Design and Analysis of an Efficient Friend-to-Friend Content Dissemination System

Abstract : Opportunistic communication, off-loading and decentrlaized distribution have been proposed as a means of cost efficient disseminating content when users are geographically clustered into communities. Despite its promise, none of the proposed systems have not been widely adopted due to unbounded high content delivery latency, security and privacy concerns. This paper, presents a novel hybrid content storage and distribution system addressing the trust and privacy concerns of users, lowering the cost of content distribution and storage, and shows how they can be combined uniquely to develop mobile social networking services. The system exploit the fact that users will trust their friends, and by replicating content on friends’ devices who are likely to consume that content it will be possible to disseminate it to other friends when connected to low cost networks. The paper provides a formal definition of this content replication problem, and show that it is NP hard. Then, it presents a community based greedy heuristic algorithm with novel dynamic centrality metrics that replicates the content on a minimum number of friends’ devices, to maximize availability. Then using both real world and synthetic datasets, the effectiveness of the proposed scheme is demonstrated. The practicality of the proposed system, is demonstrated through an implementation on Android smartphones.
Complete list of metadatas

Cited literature [41 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01369954
Contributor : Aline Carneiro Viana <>
Submitted on : Friday, September 23, 2016 - 9:46:15 AM
Last modification on : Thursday, February 7, 2019 - 5:34:13 PM

File

TMC.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Kanchana Thilakarathna, Aline Carneiro Viana, Aruna Seneviratne, Henrik Petander. Design and Analysis of an Efficient Friend-to-Friend Content Dissemination System. IEEE Transactions on Mobile Computing, Institute of Electrical and Electronics Engineers, 2016, ⟨10.1109/TMC.2016.2570747⟩. ⟨hal-01369954⟩

Share

Metrics

Record views

489

Files downloads

575