Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?
Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur Graph Search.
Approximately one billion users have access to mobile broadband, through which they intend to obtain the same data they can reach using a wired connection. Because of the cost of transmitting data over a mobile-broadband connection and given that 3G networks are quickly reaching their data-transfer capacity, some researchers envision the inter-connection of mobile devices using Wi-Fi, forming a challenged network. Such networks suffer from high latency, low data rates, and frequent disconnections; because end to end paths between pairs of nodes may not always exist, a mobile device must store content before delivering it to the intended receivers. We designed the content-optimal delivery algorithm (CODA) for distributing named data over a delay-tolerant network (DTN), which is a network of challenged networks. Current content-dissemination techniques for DTNs consist mainly of the following items: a content store, for caching and indexing retrieved content, and a query and response mechanism to search the network for matching content. Some algorithms attempt to optimize an objective function, such as the total delivery-delay. While disseminating content, CODA maximizes the network throughput by computing the utility of each item published: a device with a full buffer drops content in order of increasing utility and transmits content in order de- creasing utility. We implemented CODA over the CCNx protocol, which provides the basic tools for querying, caching, and transmitting content.
Carmela González Troncoso, Sandra Deepthy Siby
Andreas Peter Burg, Adrian Schumacher, Ruben Merz