Full metadata record
DC FieldValueLanguage
dc.contributor.authorHo, CYen_US
dc.contributor.authorChen, YCen_US
dc.date.accessioned2014-12-08T15:16:59Z-
dc.date.available2014-12-08T15:16:59Z-
dc.date.issued2006-04-01en_US
dc.identifier.issn1350-2425en_US
dc.identifier.urihttp://dx.doi.org/10.1049/ip-com:20050184en_US
dc.identifier.urihttp://hdl.handle.net/11536/12436-
dc.description.abstractImproving the performance of the traditional TCP in wireless IP communications has been an active research area. The significant cause of packet losses in such heterogenous networks is no longer limited to network congestion. The performance degradation of TCP in wireless and wired-wireless hybrid networks is mainly due to its lack of ability to differentiate the packet losses caused by network congestions from the losses caused by wireless link errors. New variants of TCP Vegas and TCP Reno named Snug-Vegas and Snug-Reno, respectively, are proposed. By using random-loss indications marked by base stations, Snug-Vegas and Snug-Reno may detect random packet losses precisely. Through the packet loss differentiation, Snug-Vegas and Snug-Reno react appropriately to the losses, and based on the simulation results, it is seen that the throughput of connection over heterogeneous networks can be significantly improved.en_US
dc.language.isoen_USen_US
dc.titleSnug-Vegas and Snug-Reno: efficient mechanisms for performance improvement of TCP over heterogeneous networksen_US
dc.typeArticleen_US
dc.identifier.doi10.1049/ip-com:20050184en_US
dc.identifier.journalIEE PROCEEDINGS-COMMUNICATIONSen_US
dc.citation.volume153en_US
dc.citation.issue2en_US
dc.citation.spage169en_US
dc.citation.epage176en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000237216200003-
dc.citation.woscount0-
Appears in Collections:Articles


Files in This Item:

  1. 000237216200003.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.