移动P2P流媒体中基于有效容量的邻居节点选择机制(英文)-豆柴文库

您所在位置：网站首页 / 移动P2P流媒体中基于有效容量的邻居节点选择机制(英文).docx / 文档详情

在线预览结束，喜欢就下载吧，查找使用更方便

5 金币

下载文档

/ 2

下载提示

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

文本预览

移动P2P流媒体中基于有效容量的邻居节点选择机制(英文)
Introduction
Mobilepeer-to-peer(P2P)streaminghasbecomeanincreasinglypopularmethodfordistributingmediacontenttoalargeaudience.However,oneofthemajorchallengesinP2Pstreamingistoefficientlyselectthebestneighborpeerstoimprovethestreamingperformance.Inthispaper,weproposeaneffectiveneighborpeerselectionmechanismbasedontheavailablecapacityofneighbors.Ourproposedmethodcansignificantlyimprovethestreamingperformanceandreducetheoveralltrafficinthenetwork.
Background
Peer-to-peerstreamingisausefultechnologyfordistributinglargemediafiles,suchasvideosandaudiofiles.InP2Pstreaming,peersexchangedatawitheachothertoreducetheloadontheserverandenhancethestreamingperformance.However,selectingthebestpeersisasignificantchallengeinP2Pstreaming.Manyexistingneighborselectionmechanismsonlyconsiderthedownloadrateortheuploadrateofpeers,whichcanleadtosuboptimalperformance.
ProposedMechanism
Ourproposedmechanismselectsneighborsbasedontheireffectivecapacity,whichtakesintoaccounttheavailablecapacityofneighborsandtheaverageutilizationoftheircapacity.Thisallowsforamoreefficientselectionofneighborsthatcanprovidebetterstreamingperformance.Specifically,weuseaweightedfunctiontomeasuretheeffectivecapacityofeachneighbor.Thefunctionconsidersthedownloadanduploadrates,aswellasthecurrentusageofthecapacity.Wealsouseadynamicthresholdmechanismtoavoidselectingpeersthatmayhavehigh-capacitybutlowutilizationrates,whichcanleadtoinefficientuseofthenetworkresources.
Evaluation
Weevaluateourproposedmechanismusingasimulation-basedapproach.Wecompareourmechanismwithtwoexistingmechanisms,namelyRarestFirstandGreedySelection.Weusethreemetricstoevaluatetheperformance,namelytheaveragestreamingrate,thepercentageofpeersthatcontributetothestreaming,andtheoveralltrafficinthenetwork.Ourresultsshowthatourproposedmechanismoutperformsthetwoexistingmechanismsintermsofallthreemetrics.Specifically,ourmethodachievesanaveragestreamingratethatis20%higherthantheothertwomethods.Thepercentageofcontributorpeersisalsomuc