Inter-swarm resource allocation in BitTorrent communities

CoShare: A Cost-Effective Data Sharing System for Data Center Networks

“…As for data sharing in P2P networks, most of the works focus on maximizing the throughput [20], [21], [4] using the BitTorrent protocol. Capota et al [20] formulated a maximum flow optimization problem while [21] improved neighbor selection based on traffic locality. Peterson et al [4] presented the response curve of P2P swarm, which represents the swarm bandwidth as a function of seeder bandwidth.…”

Slowing down to speed up: Protecting users against massive attacks in content distribution systems

“…They typically form random or small-world topologies to enable fast and robust communication (AL-HAMRA; LEGOUT; BARAKAT, 2007;DALE et al, 2008;FAUZIE et al, 2011;KRYCZKA et al, 2011). Since peers need to share chunks, the more neighbors and potential interesting peers they have, the faster the downloads can be (CAPOTA et al, 2011).…”

“…Ao invés de manter entidades centralizadoras para distribuir conteúdos, sistemas P2P são criados para que peers interajam para compartilhar dados e maximizar a utilização dos seus recursos. Nesse contexto, a popularização das arquiteturas P2P motivou a comunidade científica a investigar alguns aspectos de pesquisa desafiadores, e.g., otimização de topologias de redes (CHOFFNES; BUSTAMANTE, 2008;SÁNCHEZ;BUSTAMANTE, 2010;POESE et al, 2010;CAPOTA et al, 2011), mecanismos de inicialização de sistemas (TADDIA; MAZZINI, 2008) e serviços de descoberta de recursos (IAMNITCHI; FOSTER, 2001). Um desafio com interesse especial a esta tese diz respeito a mecanismos para conciliar a preferência dos usuários aos conteúdos publicados.…”

“…Instead of maintaining central entities to distribute content, P2P systems are designed so as peers can interact to share data and maximize their download bandwidth usage. The adoption of P2P architectures, in the context of CDS, has attracted attention from the scientific community to some interesting challenges, namely network topology optimization (CHOFFNES; BUSTAMANTE, 2008;SÁNCHEZ;BUSTAMANTE, 2010;POESE et al, 2010;CAPOTA et al, 2011), bootstrap mechanisms (TADDIA; MAZZINI, 2008), and service discovery (IAMNITCHI;FOSTER, 2001). One particular interesting challenge, in the context of this thesis, refers to mechanisms employed to match user's interests and published contents.…”

A matematikai modellezés hatása nemlineáris optimalizálási feladatok megoldásának hatékonyságára

“…Ez a tény motiválta a rajközi erőforrás-kiosztás problé-májának (inter-swarm resource allocation problem, RAP) vizsgálatát a BitTorrentben. Ez általában egy vegyes-egészértékű nemlineáris optimalizálási feladat [13], speciális esete a max-min méltányos sávszélesség-kiosztás problémája. Ebben az optimalizálási feladatban a cél alapvetően egy olyan sávszélesség-kiosztás megtalálása, ami a lehető legtöbb felhasználónak elégséges letöltési sebességet biztosít.…”