File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Exploring large-scale peer-to-peer live streaming topologies

TitleExploring large-scale peer-to-peer live streaming topologies
Authors
KeywordsPeer-to-peer streaming
Topology characterization
Issue Date2008
PublisherAssociation for Computing Machinery, Inc
Citation
Acm Transactions On Multimedia Computing, Communications And Applications, 2008, v. 4 n. 3 How to Cite?
AbstractReal-world live peer-to-peer (P2P) streaming applications have been successfully deployed in the Internet, delivering live multimedia content to millions of users at any given time. With relative simplicity in design with respect to peer selection and topology construction protocols and without much algorithmic sophistication, current-generation live P2P streaming applications are able to provide users with adequately satisfying viewing experiences. That said, little existing research has provided sufficient insights on the time-varying internal characteristics of peer-to-peer topologies in live streaming. This article presents Magellan, our collaborative work with UUSee Inc., Beijing, China, for exploring and charting graph theoretical properties of practical P2P streaming topologies, gaining important insights in their topological dynamics over a long period of time. With more than 120 GB worth of traces starting September 2006 from a commercially deployed P2P live streaming system that represents UUSee's core product, we have completed a thorough and in-depth investigation of the topological properties in large-scale live P2P streaming, as well as their evolutionary behavior over time, for example, at different times of the day and in flash crowd scenarios. We seek to explore real-world P2P streaming topologies with respect to their graph theoretical metrics, such as the degree, clustering coefficient, and reciprocity. In addition, we compare our findings with results from existing studies on topological properties of P2P file sharing applications, and present new and unique observations specific to streaming. We have observed that live P2P streaming sessions demonstrate excellent scalability, a high level of reciprocity, a clustering phenomenon in each ISP, and a degree distribution that does not follow the power-law distribution. © 2008 ACM.
Persistent Identifierhttp://hdl.handle.net/10722/92633
ISSN
2015 Impact Factor: 0.982
2015 SCImago Journal Rankings: 0.586
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorWu, Cen_HK
dc.contributor.authorLi, Ben_HK
dc.contributor.authorZhao, Sen_HK
dc.date.accessioned2010-09-17T10:52:31Z-
dc.date.available2010-09-17T10:52:31Z-
dc.date.issued2008en_HK
dc.identifier.citationAcm Transactions On Multimedia Computing, Communications And Applications, 2008, v. 4 n. 3en_HK
dc.identifier.issn1551-6857en_HK
dc.identifier.urihttp://hdl.handle.net/10722/92633-
dc.description.abstractReal-world live peer-to-peer (P2P) streaming applications have been successfully deployed in the Internet, delivering live multimedia content to millions of users at any given time. With relative simplicity in design with respect to peer selection and topology construction protocols and without much algorithmic sophistication, current-generation live P2P streaming applications are able to provide users with adequately satisfying viewing experiences. That said, little existing research has provided sufficient insights on the time-varying internal characteristics of peer-to-peer topologies in live streaming. This article presents Magellan, our collaborative work with UUSee Inc., Beijing, China, for exploring and charting graph theoretical properties of practical P2P streaming topologies, gaining important insights in their topological dynamics over a long period of time. With more than 120 GB worth of traces starting September 2006 from a commercially deployed P2P live streaming system that represents UUSee's core product, we have completed a thorough and in-depth investigation of the topological properties in large-scale live P2P streaming, as well as their evolutionary behavior over time, for example, at different times of the day and in flash crowd scenarios. We seek to explore real-world P2P streaming topologies with respect to their graph theoretical metrics, such as the degree, clustering coefficient, and reciprocity. In addition, we compare our findings with results from existing studies on topological properties of P2P file sharing applications, and present new and unique observations specific to streaming. We have observed that live P2P streaming sessions demonstrate excellent scalability, a high level of reciprocity, a clustering phenomenon in each ISP, and a degree distribution that does not follow the power-law distribution. © 2008 ACM.en_HK
dc.languageengen_HK
dc.publisherAssociation for Computing Machinery, Incen_HK
dc.relation.ispartofACM Transactions on Multimedia Computing, Communications and Applicationsen_HK
dc.subjectPeer-to-peer streamingen_HK
dc.subjectTopology characterizationen_HK
dc.titleExploring large-scale peer-to-peer live streaming topologiesen_HK
dc.typeArticleen_HK
dc.identifier.emailWu, C:cwu@cs.hku.hken_HK
dc.identifier.authorityWu, C=rp01397en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1145/1386109.1386112en_HK
dc.identifier.scopuseid_2-s2.0-52949123571en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-52949123571&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume4en_HK
dc.identifier.issue3en_HK
dc.identifier.eissn1551-6865-
dc.identifier.isiWOS:000259433300003-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridWu, C=15836048100en_HK
dc.identifier.scopusauthoridLi, B=23467418800en_HK
dc.identifier.scopusauthoridZhao, S=22137150800en_HK
dc.identifier.citeulike6587569-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats