Network coding enhanced browser based Peer-to-Peer streaming

Research output: Contribution to book/Conference proceedings/Anthology/ReportConference contributionContributedpeer-review

Contributors

Abstract

Peer-to-Peer network topology is well known for its beneficial characteristic, like good scalability high robustness. In spite of this, web browsers are still using the standard server-client topology for data download. In this paper we investigate the methods of implementing Peer-to-Peer data streaming in web browsers, using only JavaScript, without the need of any third party plugin. We are using WebRTC to establish direct browser to browser connections. With its help, we are designing two efficient protocols for browser based Peer-to-Peer streaming. The first protocol is an efficient content sharing Peer-to-Peer protocol. The second one a network coding enhanced Peer-to-Peer protocol. In order to demonstrate the characteristics of the solution and prove the advantages of it we have established a testbed. In this testbed we run several measurements to analyze the behavior and the throughput of our protocols. Through our results, we show that modern browsers are capable of maintaining Peer-to-Peer connections and carrying out complex network coding calculations. We show that employing our protocols for data streaming, average data download speed can be significantly increased and server load can be decreased up to 80%. This research can be considered as a pioneer work in the field of Peer-to-Peer solutions with network coding, based purely on web technologies.

Details

Original languageEnglish
Title of host publication2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2104-2109
Number of pages6
ISBN (electronic)9781509018970
Publication statusPublished - 6 Feb 2017
Peer-reviewedYes

Conference

Title2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016
Duration9 - 12 October 2016
CityBudapest
CountryHungary

External IDs

ORCID /0000-0001-8469-9573/work/161891288