The explosive growth of the Internet is a major driver of the telecommunications market today. In future years, the number of online users will exhibit strong growth in every geographic region. In addition to a larger number of Internet users, the amount of content as well as the richness of the content are rapidly increasing. Users around the world are also beginning to have broadband access services. Higher access rates to the Internet allow users to view more and richer content and exacerbate the congestion problems in the network. There is, therefore, a strong need for scalable and efficient content distribution schemes. The research conducted in this thesis focuses on the study, design, and evaluation of different content distribution approaches, paying special attention to scalability issues. The solutions considered include caching, replication, load balancing, multicasting, and satellite broadcasting. We consider the whole spectrum of solutions, putting them in a global perspective and discussing how the different parties involved - ISPs, content provider, and users- can benefit from each solution. To evaluate content distribution systems we use analytical models, trace driven simulations, and real prototypes.
Scalable content distribution in the Internet
© EPFL. Personal use of this material is permitted. The definitive version of this paper was published in Thesis and is available at : http://dx.doi.org/10.5075/epfl-thesis-2274
PERMALINK : https://www.eurecom.fr/publication/922