In this thesis, we propose a decentralized peer-to-peer (P2P) Web proxy cache for enterprise networks (ENs). Currently, enterprises use a centralized proxy-based Web cache, where a dedicated proxy server does the caching. A dedicated proxy Web Cache has to be over-provisioned to handle peak loads. It is expensive, a single point of failure, and a bottleneck. In a P2P Web Cache, the clients themselves cooperate in caching the Web objects without any dedicated proxy cache. The resources from the client machines are pooled together to form a Web cache. This eliminates the need for extra hardware and the single point of failure, and improves the average response time, since all the machines serve the request queue. The most important attraction for the P2P scheme is its inherent scalability. Squirrel was the earliest P2P Web cache. Squirrel is built upon a structured P2P protocol called Pastry. Pastry is based on consistent hashing; a special hashing that performs well in the presence of client membership changes. Consistent hashing based protocols are designed for Internet-wide environments to handle very large membership sizes and high rates of membership change. To minimize the protocol bandwidth, the membership state maintained at each peer is very small. This state consists of the information about the peer’s immediate neighbours, and those of a few other P2P members, to achieve faster look-up. This scheme has the following advantages: (i) since peers do not maintain information about all the other peers in the system, any peer needing an object has to find the peer responsible for the object through a multi-hop lookup, thereby increasing the latency, and (ii) the number of objIds assigned to a peer depends on the hashing used, and this can be skewed, which affects the load distribution. The popular applications of the P2P paradigm have been file-sharing systems. These systems are deployed across the Internet. Hence, the existing P2P protocols were designed to operate within the constraints of Internet environments. The P2P proxy Web cache has been a recent application of the P2P paradigm. P2P Web Proxy caches operate across the entire network of an enterprise. An enterprise network(EN) comprises all the computing and communications capabilities of an institution. Institutions typically consist of many departments, with each department having and managing its own local area netwok (LAN). The available bandwidth in LANs is very high. LANs have low latency and low error rates. EN environments have smaller membership size, less frequent membership changes and more available bandwidth. Hence, in such environments, the P2P protocol can afford to store more membership information. This thesis explores the significant differences between EN and Internet environments. It proposes a new P2P protocol designed to exploit these differences, and a P2P Web proxy caching scheme based on this new protocol. Specifically, it shows that it is possible to maintain complete the consistent membership information on ENs. The thesis then presents a load distribution policy for a P2P system with complete and consistent membership information to achieve (i) load balance and (ii) minimum object migrations subsequent to each node join or node leave event. The proposed system requires extra storage and bandwidth costs. We have seen that the necessary storage is available in general workstations and the required bandwidth is feasible in modern networks. We then evaluated the improvement in performance achieved by the system over existing consistent hashing based systems. We have shown that without investing in any special hardware, the P2P system can match the performance of dedicated proxy caches. We have further shown that the buddy based P2P scheme has a better load distribution, especially under heavy loads when load balancing becomes critical. We have also shown that for large P2P systems, the buddy based scheme has a lower latency than the consistent hashing based schemes. Further, we have compared the costs of the proposed scheme and the existing consistent hashing based scheme for different loads (i.e., rate of Web object requests), and identified the situations in which the proposed scheme is likely to perform best. In summary, the thesis shows that (i) the membership dynamics of P2P systems on ENs are different from that of Internet file-sharing systems and (ii) it is feasible in ENs, to maintain complete the consistent view of the P2P membership at all the peers. We have designed a structured P2P protocol for LANs that maintains a complete and consistent view of membership information at all peers. P2P Web caches achieve single hop routing and a better balanced load distribution using this scheme. Complete and consistent view of membership information enabled a single-hop lookup and a flexible load assignment.

Video conferencing has been a part of many communication platforms over the years. Over the last decades users have moved from dedicated telephony networks to the Internet, and recently to the Web. With the introduction of Web Real-Time Communication (WebRTC) it is now possible to make voice- and video calls simply by visiting a web page, without having to install any additional software. Services that enable multi-user conferences are quite common. However existing solutions such as the Multipoint Control Unit (MCU) inherently do not scale and can be a single point of failure, due to its centralized architecture. This can lead to high maintenance costs and poor service availability.To solve the scalability- and availability problems of video-conferencing services, a decentralized alternative to the MCU is proposed. A decentralized conferencing system uses the distributed resources of its users instead of relying on a central server. This means that the system can handle an increasing number of users without having to upgrade any server infrastructure. Additionally, failures are only partial and can happen regularly without affecting the rest of the system. This report presents the development of a protocol built on top of WebRTC that enables completely decentralized multi-user conferencing. It includes a distributed algorithm for voice-activated switching to reduce the computation and network resources used. A load-balancing technique based on media stream relays is used to distribute the resource requirements of the conference participants. The protocol is implemented as a Javascript library that can be included in a web application. A proof-of-concept web application is developed using the library and its performance is evaluated. The performance data is analyzed and the results are used to make incremental improvements to the protocol and implementation. Although not all features of the protocol are implemented, the tests show promising results. The application allows multiple users to participate in high-definition video conferences, with no server infrastructure aside from a Mini PC that hosts a web server and a WebRTC signaling server. / Videokonferenser har varit en del av många olika kommunikationsplattformar genom åren. Tekniken har yttats från dedikerade telefonnnät,, till Internet, och på senare tid till webben. I och med introduktionen av WebRTC (Web Real-Time Communication) är deti dag möjligt att enkelt deltaga i röst- och videosamtal genom att gå till en webbsida utan att behöva installera någon programvara annat an en webbläsare. De flesta existerande konferenstjänster är byggda med en centraliserad arkitektur, vilket kan leda till tekniska problem när antalet användare ökar eller när fel uppstår i systemens centrala servrar. Dessa problem kan leda till driftstopp och skada tjänstens tillgänglighet för användarna. Den här rapporten täcker utvecklingen av ett protokoll som tillsammans med WebRTC kan användas för att bygga en helt decentraliserad konferenstjänst. Målet är att tjänsten ska vara oberoende av centrala servrar, och på så vis lösa problemen med skalbarhet och tillgänglighet. Protokollet implementeras i en webbapplikation som testas och utvärderasöver flera iterationer för att hitta nya förbättringar. Testerna visar lovande resultat. Slutsatsen dras det är fullt möjligt att bygga en konferenstjänst på detta sätt, och möjligheter för framtida optimeringar och testfall föreslås.

Dans cette thèse, nous nous sommes intéressés aux protocoles pair-à-pair (P2P), qui représentent une solution prometteuse pour la diffusion et le partage de données à faible coût sur Internet. Nous avons mené, dans un premier temps, une étude comportementale de différents protocoles P2P pour le partage de fichier (distribution de contenus sans contrainte de temps) puis le live. Dans la première étude centréesur le partage de fichier, nous avons montré l’impact d’Hadopi sur le comportement des utilisateurs et discuté l’efficacité des protocoles en fonction du contenu et l’efficacité protocolaire, en se basant sur les choix des utilisateurs. BitTorrent s’est nettement démarqué au cours de cette étude, notamment pour les grands contenus. En ce qui concerne le live, nous nous sommes intéressés à la qualité de servicedu réseau de distribution live Sopcast, car plus de 60% des événements live diffusés en P2P le sont sur ce réseau. Notre analyse approfondie de ces deux modes de distribution nous a fait nous recentrer sur BitTorrent, qui est à la base de tous les protocoles P2P Live, et est efficace en partage de fichier et complètement open source. Dans la seconde partie de la thèse, nous avons proposé et implémenté dansun environnement contrôlé un nouveau protocole sur la base de BitTorrent avec des mécanismes protocolaires impliquant tous les pairs dans la gestion du réseau. Ces nouveaux mécanismes permettent d’augmenter l’efficacité du protocole via une meilleure diffusion, tant pour le live que le partage de fichier, de métadonnées (la pièce la plus rare) et via une méthode dite de push, par laquelle un client va envoyer du contenu aux pairs les plus dans le besoin / In this study, we focused on peer-to-peer protocols (P2P), which represent a promising solution for data dissemination and content delivery at low-cost in the Internet. We performed, initially, a behavioral study of various P2P protocols for file sharing (content distribution without time constraint) and live streaming. Concerning file sharing, we have shown the impact of Hadopi on users’ behavior and discussed the effectiveness of protocols according to content type, based on users’ choice. BitTorrent appeared as the most efficient approach during our study, especially when it comes to large content. As for streaming, we studied the quality of service of Sopcast, a live distribution network that accounts for more than 60% of P2P broadcast live events. Our in-depth analysis of these two distributionmodes led us to focus on the BitTorrent protocol because of its proven efficiency in file sharing and the fact that it is open source. In the second part of the thesis, we proposed and implemented a new protocol based on BitTorrent, in a controlled environment. The modifications that we proposed allow to increase the efficiency of the protocol through improved dissemination of metadata (the rarest piece), both for live and file sharing. An enhanced version is introduced with a push method, where nodes that lag behind receive an extra service so as to improve the overall performance