In recent years, adaptive HTTP streaming protocols have become the de facto standard in the industry for the distribution of live and video-on-demand content over the Internet. In this thesis, we solve the problem of distributing adaptive HTTP live video streams to a large number of viewers using peer-to-peer (P2P) overlays. We do so by assuming that our solution must deliver a level of quality of user experience which is the same as a CDN while trying to minimize the load on the content provider’s infrastructure. Besides that, in the design of our solution, we take into consideration the realities of the HTTP streaming protocols, such as the pull-based approach and adaptive bitrate switching. The result of this work is a system which we call SmoothCache that provides CDN-quality adaptive HTTP live streaming utilizing P2P algorithms. Our experiments on a real network of thousands of consumer machines show that, besides meeting the the CDN-quality constraints, SmoothCache is able to consistently deliver up to 96% savings towards the source of the stream in a single bitrate scenario and 94% in a multi-bitrate scenario. In addition, we have conducted a number of pilot deployments in the setting of large enterprises with the same system, albeit tailored to private networks. Results with thousands of real viewers show that our platform provides an average offloading of bottlenecks in the private network of 91.5%. These achievements were made possible by advancements in multiple research areas that are also presented in this thesis. Each one of the contributions is novel with respect to the state of the art and can be applied outside of the context of our application. However, in our system they serve the purposes described below. We built a component-based event-driven framework to facilitate the development of our live streaming application. The framework allows for running the same code both in simulation and in real deployment. In order to obtain scalability of simulations and accuracy, we designed a novel flow-based bandwidth emulation model. In order to deploy our application on real networks, we have developed a network library which has the novel feature of providing on-the-fly prioritization of transfers. The library is layered over the UDP protocol and supports NAT Traversal techniques. As part of this thesis, we have also improved on the state of the art of NAT Traversal techniques resulting in higher probability of direct connectivity between peers on the Internet. Because of the presence of NATs on the Internet, discovery of new peers and collection of statistics on the overlay through peer sampling is problematic. Therefore, we created a peer sampling service which is NAT-aware and provides one order of magnitude fresher samples than existing peer sampling protocols. Finally, we designed SmoothCache as a peer-assisted live streaming system based on a distributed caching abstraction. In SmoothCache, peers retrieve video fragments from the P2P overlay as quickly as possible or fall back to the source of the stream to keep the timeliness of the delivery. In order to produce savings, the caching system strives to fill up the local cache of the peers ahead of playback by prefetching content. Fragments are efficiently distributed by a self-organizing overlay network that takes into account many factors such as upload bandwidth capacity, connectivity constraints, performance history and the currently being watched bitrate. / <p>QC 20131122</p>

As aplicações de live streaming em redes P2P têm grande potencial de crescimento, em popularidade e qualidade, mas são potencialmente vulneráveis ao ataque de poluição de conteúdo. Tal ataque corresponde a qualquer adulteração de áudio e/ou vídeo na mídia transmitida buscando ludibriar espectadores. A autenticação de blocos do fluxo de dados contínuo (stream) permite a detecção de conteúdo poluído e a possível identificação de pares maliciosos na rede P2P. A literatura contém diversas propostas de autenticação baseadas em assinatura digital leve e em amortização de assinatura digital. O presente trabalho, como nenhum anterior, compara tanto os esquemas de assinatura leve quanto os de amortização sob diferentes perspectivas de qualidade de transmissão (vídeos convencionais e de alta definição) em redes P2P de live streaming através da formularização analítica dos mesmos. Para isto, é feita uma comparação quantitativa de sobrecargas e nível de segurança, observando fenômenos e identificando desafios de pesquisa que precisarão ser vencidos. Particularmente, para avaliar a viabilidade dos esquemas, foi definido um coeficiente que leva em consideração o tempo total de transmissão e o custo computacional proporcionado pelo esquema estudado. Como uma das conclusões inéditas dessa análise, o esquema PARM2 obteve o melhor desempenho dentre os esquemas leves de assinatura. Já em relação aos esquemas de amortização, o Linear Digests se sobressaiu entre os demais. Por fim, foi analisada uma solução baseada na amortização de um esquema de assinatura leve, algo também inédito. A partir dessa análise em particular, foi possível observar que a autenticação é viável apenas com baixos e médios níveis de segurança em transmissões convencionais. Além disso, a partir dos resultados foi possível observar que o esquema de amortização Linear Digests deve ser utilizado isoladamente apenas em transmissões convencionais. Por fim, o esquema PARM2, se utilizado individualmente, não apresenta valores de coeficiente aceitáveis para os cenários estudados. / P2P live streaming applications have great potential for improvements in terms of popularity as well as quality. However, they are subject to pollution attacks, in which a malicious user tampers with audio/video of streams in order to trick other users. The authentication of blocks in a stream allows the detection of pollution in received content and can lead to the identification of malicious users. The literature includes several proposals of light digital signature schemes and amortization schemes. Our work, unlike previous ones, compares both amortization schemes and light signature schemes under di erent perspectives of transmission quality (convencional and high definition videos) in P2P live streaming by formulating equations for them. For such, it quantitatively compares overheads and security levels during P2P streaming sessions, identifying research challenges to be faced. In particular, to assess the viability of such schemes, we defined a coe cient that takes into account the total transmission time and computational cost provided by such scheme. As one of the novel findings of our analysis, the scheme PARM2 showed the best performance among light signature schemes. With respect to amortization, Linear Digests was the most e cient. Finally, we analyzed a solution based on the amortization of a light signature. From this particular analysis, we observed that the authentication is only feasible in conventional transmissions with low and medium security leves. In addition, the amortization scheme Linear Digests must be used in isolation only in conventional transmissions. Finally, the scheme PARM2, if used alone, has no acceptable coe cient values for the studied scenarios.

As aplicações de live streaming em redes P2P têm grande potencial de crescimento, em popularidade e qualidade, mas são potencialmente vulneráveis ao ataque de poluição de conteúdo. Tal ataque corresponde a qualquer adulteração de áudio e/ou vídeo na mídia transmitida buscando ludibriar espectadores. A autenticação de blocos do fluxo de dados contínuo (stream) permite a detecção de conteúdo poluído e a possível identificação de pares maliciosos na rede P2P. A literatura contém diversas propostas de autenticação baseadas em assinatura digital leve e em amortização de assinatura digital. O presente trabalho, como nenhum anterior, compara tanto os esquemas de assinatura leve quanto os de amortização sob diferentes perspectivas de qualidade de transmissão (vídeos convencionais e de alta definição) em redes P2P de live streaming através da formularização analítica dos mesmos. Para isto, é feita uma comparação quantitativa de sobrecargas e nível de segurança, observando fenômenos e identificando desafios de pesquisa que precisarão ser vencidos. Particularmente, para avaliar a viabilidade dos esquemas, foi definido um coeficiente que leva em consideração o tempo total de transmissão e o custo computacional proporcionado pelo esquema estudado. Como uma das conclusões inéditas dessa análise, o esquema PARM2 obteve o melhor desempenho dentre os esquemas leves de assinatura. Já em relação aos esquemas de amortização, o Linear Digests se sobressaiu entre os demais. Por fim, foi analisada uma solução baseada na amortização de um esquema de assinatura leve, algo também inédito. A partir dessa análise em particular, foi possível observar que a autenticação é viável apenas com baixos e médios níveis de segurança em transmissões convencionais. Além disso, a partir dos resultados foi possível observar que o esquema de amortização Linear Digests deve ser utilizado isoladamente apenas em transmissões convencionais. Por fim, o esquema PARM2, se utilizado individualmente, não apresenta valores de coeficiente aceitáveis para os cenários estudados. / P2P live streaming applications have great potential for improvements in terms of popularity as well as quality. However, they are subject to pollution attacks, in which a malicious user tampers with audio/video of streams in order to trick other users. The authentication of blocks in a stream allows the detection of pollution in received content and can lead to the identification of malicious users. The literature includes several proposals of light digital signature schemes and amortization schemes. Our work, unlike previous ones, compares both amortization schemes and light signature schemes under di erent perspectives of transmission quality (convencional and high definition videos) in P2P live streaming by formulating equations for them. For such, it quantitatively compares overheads and security levels during P2P streaming sessions, identifying research challenges to be faced. In particular, to assess the viability of such schemes, we defined a coe cient that takes into account the total transmission time and computational cost provided by such scheme. As one of the novel findings of our analysis, the scheme PARM2 showed the best performance among light signature schemes. With respect to amortization, Linear Digests was the most e cient. Finally, we analyzed a solution based on the amortization of a light signature. From this particular analysis, we observed that the authentication is only feasible in conventional transmissions with low and medium security leves. In addition, the amortization scheme Linear Digests must be used in isolation only in conventional transmissions. Finally, the scheme PARM2, if used alone, has no acceptable coe cient values for the studied scenarios.

As aplicações de live streaming em redes P2P têm grande potencial de crescimento, em popularidade e qualidade, mas são potencialmente vulneráveis ao ataque de poluição de conteúdo. Tal ataque corresponde a qualquer adulteração de áudio e/ou vídeo na mídia transmitida buscando ludibriar espectadores. A autenticação de blocos do fluxo de dados contínuo (stream) permite a detecção de conteúdo poluído e a possível identificação de pares maliciosos na rede P2P. A literatura contém diversas propostas de autenticação baseadas em assinatura digital leve e em amortização de assinatura digital. O presente trabalho, como nenhum anterior, compara tanto os esquemas de assinatura leve quanto os de amortização sob diferentes perspectivas de qualidade de transmissão (vídeos convencionais e de alta definição) em redes P2P de live streaming através da formularização analítica dos mesmos. Para isto, é feita uma comparação quantitativa de sobrecargas e nível de segurança, observando fenômenos e identificando desafios de pesquisa que precisarão ser vencidos. Particularmente, para avaliar a viabilidade dos esquemas, foi definido um coeficiente que leva em consideração o tempo total de transmissão e o custo computacional proporcionado pelo esquema estudado. Como uma das conclusões inéditas dessa análise, o esquema PARM2 obteve o melhor desempenho dentre os esquemas leves de assinatura. Já em relação aos esquemas de amortização, o Linear Digests se sobressaiu entre os demais. Por fim, foi analisada uma solução baseada na amortização de um esquema de assinatura leve, algo também inédito. A partir dessa análise em particular, foi possível observar que a autenticação é viável apenas com baixos e médios níveis de segurança em transmissões convencionais. Além disso, a partir dos resultados foi possível observar que o esquema de amortização Linear Digests deve ser utilizado isoladamente apenas em transmissões convencionais. Por fim, o esquema PARM2, se utilizado individualmente, não apresenta valores de coeficiente aceitáveis para os cenários estudados. / P2P live streaming applications have great potential for improvements in terms of popularity as well as quality. However, they are subject to pollution attacks, in which a malicious user tampers with audio/video of streams in order to trick other users. The authentication of blocks in a stream allows the detection of pollution in received content and can lead to the identification of malicious users. The literature includes several proposals of light digital signature schemes and amortization schemes. Our work, unlike previous ones, compares both amortization schemes and light signature schemes under di erent perspectives of transmission quality (convencional and high definition videos) in P2P live streaming by formulating equations for them. For such, it quantitatively compares overheads and security levels during P2P streaming sessions, identifying research challenges to be faced. In particular, to assess the viability of such schemes, we defined a coe cient that takes into account the total transmission time and computational cost provided by such scheme. As one of the novel findings of our analysis, the scheme PARM2 showed the best performance among light signature schemes. With respect to amortization, Linear Digests was the most e cient. Finally, we analyzed a solution based on the amortization of a light signature. From this particular analysis, we observed that the authentication is only feasible in conventional transmissions with low and medium security leves. In addition, the amortization scheme Linear Digests must be used in isolation only in conventional transmissions. Finally, the scheme PARM2, if used alone, has no acceptable coe cient values for the studied scenarios.

Little is known about ‘uninformative live-streaming’, a new genre of online streaming media that has become a new trend in China. In these real-time streams, streamers would not interact and communicate with viewers and not perform in front of cameras. The content is about uninterrupted trivial everyday activities, such as sleeping and studying for several hours. This thesis aims to obtain a comprehensive understanding of this media and to explore what motivates users to continuously watch it. This research employed qualitative methods of online observation and semi-structured in-depth interviews to collect empirical data, through the cases of study-stream and sleep-stream. The concept of media life by Mark Deuze provides a general theoretical context of mediatized lifeworld. Based on Uses and Gratifications Theory and Compensatory Internet Use Theory, I described and explained the prominent features of uninformative live-streaming and examined the user motivation for it. The research results show that this authentic, less-interactive, and non-narrative live-streaming creates an undisturbed media environment, in which users can escape media distraction and media overload. The prominent user motivations for uninformative live streams are self-discipline and self-management, and compensation for the real-life deficiency of ‘non-social companion’. These findings offer new insight into user motivation and help to expand and improve related theories.

Through the past decade live streaming has grown to be a greater sensation, creating a competitive scene among those involved. Live streamers are able to broadcast their daily life or their gameplay sessions while also interacting with viewers. As this is a relatively new phenomenon it has not yet been fully explored, and it is missing critical research in how attitudes and purchase intention among viewers change with different factors. Previous research has shown that elements such as demographics, content consumption and behavioral aspects might increase viewers’ purchase intention. Furthermore, in accordance with attitudinal theory, attitudes have been shown to correlate with the general purchase intention,  when it comes to Internet users. This study was therefore conducted to fill the gap in knowledge regarding personal branding on Twitch.tv, or Twitch in short, and how it affects attitudes with its subsequent purchase intention.   This research adopted an exploratory approach as it aimed to “explore the unknown” and to provide pertinent data for future studies. This was realized via a qualitative method of semi-structured one-to-one interviews involving both streamers and viewers. Findings show that two aspects of personal branding on Twitch have a greater potential of affecting attitudes; namely personalities of a streamer and the type of content they provide. If these two are managed well there are implications of positive attitudes among the viewers and subsequently an intention to purchase.

Video delivery over the Internet is becoming increasingly popular and comes in many flavors, such as Live Streaming and Video-on-Demand. In the recent years, many peer to peer solutions for Live Streaming and VoD have been proposed as opposed to the centralized solutions that are not scalable due to the high bandwidth requirements. In all existing solutions, Live Streaming and VoD have traditionally and artificially been considered as separate technical problems. We propose an integrated Live Streaming with VoD system that offers the potential for users to watch live TV with short delays. In Live Streaming, peers are interested in the content that is being generated live by the streaming source, unlike VoD in which peers are interested in the content that has been generated from the beginning of the streaming. In this manner, Live nodes can contribute to VoD nodes and send them the pieces they have downloaded since their joining time. In this work, we demonstrate that our system, called Live-VoD, brings out the possibility of having both types of nodes in one system, each being served based on their interest. We propose a P2P Live-VoD protocol for overlay construction based on peer’s upload bandwidth that is built on top of the Gradient topology and an innovative algorithm based on the number of pieces peers can contribute to each other. We also propose an innovative stochastic algorithm for data dissemination based on the rareness of the piece and the requesting node’s download position. Our experiments show that Live-VoD is decentralized, scalable and self-organizing. We also show that even when most of the nodes in the system are VoDs, all VoD nodes regardless of their joining time, manage to download the whole movie with no assistance from the streaming source.

Background: With the rapid development of information technology, social media and e-commerce platforms have become increasingly popular among consumers. Live streaming e-commerce is a new shopping pattern that has emerged in the process of development. With the help of short videos and live broadcast platforms, the popularity of live streaming e-commerce has significantly increased in the Chinese market. Outside of China, this shopping pattern is also gaining traction. However, due to the differences in markets and consumers among different countries, it is also necessary to understand the factors that affect consumers' cognitive perceptions of live streaming e-commerce. Purpose:  This study aims to find differences in consumers' perceptions of live streaming e-commerce between Chinese and Swedish consumers and investigate the factors influencing consumers' perceived attitudes towards live streaming e-commerce. Method:  Quantitative data was collected in the Swedish and Chinese markets through online questionnaires to achieve the research purpose. The researchers used convenience sampling and snowball sampling techniques to ensure that sufficient responses were collected. Aside from demographic sections and filter questions about the user experience of live streaming e-commerce, the remaining seven dimensions of the questionnaire assessed the cognitive perceptions of consumers based on two well-established models: The S-O-R Paradigm and IS success model. Conclusion:  Based on the results of this study, there are differences between online consumers in Sweden and China regarding live streaming e-commerce. Chinese respondents were generally more favorable and consistent in their views regarding user satisfaction, perceived attitudes, and intention to purchase. In contrast, respondents in Sweden considered the qualities of system, information, and service more positively. Additionally, consumers' perceived attitudes toward live streaming e-commerce were most strongly predicted by service quality, followed by system quality. Moreover, there is a favorable correlation between information quality and user satisfaction, which adds to the individual organism linkage's perceived attitude. A positive relationship is also founded between system quality and perceived attitudes. Furthermore, user satisfaction is the determining factor of perceived attitude. Perceived attitude is a more decisive factor than user satisfaction which positively influences the intention to purchase in the consumers' response. The findings of this research provided wide-ranging theoretical and managerial implications and developed possible opportunities for future research.

The music business is one of the industries most affected by digitalization of content and distribution channels. As industry revenue shifted from principally physical to digital channels in 2015, while being the business with the largest presence and most popular accounts in virtually all social media platforms - the current state of the music industry is change. This has led industry professionals into searching for new and innovating ways of reimagining the business model of music distribution. Thus, the purpose of this study is to investigate the potential of video live-streaming as an addition to the current social media channels used to market artists. This was done through looking into what industry professionals think of the subject in terms of strategic reasoning and potential, observing an interactive live-stream with a Swedish boy band, and a questionnaire directed towards end-users and listeners of Swedish popular artists to define what their stance is towards music-related social media in general, and live-streaming in particular. The findings show that live-streaming certainly has a gap to fill in the social media tool-box at music companies through facilitating the defining process of superfans based on data analysis gathered from live-stream consumers, and that the channel has potential to create engagement beyond that of other social media platforms. Furthermore, end-users want to consume more live-stream content from Swedish artists. They want content that feels more personal and revealing, while utilizing the abstract feeling of “here and now” in order for it to be more interesting than other content on social media - something that the music industry professionals agree is important in live-streamed music content. / Musikbranschen är en av de branscher där digitaliseringen av innehålls- och distributionskanaler haft störst påverkan. Industrins inkomst skiftar från att huvudsakligen komma från fysiska till digitala kanaler samtidigt som musikbranschen har den största närvaron och de mest populära kontona i praktiskt taget alla sociala medier - musikindustrins nuvarande tillstånd är förändring. Detta har lett branschfolk in i letandet efter nya och innovativa sätt att återuppfinna affärsmodellen för musikdistribution. Således är syftet med denna studie att undersöka potentialen för video live-streaming som ett tillägg till de nuvarande sociala media-plattformar som används för att marknadsföra artister. Detta gjordes genom att titta på vad branschfolk tycker om ämnet vad gäller strategiska resonemang och potential, observera en interaktiv live-stream med ett svenskt pojkband, samt en enkät riktad till användare och lyssnare av svenska populära artister för att definiera vad deras inställning är till musikrelaterat innehåll i sociala medier i allmänhet, och live-streaming i synnerhet. Resultaten visar att live-streaming har en lucka att fylla i musikföretagens sociala medier-verktygslåda genom att underlätta definitionsprocessen av superfans baserat på dataanalys som samlats in från lives-streams, och att kanalen har potential att skapa engagemang utöver det som genereras av andra sociala medierna. Dessutom vill användare konsumera mer live-stream-innehåll från svenska artister. De vill ha innehåll som känns mer personligt och avslöjande, samtidigt som man utnyttjar den abstrakta känsla av "här och nu" för att det ska vara mer intressant än annat innehåll på sociala medier - något som musikindustrins yrkesverksamma också tycker är viktigt i live-streamat musikinnehåll.

The various capabilities provided by the Internet have attracted a large amount of Internet-based applications over the last decades. Many services that previously only used other means of communication are now also deployed on the Internet. As the content in the communication becomes richer, the bandwidth required to communicate it increases. In the case of delivering audiovisual content over the Internet, a significant amount of bandwidth is required to send the content to a single recipient, and increases rapidly for each additional recipient. To be able to provide scalable, Internet-based systems for video content delivery, researchers and companies have begun to focus on peer-to-peer-based approaches, meaning participants collaborating and contributing their bandwidth to assure content delivery to all others. This thesis proposes a design for a peer-to-peer system for delivery of live video, and provides simulation results for an implementation of the design. The design targets some of the current issues of peer-to-peer systems – mainly that of providing friendliness towards Internet Service Providers (ISPs). Peer-to-peer systems generate considerable amounts of traffic, which is often sent between peers located in different ISPs, even when data is available at a peer in the same ISP as the recipient. This creates problems for ISPs as they often have to pay other ISPs for data sent over cross-ISP connections, and because congestion can occur in the ISPs gateways to the rest of the Internet – the problems increasing with the number of ISPs that the traffic has to go through. This has forced some ISPs to limit or block peer-to-peer traffic completely. The system designed in this thesis uses a gossip-based peer-to-peer protocol for content dissemination, and to minimize cross-ISP traffic, the thesis proposes that peers should choose peers closer in the network topology to connect to. This can be achieved by creating a database composed of ISPs and the distance between them, which is consulted every time a new connection is to be created. The database is small enough to be stored locally at each peer. As long as a peer is able to deliver a clear stream it will only connect to close peers, however should the close peers not be able to provide data at a sufficient rate, the peer will request random peers in the system to also provide it with data. Evaluation of the system in various simulation scenarios shows that it operates well in a constrained environment as well as during peer failures. The evaluation also shows that it is possible to have high clustering of peers and still deliver a clear stream to all of them, as long as a few random connections are allowed to be created when close neighbors can’t provide a suffi cient download rate. Comparing the use of biased neighbor selection to random selection, traffic between ISPs is efficiently reduced in the overall system, the portion of traffic exchanged between peers in the same ISP experience a ten times increase or more in most scenarios, and in larger ISPs that contain many peers, 75% of all traffic is exchanged between peers within the ISP. Thus the design presented in this thesis can be recommended to developers and content providers that are looking to increase ISP friendliness in their existing or future peer-to-peer applications. / De många möjligheter som Internet medför har gett upphov till ett stort antal Internet-baserade tjänster de senaste decennierna. Flertalet tjänster som tidigare endast fanns tillgängliga via andra kommunikationskanaler är numera också möjliga att nå via Internet. I och med att informationen som skall skickas via olika tjänster ökar så ökar också kraven på bandbredd, och för att kunna leverera video krävs en ansenlig bandbredd. Bandbredden som krävs av den som levererar videon ökar dessutom snabbt i takt med antalet mottagare av den. För att kunna skapa Internet-baserade tjänster för video som tillåter ett större antal användare har forskare och företag börjat använda peer- to-peer-baserade lösningar, där användarna av tjänsten samarbetar och bidrar med deras egen bandbredd för att göra det möjligt för samtliga användare att ta emot videon. Detta arbete beskriver hur ett peer-to-peer-system för live-video kan utformas, och tillhandahåller resultat från simulationer med en implementation av systemet. Det huvudsakliga målet med systemets design är att minska bördan som peer-to-peer-system vanligen utgör för internetleverantörer. Denna typ av system genererar ofta stora mängder data, som i de flesta fall skickas mellan användare som befinner sig i nätverk tillhörande olika internetleverantörer, trots att samma data ofta finns tillgänglig på närmare håll – det vill säga hos användare som tillhör samma internetleverantör som mottagaren. Detta är ett problem för internetleverantörerna eftersom de ofta behöver betala för trafik som lämnar eller går till deras nätverk. Utöver detta så kan de anslutningar som existerar mellan dessa nätverk inte alltid klara sådana mängder trafik, vilket gör att alla användare av de anslutningarna blir lidande. Detta har lett till att vissa internetleverantörer begränsar eller inte tillåter peer-to-peer-trafik överhuvudtaget. Systemet som utformats i detta arbete bygger på gossiping (ryktesspridning) för att förse användare med videoströmmen. För att minimera mängden trafik som skickas mellan användare hos olika internetleverantörer så jämför användarna avståndet i nätverkstopologin till andra användare och skapar bara anslutningar till de som befinner sig närmast. Avståndet mellan två internetleverantörer utgörs av antalet anslutningar mellan två internetleverantörers nätverk som måste passeras på vägen. Dessa avstånd är lagrade i en databas som finns lokalt hos varje användare. Så länge en användare kan se en videoström utan störningar så laddas den endast ner från närbelägna användare, men skulle dessa inte kunna tillgodose användaren med tillräcklig datahastighet så kommer andra, slumpmässigt utvalda, också att kontaktas för att bidra med delar av videoströmmen till denna användare. I den utvärdering av systemet som gjorts så har det visat sig fungera väl när tillgängliga resurser som bandbredd och tillförlitligheten i det fysiska nätverket är begränsade, samt under svåra förhållanden som när en stor del av användarna lämnar systemet samtidigt. Utvärderingen visar också att användarupplevelsen inte påverkas av förändringen som det innebär att föredra kommunikation med närbelägna användare, så länge några få slumpmässiga anslutningar är tillåtna i de fall då användare i närheten inte kan tillhandahålla tillräcklig datahastighet. Jämfört med att välja alla kommunikationspartners slumpmässigt så minskar tillvägagångssättet i detta arbete effektivt trafiken mellan olika internetleverantörer både sett till hela systemet och i enskilda nätverk—andelen trafik som utbyts mellan användare tillhörande samma internetleverantör blir i de flesta fall tio gånger större—och i stora nätverk som innehåller många användare så utgör trafik mellan dess användare 75 % av all systemets trafik i detta nätverk. Den design som utformats i detta arbete kan därför rekommenderas till utvecklare och tillhandahållare av både existerande och framtida tjänster som använder peer-to-peer-teknik, och som är intresserade av att minska belastningen som deras system utgör för internetleverantörer.