is staged by spreading it through intermediate users until the destination is reached. Flooding every node minimises delivery times but is not scalable. We show that the human contact network is resilient to individual path failures, and for unicast paths, can efficiently approximate flooding in delivery time distribution simply by randomly sampling a handful of paths found by it. Multicast by contained flooding within a community is also efficient. However, connectivity relies on rare contacts and frequent contacts are often not useful for data delivery. Also, periods of similar duration could achieve different levels of connectivity; we devise a test to identify good periods. We finish by discussing how these properties influence routing algorithms.

Made available in DSpace on 2015-04-11T14:03:00Z (GMT). No. of bitstreams: 1 Polianny Almeida Lima.pdf: 1135711 bytes, checksum: 18018c30e2dd4e938af7eadcae042cbe (MD5) Previous issue date: 2013-03-27 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Standard networking technologies are based on typical assumptions such as the existence of connectivity end-to-end between source and destination for the entire period of communication, low error rates, retransmission mechanisms to repair errors, and relatively small communication delays. If one or more of these assumptions are not achieved in practice, blinks occur in communication, creating challenges that must be overcome to ensure the successful transmission. In this context, came the delay-tolerant networks and disconnection (DTN - Delay Tolerant Networks), an emerging technology for communications when there is no network infrastructure and disconnections may occur frequently due to the mobility of nodes. To bypass the problem of disconnections, DTN networks use the concept of persistent storage, which becomes a problem because the nodes have limited capacity of the buffers. The question is how to select the messages that remain in buffers longer considering the unpredictable mobility of nodes, short contacts between pairs of nodes, storage nodes achieved by finite and so on. This paper proposes a buffer management that transmits messages adaptively based on entropy variation of mobility network. / Tecnologias de redes tradicionais baseiam-se em suposições típicas, como a existência de conectividade fim a fim entre origem e destino durante todo o período de comunicação, baixas taxas de erros, mecanismos de retransmissão para reparar erros, e atrasos de comunicação relativamente pequenos. Caso uma ou mais dessas suposições não sejam alcançadas na prática, ocorrem intermitências na comunicação, criando desafios que devem ser superados a fim de garantir o sucesso na transmissão. Nesse contexto, surgiram as redes tolerantes a atraso e desconexão (DTN - Delay Tolerant Networks), uma tecnologia emergente para comunicações quando não há infraestrutura de rede e desconexões podem ocorrer com frequência devido à mobilidade dos nodos. Para contornar o problema das desconexões, as redes DTN utilizam o conceito de armazenamento persistente, o que se torna um problema, pois os nodos tem capacidade de buffers limitada. A questão é selecionar as mensagens que ficarão nos buffers por mais tempo levando em consideração a mobilidade imprevisível dos nodos, contatos de curta duração entre pares de nodos, armazenamento finito realizado pelos nodos e assim por diante. Este trabalho apresenta uma proposta de gerenciamento de buffer que transmite mensagens de forma adaptativa baseada na variação de entropia de mobilidade da rede.