RaptorQP2P: Maximize the performance of P2P file distribution with RaptorQ coding

Zeyang Su, Feng Wang, John Daigle, Haiyang Wang, Tong Shan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Presented herein is a new protocol, RaptorQP2P, for reliable peer-to-peer sharing of large files-currently on the order of hundreds of MB but expected to grow to the terabyte range-over networks. The new protocol features two levels of RaptorQ encoding. At the top layer, the entire file is RaptorQ encoded to yield a collection of source blocks and repair blocks. At the lower layer, each source/repair block is RaptorQ encoded independently to yield a collection of source symbols and repair symbols for the block. The symbols are independently transferred among the peers and when a sufficient number of distinct symbols for a block have been received, whether source or repair, the block can be reconstructed. Similarly, the file can be reconstructed using a sufficient number of arbitrary distinct blocks. With real world traces measured on the BitTorrent system, we have conducted extensive simulations to evaluate and compare the performance of RaptorQP2P and BitTorrent. The results indicate that the new protocol handles network dynamics and peer churn smoothly, has excellent scalability with respect to both file size and user population, and performs well. As an example, for a 512 MB file distributed to 1000 peers, download completion time using the new protocol was found to be approximately 45.5% of the completion time required using BitTorrent.

Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Communications, ICC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5331-5336
Number of pages6
ISBN (Electronic)9781467364324
DOIs
StatePublished - Sep 9 2015
EventIEEE International Conference on Communications, ICC 2015 - London, United Kingdom
Duration: Jun 8 2015Jun 12 2015

Publication series

NameIEEE International Conference on Communications
Volume2015-September
ISSN (Print)1550-3607

Other

OtherIEEE International Conference on Communications, ICC 2015
Country/TerritoryUnited Kingdom
CityLondon
Period6/8/156/12/15

Fingerprint

Dive into the research topics of 'RaptorQP2P: Maximize the performance of P2P file distribution with RaptorQ coding'. Together they form a unique fingerprint.

Cite this