Bey ond the Model of ersistent TCP Flo ws OpenLoop vs ClosedLoop Arri als of NonP ersistent Flo ws Ra vi S - Description

Prasad and Constantine Do vrolis Colle ge of Computing Geor gia Institute of echnology ra vido vrolis ccgatechedu Abstract It is common for simulation and analytical studies to model Internet tr af 57346c as an gr gation of mostly per sis tent TCP 5 ID: 28576 Download Pdf

Similar presentations

A Probabilistic Approach to Mixed Openloop and Closedloop Con trol with Application to Extreme Autonomous Driving J
A Probabilistic Approach to Mixed Openloop and Closedloop Con trol with Application to Extreme Autonomous Driving J

Zico Kolter Christian Plagemann David T Jackson Andrew Y Ng Sebastian Thrun Abstract We consider the task of accurately controlling a complex system such as autonomously sliding a car sideways into a parking spot Although certain regions of this do

\r\f \f\n\t\b 
\r\f \f\n\t\b 

       hristmas n arrial\r\f \n\t\b

On Time Clocks Chronometers and OpenLoop Control Steven M
On Time Clocks Chronometers and OpenLoop Control Steven M

LaValle Magnus B Egerstedt lavalleuiucedu magnusecegatechedu Department of Computer Science School of Electrical and Comput er Engineering University of Illinois Georgia Institute of Technology Urbana IL 61801 USA Atlanta GA 30332 USA Abstract This

Mining Requirements from ClosedLoop Control Models Xiaoqing Jin Univ
Mining Requirements from ClosedLoop Control Models Xiaoqing Jin Univ

of California Riverside jinxcsucredu Alexandre Donz Univ of California Berkeley donzeeecsberkeleyedu Jyotirmoy V Deshmukh Toyota Technical Center jyotirmoydeshmukhtematoyotacom Sanjit A Seshia Univ of California Berkeley sseshiaeecsberkeleyedu ABSTR

ESTHETIQUE-Les vides Point focal, les vides et les plans
ESTHETIQUE-Les vides Point focal, les vides et les plans

Litérati. Bonsaï Club. Le point focal. où est-il ?. Les fleurs, à droite. autre exemple de point focal. . Le bois mort. Vide principal, secondaire, vides intérieurs, où sont-ils ?. Leur importance: permet au regard de plonger à travers l’arbre.

How does it work Once installed at the main MV substations in an openloop network Easergy T units establish peertopeer communication using a virtual private network
How does it work Once installed at the main MV substations in an openloop network Easergy T units establish peertopeer communication using a virtual private network

If a fault occurs within the network the control centre is noti57375ed but theres no need to wait for an operator response Instead the Easergy T200 units communicate with one another automatically to determine where the fault has occurred isolate it

DATE OF CRASH TIME OF CRASH TI M E OFFI CER NOTI FI ED TI M E OFFI CER ARRI VED INVEST
DATE OF CRASH TIME OF CRASH TI M E OFFI CER NOTI FI ED TI M E OFFI CER ARRI VED INVEST

AGENCY REPORT NUMBER HSMV CRASH REPORT NUMBER COUNTY CITY CODE FEET or COUNTY AT NODE NO or NEXT NODE NO NO OF LANES 1 DIVIDED 2 UNDIVIDED MILES of CITY OR TOWN Check if in City or Town FEET or MILES FROM NODE NO FEET MILES FROM INTERSECTION OF AM

Root Locus Analysis Introduction The basic characteristic of the transient response of a clos edloop system is closely related to the location of the closedloop poles
Root Locus Analysis Introduction The basic characteristic of the transient response of a clos edloop system is closely related to the location of the closedloop poles

If the system has a v ariable loop gain then the location of the closedloop poles depends on the value of the loop gain chosen It is important therefore that the designer know how the closedloop poles move in the splane as the loop gain is varied Fr

Introduction to the Nyquist criterion The Nyquist criterion relates the stability of a closed system to the openloop frequency response and open loop pole location
Introduction to the Nyquist criterion The Nyquist criterion relates the stability of a closed system to the openloop frequency response and open loop pole location

Mapping If we take a complex number on the splane and substitute into a function an other complex number results eg substitut ing 4 3 into 2 1 yields 16 30 Contour Consider a collection of points called a contour A Contour A can be mapped

Closedloop System Modeling Validation and Verication Sebastian Preue HansChristian Lapp and HansMichael Hanisch University of HalleWittenberg Institute of Computer Science Chair of Automation Technol
Closedloop System Modeling Validation and Verication Sebastian Preue HansChristian Lapp and HansMichael Hanisch University of HalleWittenberg Institute of Computer Science Chair of Automation Technol

preusse hanschristianlapp hansmichaelhanisch informatikunihallede Abstract Control software engineering has become a weighty factor according to implementation expense especially when developing a new plant or migrating an existing one Because of thi

119K - views

Bey ond the Model of ersistent TCP Flo ws OpenLoop vs ClosedLoop Arri als of NonP ersistent Flo ws Ra vi S

Published bygiovanna-bartolotta

Prasad and Constantine Do vrolis Colle ge of Computing Geor gia Institute of echnology ra vido vrolis ccgatechedu Abstract It is common for simulation and analytical studies to model Internet tr af 57346c as an gr gation of mostly per sis tent TCP 5

Tags : Prasad and Constantine
Embed :
Pdf Download Link

Download Pdf - The PPT/PDF document "Bey ond the Model of ersistent TCP Flo w..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Bey ond the Model of ersistent TCP Flo ws OpenLoop vs ClosedLoop Arri als of NonP ersistent Flo ws Ra vi S






Presentation on theme: "Bey ond the Model of ersistent TCP Flo ws OpenLoop vs ClosedLoop Arri als of NonP ersistent Flo ws Ra vi S"— Presentation transcript:

BeyondtheModelofPersistentTCPFlows:Open-LoopvsClosed-LoopArrivalsofNon-PersistentFlowsRaviS.PrasadandConstantineDovrolisCollegeofComputing,GeorgiaInstituteofTechnologyfravi,dovrolisg@cc.gatech.eduAbstractItiscommonforsimulationandanalyticalstudiestomodelInternettrafcasanaggregationofmostlypersis-tentTCPows.Inpractice,however,owsfollowaheavy-tailedsizedistributionandtheirnumbeructuatessigni-cantlywithtime.Oneimportantissuethathasbeenlargelyignorediswhethersuchnon-persistentowsarriveinthenetworkinanopen-loop(sayPoisson)orclosed-loop(in-teractive)manner.ThispaperfocusesonthedifferencesthattheTCPowarrivalprocessintroducesinthegener-atedaggregatetrafc.WerstreviewtheProcessorSharingmodelsforsuchowarrivalprocessesaswellasthecorre-spondingTCPpacket-levelmodels.Then,wefocusonthequeueingperformancethatresultsfromeachmodel,andshowthattheclosed-loopmodelproduceslowerlossrateandqueueingdelaysthantheopen-loopmodel.Weexplainthisdifferenceintermsoftheincreasedtrafcvariabilitythattheopen-loopmodelproduces.Thecauseofthelat-teristhattheowarrivalrateintheopen-loopmodeldoesnotreduceuponcongestion.Wealsostudythetransientef-fectofcongestioneventsonthetwomodelsandshowthattheclosed-loopmodelresultsincongestion-responsivetraf-cwhiletheopen-loopmodeldoesnot.Finally,wediscussimplicationsofthedifferencesbetweenthetwomodelsinseveralnetworkingproblems.1IntroductionModelsofaggregateTCPtrafcarevaluableinnet-workingresearchandpractice.MuchofthepreviousworkinthisareahasbeenfocusingonthemodelofpersistentTCPows,i.e.,onowsthathaveunlimiteddatatosendandthatarenotlimitedbythereceiveradvertisedwindow.Thismodelismathematicallytractableanditiseasiertosimulate,butatthesametimeitfailstocapturekeyas-pectsofrealInternettrafc[10].Specically,itignorestheheavy-tailednatureoftheowsizedistribution(thatcanproduceLong-RangeDependency),thesignicantvari-ationsinthenumberofactiveowswithtime,andthere-lationbetweencongestionandtheowarrivalprocess.Ontheotherhand,somepreviousworkhasconsiderednon-persistentTCPows,followingaheavy-tailedsizedistri-bution.TheopenissuethereiswhetherthearrivalprocessoftheTCPowsshouldbemodeledinanopen-loop(OL)manner(say,accordingtoaPoissonprocess),orinaclosed-loop(CL)manner(say,fromanumberofinteractiveusers).Thispaperfocusesonthedifferencesthattheowarrivalprocess,OLversusCL,causesinthegeneratedaggregatetrafc.Therelatedissueofwhichmodelismorerealistichasbeenthefocusofarecentmeasurementstudy[16].WestartwiththeuidProcessorSharing(PS)mod-elsfortheOLandCLowarrivalprocesses.ThePSmodelsprovideanaccurateestimateoftheofferedloadinlight/moderateloadconditions.Ontheotherhand,whentheloadapproachesthecapacity,thePSmodelscanleadtosignicantunderestimationoftheofferedload.ThemainproblemisthatthePSmodelsignorepacketlossesandTCPretransmissions,whichareasignicantcontributionofad-ditionalloadincongestedlinks.Nevertheless,thePSmod-elsshowclearlythattheopen-loopmodelcanbeunstable,whiletheclosed-loopmodelisalwaysstable,asthenumberofactiveowsisbounded.Wethencomparethequeueingperformanceofthe(packetlevel)OLandCLmodels,examiningthelossrateandqueueingdelaydistributionthatthetwomodelspro-duceunderthesameofferedload.TheOLmodelproduceshigherlossrateandqueueingdelaysthantheCLmodel.Toexplainthisdifference,weexaminethetrafcvariabil-ityproducedbythetwomodelsinarangeoftimescales(10msec-1sec).WendoutthattheOLmodelresultsinhighervariancethantheCLmodel,especiallywhenthetimescaleexceedstheTCPRound-TripTime(RTT).ThecauseoftheincreasedtrafcvariabilityintheOLmodelisthatthelatterdoesnotreducetheowarrivalrateuponcongestion.Thisleadstomoresignicantoverloadevents,inmagnitudeandduration,thantheCLmodel,generatinghighertrafcvariability.TheCLmodelrespondstoconges-1 tionroughlyoneRTTafteritsoccurrence,whichexplainswhythevariabilitydifferencebecomessignicantwhenthetimescaleislargerthantheRTT.Wealsoexaminethedistributionofthenumberofac-tiveowswitheachowarrivalmodel.Here,wendthattheOLmodelresultsinhighervariabilityinthenumberofowsthantheCLmodelwhentheofferedloadissig-nicant.TherearetimeperiodsinwhichthenumberofongoingowswiththeOLmodelismuchhigherthantheaverage.ThisobservationisrelatedtoanearlierstudybySchroederetal.whichshowedthatjobschedulingiscru-cialmostlywiththeOLmodel,astheformergivesawiderleewaytotheschedulerthantheCLmodel[18].Finally,wefocusonthetransientresponseofthetwomodelsintermsofthecongestionresponsivenessoftheag-gregatetrafc.WithOLowarrivals,theresultingtrafcisnotcongestionresponsive,meaningthattheofferedloaddoesnotfollowtheavailablecapacityinthenetwork.WithCLowarrivals,ontheotherhand,thetrafciscongestionresponsive.Therestofthepaperisorganizedasfollows.Sections2and3reviewpreviousworkandthelimitationsoftheper-sistentowsmodel,respectively.Section4describetheOLandCLmodelsandreviewbasicresultsaboutthecorre-spondingPSmodels.OursimulationsetupispresentedinSection5,whilethequeueingandofferedloaddifferencesbetweenthetwomodelsarepresentedinSections6and7.Section8examinesthevariabilityintheofferedloadatdif-ferenttimescales,whileSection9showsthevariationinthenumberofactiveows.Section10focusesontheconges-tionresponsivenessofthetwomodels.Weconcludethepa-perinsection11,alsodiscussingsomeimplicationsofthisworkinvariousareasofnetworkingresearchandpractice.2RelatedWorkOverthelastfewyears,andespeciallyafterthesemi-nalworkbyKellyetal.[11],severalresearchersappliedcontroltheorytoexaminethestabilityofTCPcongestioncontrol[14,20,15].AkeypointaboutthatlineofworkisthatitassumespersistentTCPows,anditfocusesontheasymptoticstabilityofthequeuesizeatthenetworkbottle-neck.Theassumptionofpersistentowsremovesfromtheproblemtheimportanceoftheowarrivalprocess.Somepreviousworkusesnon-persistentowmodels,butoftenwithoutdiscussingwhethertheOLortheCLmodelismoreappropriate.BenFredjetal.[7]consideredtheOLmodel.Theynotedthattheonlyreductionintheof-feredloaduponacongestioneventisduetoabortedtrans-fers.Suchtransfers,however,resultinwastedthroughputanduserdissatisfaction.Forthisreason,theauthorspro-posedadmissioncontrolastheonlyefcientwaytopreventpersistentoverload.Vecianaetal.[4]consideredtheOLmodelandconcludedthattheInternettrafcmaybecomeunstableundercertainconditions.Heymanetal.[8]usedaCLmodeltoanalyzetheper-formanceofWeb-liketrafcoverTCP.Theyshowedthatthesessiongoodputandthefractionoftimethesystemhasagivennumberofactivesessionsareinsensitivetothedis-tributionofsessionsizesand“thinktimes”,andtheyonlydependonthemeanofthesedistributions.BergerandKo-gan[2],aswellasBonaldetal.[3],usedasimilarCLmodeltodesignbandwidthprovisioningrulesformeetingcertainthroughput-relatedQoSobjectives.BondiandWhitt[1]examinethedifferencesbetweentheOLandCLmodelsinthecontextofnetworksofqueues,focusingontherela-tionbetweentheaveragequeuesizeatthebottleneckqueueandthevariabilityinthejobservice-timedistribution.MostofthepreviousworkwiththeOLorCLmodelsassumesthatTCPcongestioncontrolcansharethecapacityofalinkasauidPSserver[17].KheraniandKumar[12]showedthatthePSmodelisnotalwaysaccurate,mostlybecauseTCPtransfersdonotmanagetokeepthelinkfullyutilizedundercertainconditions.Inthispaper,weusethePSmodeljusttogainsomebasicanalyticinsight.MostofourconclusionsarebasedonNS2simulationswithTCPtransfers.Inapaperthatiscloselyrelatedtoourwork,Schroederetal.[18]comparetheOLandCLmodelsinageneralcon-textofjobarrivalsataserver.Theyhighlightthedifferencesbetweenthetwomodelsintermsofthemeanjobcomple-tiontime,andtheyfocusontheeffectivenessofdifferentjobschedulingpolicieswitheachmodel.Morerecently,wehaveanalyzedseveraltrafctracescollectedatadozenofInternetlinksinordertoestimatethefractionoftrafcthatcanbemappedtoeithertheOLorCLmodel[16].Thatmeasurementstudyshowsthatabout60-80%oftrafcto/fromwell-knownports(mostlyHTTP)followtheCLmodel.Nevertheless,thepercentageofOLtrafcissignicantinsomelinks.Additionally,wecouldnotclassifyreliablyupto70%ofthetrafcincertaintraces.3CritiqueofthePersistentFlowsModelItiscommonforanalyticalandsimulationstudiestomodelmostofthetrafcwithpersistentTCPconnections.Acommonargumenttojustifythismodelisthatmosttraf-cinanInternetlinkiscarriedbyafewlargeTCPowselephantsandsothoseowscanbemodeledaspersistent.Thesmallerows,referredtoasmice,donotcontributeasignicantamountoftrafcandsotheyareoftenignored,ortheyareviewedasasourceofstochasticnoiseinsim-ulationstudies.Thepreviousargumentisanoversimpli-cationanditignorestwokeycharacteristicsofrealInternettrafc.First,thesizeofTCPowsfollowsacontinuousandheavy-taileddistributioninpractice,ratherthanabimodal distributioninwhichowsareeitherveryshort(mice)orverylong(elephants).Inotherwords,thepreviousargu-mentignorestheowsofsignicant,butnotextreme,size.Second,owswithverylargesize(relativetootherowsintheaggregate)donotalwayshaveverylongduration.Somelargeowsgethigherthroughput,andsotheirdurationcanbecomparabletothatofshortows.Suchowscannotbemodeledaspersistent,especiallywhenthetimescaleofin-terest(forexample,thedurationofthesimulationstudy)islongerthantheirduration.Toillustratetheseissues,weanalyzeapackettracethatwascollectedattheborderrouterofGeorgiaTechinJan-uary2005.Thetracedurationistwohoursandthemoni-toredlinkcarriestheinboundtrafcinaGigabitEthernetsegmentthatconnectsthecampusnetworktotheSoXGi-gaPoP.Theobjectiveofthistrafcanalysisistoexaminetheassumptionsbehindthepersistentowsmodel.Notethatsimilarstudieshavebeenconductedseveraltimesinthepast(forinstance,see[6]),usingtracesfrommanylinksandunderdiverseloadconditions.0102030405060708090100110120Time interval T (min.)0.20.30.40.50.60.7Fraction of bytes from Figure1.ThefractionofbytesfgeneratedbyowsthatareactivefortheentiredurationofagiventimeintervalTasafunctionofT.Theerrorbarsdepicttheminimumandthemaximumvaluesofthefractionf.Werstlookedattheowsizedistribution.WendthattheC-CDFofthatdistributionshowsclearlineardecreaseinalog-logplot,pointingtotheheavy-tailedParetodistri-bution(withshapeparameterabout1.3).Wealsoexaminedthedistributionofowinterarrivals.Whentheinterarrivalsarelargerthan100msecorso,theycanbemodeledasex-ponentialandindependent(pointingtoaPoissonowar-rivalprocess).However,therearesignicantcorrelationsinlowerinterarrivals,probablyduetothegenerationofsimul-taneousowsbythesameapplicationsession.Next,wemeasuredthenumberofactiveowsasafunc-tionoftimefordifferentowsizethresholds.Ifweonlyconsiderowsthatarelargerthan1.5MB(or1000pkts),thenumberofactiveowsremainsalmostconstantwithtime.Thisobservation,however,shouldnotbeinterpretedasvalidationofthepersistentowsmodel.Thereasonisthateventhoughthenumberof(sufcientlylarge)activeowsremainsroughlyconstantwithtime,thesetofactiveowschangessignicantlywithtime.ToillustratethispointweexaminedthefractionofbytesfthatisgeneratedbyowsthatremainedactivethroughoutagiventimeintervaloflengthT.Withthepersistentmodel,allowsareactivethroughoutTandthisfractionshouldbecloseto100%.IfallowslastedforlessthanTseconds,thenthisfrac-tionshouldbezero.Wemeasuredfforthefollowingval-uesofT:7.5,15,30,60and120minutes.ForeachvalueofT(exceptfor120minutes),weobtained30samplesofthefractionf,ignoringthersttwominutesofthetrace,andconsideringowsthatlastlongerthan0:95TasactivethroughoutthedurationT.Figure1showsthemean,theminimumandthemaximumvalueoffasafunctionofT.Thekeyobservationhereisthatevenfortimeintervalsthatlastonly5-10mins,thefractionoftrafcfrompersistentowsisonly40-70%.So,theassumptionthatthesamesetofowscarriesalmostalltrafcignoresthevariabilityduetothedynamicowarrivalandcompletionprocesses.4TwoModelsofNon-PersistentFlowAr-rivalsInthissection,wedescribetwobasicmodelsofnon-persistentowarrivals:theOLandCLmodels.Bothmod-elsaresimpleandwell-studiedintheperformanceevalua-tionliterature.Notethattheterms“open-loop”and“closed-loop”havebeenpreviouslyusedtodistinguishbetweennon-TCPtraf-c(viewedasopen-loopbecausepacketsarriverandomlybasedonanexogenousprocess)andTCPtrafc(viewedasclosed-loopbecausetheowisregulatedbyTCPcon-gestioncontrol).Inthispaper,bothOLandCLmodelsdescribeanaggregateofTCPows.Theydiffer,however,inthehigherlevelprocess,operatingatthesessionorap-plicationlayer,thatgeneratestheseows.Figure2showsaschematicdiagramoftheowgenerationprocess.Ifthesessionlayerusessomefeedbackfromthenetwork,sothatitslowsdownthegenerationofnewowsuponcongestion,theresultingtrafcwillbeclosertotheCLmodel.Oth-erwise,intheabsenceofsuchfeedback,theOLmodelismoreappropriate.4.1Open-LoopmodelIntheOLmodel,usersorapplicationsgenerateowsindependentofanypreviousowstheymayhavegenerated.Tomotivatethismodel,considertheaccesslinkofaWebserver.Intheoutbounddirection,theserversendslestoalargepopulationofuserslocatedanywhereintheInternet. NetworkTCP feedback loopSession feedback loop ?TransportSessionClientServerFigure2.Theowarrivalprocessiscon-trolledbythesession/applicationlayer.Isthatlayerresponsivetonetworkcongestion?Assumethatauserdoesnotreturntothisserver,atleastforalongtime,aftercompletingaletransfer.Consequently,theserver'ssessionsarealwayswithnewusers.Ifthelinkbecomescongested,thearrivalrateofnewsessionswillnotbeaffected,asInternetusersaretypicallyunawareofthenetworkstateinagivenpath.ConsideraPSserverwithcapacityC(bytes/sec),aver-ageowarrivalrate(ows/sec),andaverageowsizeS(bytes).WerefertothismodelasPS-OL.Theaverageof-feredloadintheserverisgivenbySandthenormalizedofferedloadiso=S=C:(1)Ifo1,theserverisstableandoistheaverageutiliza-tion.ForaPoissonowarrivalprocess,itcanbeshownthattheaveragenumberofactiveowsisgivenby[13]No=1(1o):(2)Otherwise,ifo�1,theserverisunstable(aslongasowsareneveraborted).Sinceboththeowarrivalrateandtheaverageowsizeareindependentofthenetworkstate,theaverageofferedloadremainsconstanteveninthepresenceofcongestion.Further,theexpectedthroughputofanewowinthePS-OLmodelisgivenbytheavailablecapacityintheserver,R=C(1o):(3)DeviatingfromthePSmodel,wecanconsiderapacket-levelmodelofaFirst-Come-First-Served(FCFS)queuewithanitebufferandwithowsthatarecontrolledbyTCPcongestioncontrol(TCP-OL).NoticetwoimportantdifferencesbetweentheTCP-OLmodelandthePS-OLmodel.Intheformer,wecanhavepacketdrops.TCPreactstothemwithretransmissions,whicheffectivelyincreasethesizeoftheaffectedows.Further,itiswellknownthatTCPcangenerateredundantretransmission.ThismeansthattheactualofferedloadbyasetofTCPowsintheOLmodelcanbehigherthanwhatthePSmodelpredictsinEqua-tion(1).Second,aTCPowcanbeactiveevenwhenitdoesnotcompeteforavailablecapacity,becauseofwindowlimitationsduetoslow-start,retransmissiontimeouts,lim-itedadvertisedwindow,etc.ThismeansthattheaveragenumberofactiveTCPowscanbemuchlargerthanEqua-tion(2).4.2Closed-LoopmodelToillustratetheCLmodel,considertheaccesslinkofasmallenterprisewith,sayN,users.Intheinbounddi-rection,mostofthetrafcatthelinkisdownloadsthataregeneratedbytheactivityoftheseNusers.Inthesimplestmodel,eachusercanbeinthe“Active”statedownloadingale,thenspendingsometimeinthe“Idle”(or“Thinking”)state,andtheneitherdownloadinganotherle,orleavingthesystemforalongertimeperiod(“Inactive”state).ThislinkwouldnotcarrymorethanNactiveowsatanytime.Furthermore,ifthelinkbecomescongested,thenthedown-loadlatenciesofallactiveowswillincrease,reducingtheratewithwhichnewowsaregenerated.InthePSversionoftheCLmodel,wehaveaxednum-berofusersN.Eachusergoesthroughcyclesofactivity,withowsofaveragesizeS,followedbyidleperiodsofaveragelengthTi.TheaveragesessionarrivalrateintheCLmodelisgivenbyc=NTt+Ti(4)whereTtistheaverageowtransferlatency.Thelatterde-pendsontheloadatthePSserver.ThustheaverageserverutilizationatthePS-CLmodelisgivenbyc=NSC(Ti+Tt):(5)TheaveragenumberofactiveowsinthePS-CLmodelisgivenby(see[2])Nc=a1afora1=N1a1=NCTiSfora�1(6)wherethenormalizedofferedloadisgivenbya=NS=CTi:(7)Notethattheexpectednumberofactiveowsfora1issamewiththeOLmodel.Ontheotherhand,when�a1,NcincreasesslowlywithaandremainsboundedbyN.SimilartotheTCP-OLmodel,theCLmodelwithaFCFSqueueandTCPows(TCP-CL)candeviatesigni-cantlyfromitsPS-CLcounterpart.First,asinTCP-OL,weneedtoconsidertheextraloadduetorequiredorredundantretransmissions.Second,asintheTCP-OLmodel,TCPisnotabletoalwaysusetheavailablecapacity. 5SimulationSetupTheprevioussectionreviewedwell-knownresultsfortheOLandCLmodels,basedonthePSmodel.Inthiswork,wearemoreinterestedinTCP-speciceffectsthatcannotbecapturedbythePSmodel,aswellasonthevarianceoftheresultingaggregatetrafc.Forthesereasons,werelymostlyonsimulation.Figure3showsourNS-2simulationsetup.Thereare 1Gbps1Gbps50MbpsB=250pkts1105ms45ms5ms5msServersClientsFigure3.Simulationsetup10inputlinks,eachwithcapacity1Gbps,connectedtoanoutputlinkwithcapacityC=50MbpsandbuffersizeB.Thistopologydescribesascenarioinwhichthebottleneckistheingresslinkofanenterprisenetwork,andwheretheserver,backboneandclientlinksareover-provisioned.Inthissetup,wehave20serversthatareconnectedtothebot-tleneckwith1Gbpslinksandwithpropagationdelaysthatvarybetween5msecand45msec.Theround-trippropaga-tiondelayinthissetupvariesfrom30msecto110msec,withaharmonicmeanofaboutT0=60msec1.InallsimulationsweusetheSACK-enabledNS-2TCPmodulesack1.ThebuffersizeBissettothebandwidth-delayproductofthepath(250packets),consideringT0astherepresentativedelay.Themaximumadvertisedwindowissetto256packets.IntheCLsimulations,thereareNclientsthatinitiateTCPtransfers.Theseusersarriveforthersttimeatthenetworkatarandominstantduringtherstfewsecondsofthesimulation.Afterarriving,eachuserfol-lowstheCLowgenerationprocessselectingaserverforeachtransferrandomlyfromthesetof20servers.IntheOLsimulations,theowarrivalprocessisPoissonwithar-rivalrate.Inallsimulations,theowsizefollowsaParetodistributionwithameanof25packetsandshapeparameter1.5.ThethinktimeTifortheCLmodelfollowsanexpo-nentialdistributionwithameanof2seconds.ThevaluesofandNarevariedtoobtaindifferentofferedloadsintheOLandCLmodels,respectively.Eachsimulationrunsfor1000secondsandwereportresultsfortheperiodfrom200to950seconds.6ControllingtheOfferedLoadTocomparethetrafccharacteristicsandqueueingper-formanceoftheOLandCLmodels,werstneedtomake1Theuseoftheharmonicmeanhasbeenrecommendedin[5].surethattheirparametersareselectedsothatbothmodelsproduceequalaverageofferedload.Theofferedloadisde-nedastheamountoftrafcthatarrivesatthebottlenecklinkperunitoftime,anditincludestrafcthatmaygetdroppedduetocongestion.ControllingtheofferedloadintheOLandCLmodels,however,isnottrivial.SupposethatwewanttogenerateacertainofferedloadXatthebottlenecklinkoftheprevioussimulationsetup.GiventheaverageowsizeS(andtheav-eragethinktimeTiinthecaseoftheCLmodel),acommonapproachistorelyonthePSmodel.FortheOLmodel,wecancalculatetherequiredowarrivalrateas=X=S.FortheCLmodel,however,thetermTtdependsonthegivenloadconditions.Acrudeapproximationistoassumelightloadconditions(a1),andthusTtTi.Then,therequirednumberofusersisN=XTi=S.010203040506070PS Model Offered Load (Mbps)020406080100Offered Load (Mbps)PS-OLPS-CL-TPS-CLCapacityFigure4.TheofferedloadwiththeTCP-OLandTCP-CLmodels(simulated,y-axis)asafunctionoftheofferedloadXthatispre-dictedbythecorrespondingPSmodels(cal-culated,x-axis).Next,weexaminetherelationbetweentheaverageof-feredloadXpredictedbythetwoPSmodels,aspreviouslydescribed,andtheactualofferedloadthatweobserveinsimulationswithTCPtrafc(TCP-OLandTCP-CLmod-els).Figure4showstheresultsofthiscomparison.ThecapacitylinesX=CandY=Careshownforreference.WeobservethattheofferedloadwiththeTCP-OLmodelisveryclosetotheloadXpredictedbythePS-OLmodel,aslongasXremainsbelowthecapacityC.AsXapproachesCtheTCP-OLofferedloadstartsdeviatingfromX,andwhenX�C(overload)theTCP-OLofferedloadissignif-icantlyhigherthanX.ThereasonisthattheTCP-OLof-feredloadincludesretransmissions(requiredorredundant)ofdroppedpackets.ThefactthattheincreaserateoftheTCP-OLofferedloaddropsasXgoesmoredeeplyintooverloadisduetotheincreasingfrequencyofretransmis-siontimeoutsthattheTCPconnectionsexperience.Nev-ertheless,theimportantobservationhereisthatwecanuse theofferedloadpredictedbyPS-OLmodelasareasonableapproximation,aslongasXC.InthecaseoftheCLmodel,theofferedloadpredictedbythePS-CLmodelislowerthanthatwithTCP-CL,eveninlight/moderateloadconditions.Thereason,ofcourse,isthatwehaveignoredtheload-dependenttransfertimeTt,assumingthatitismuchlessthanTi.EspeciallyforTCPows,however,wecannotignorethatforaowofsizeSthereisaminimumtransferlatencyofseveralRTTsdueslow-start,eveniftherearenoqueueingdelaysorpacketlosses.Thus,wenextconsiderthefollowingimprovedap-proximationoftheofferedloadwiththePS-CLmodel,X=NSTi+Tt;min(S)(8)whereTt;min(S)istheminimumlatencyrequiredbyTCPtotransferaowofsizeSusingslow-start.ItissimpletoestimatethisparameteraslongastheRTTandtheTCPvariantusedareknown.WerefertothisapproximationasthePS-CLmodelwithaconstanttermfortheminimumtransfertimeoftheaverageowsize,orPS-CL-Tforshort.Figure4showstherelationbetweentheofferedloadoftheTCP-CLandPS-CL-Tmodels(withTt;min(S)=0.36secinoursimulations).Notethatthelatterisareasonablygoodapproximationbothwhenthelinkisnotcongested(XC)andinoverload(X�C).ThereasontheofferedloadisslightlyabovethecapacityinoverloadisagainthepresenceofsomeTCPretransmissions.Insummary,thePSmodelcanprovideareasonableapproximationoftheofferedloadintheTCP-CLmodel,aslongasweconsidertheminimumtransfertimewithTCPslow-startfortheaverageowsize.010203040506070PS Model Offered Load (Mbps)020406080100Offered Load (Mbps)PS-OLPS-CL-T (TI=20sec)PS-CL-T (TI=2sec)CapacityN=3200N=390Figure5.TheofferedloadfromtheCLmodeltendstothatoftheOLmodelasNandTiincrease.NoticethattheOLmodelcanbeviewedastheasymp-toticlimitoftheCLmodel,ifweletthenumberofusersNandtheaverageidletimeTigotoinnity,whiletheinitialtransferofeachuserisrandomlyplacedonthetimeaxis.Indeed,wemaywonderwhethertheofferedloadwiththeTCP-CLmodelapproachesthatoftheTCP-OLmodelasweincreaseNandTi.Figure5showstheofferedloadfromtheTCP-CLmodelfortwovaluesofTi,2and20seconds.Notethatanincreaseintheidletimealsorequiresanincreaseinthenumberofusersinordertoattainthesameofferedload.Forexample,withTi=2secweneed400userstoget46Mbpsofofferedload,whilewithTi=20secweneed3200users.Weseethattheofferedloadbetweenthethreecurvesdiffersmostlyinoverload,asexpected.AsweincreaseTiandN,theTCP-CLcurveapproachestheTCP-OLcurve,implyingthegradualconvergenceoftheCLmodeltotheOLmodel.NoticehoweverthatthisconvergenceisveryslowandinpracticewewouldneedaverylargenumberofusersbeforewecanclaimthattheaclosedpopulationofuserscanbemodeledwiththeOLmodel,inoverloadconditions.Intherestofthepaper,weusetheofferedloadthatiscalculatedfromns-2simulations.7QueueingPerformanceNext,wecomparethequeueingperformanceoftheTCP-OLandTCP-CLmodels.Themainobservationisthat,un-derthesameofferedload,theTCP-OLmodelresultsinhigherqueueingdelaysthantheTCP-CLmodel.Iftherearepacketlosses,thenthelossratewithTCP-OLisalsohigherthanwithTCP-CL.01020304050Offered Load (Mbps)00.511.52Loss Rate (%)TCP-OLTCP-CLFigure6.Thelossrateasafunctionoftheof-feredloadfortheTCP-OLandTCP-CLmod-els.6and7showthelossrateandthequeueingde-laysfortheTCP-OLandTCP-CLmodelsasafunctionoftheofferedload.Forqueueingdelays,wereporttheme-dianandthe90-thpercentileoftheper-packetdelaydistri-bution.Thedifferencesareofcourseminorforlightloadconditions,whentheofferedloadis,say,below50%ofthecapacity.Inheavierloadconditions,however,thediffer- 01020304050Offered Load (Mbps)00.010.020.030.040.050.06Queueing Delay (sec.)TCP-OL: 90thPercentileTCP-CL: 90thPercentileTCP-OL: MedianTCP-CL: MedianFigure7.Themedianand90-thpercentileofthequeueingdelaydistributionasafunctionoftheofferedloadfortheTCP-OLandTCP-CLmodels.encesaresignicantandcannotbeignored.Inthenextsec-tionweexplainthesedifferencesexaminingthestatisticalvariabilityoftheaggregatetrafcindifferenttimescales.8TrafcVariabilityatDifferentTimescalesTheresultsoftheprevioussectionsuggestthattheTCP-OLmodelproduceslargertrafcburstinessthantheTCP-CLmodel.Inthissectionweaimtofurtherunderstandwhatcausesthisdifferenceandtoidentifytheloadconditionsandtimescalesinwhichthisismoreevident.Figure8showsthevarianceoftheofferedloadforanaveragingtimescaleof10msec,100msecand1sec.First,noticehowthevariancedependsontheofferedload.Thevarianceincreasesuptoacertainpoint(20-45Mbps,de-pendingonthetimescaleandthemodel).Afterthatpointthevariancedecreaseswiththeofferedload.Foranex-planationofthiswell-understoodtrendwereferthereaderto[9,19].WhatismorerelevanthereisthattheTCP-OLmodelproduceshighervariancethantheTCP-CLmodelinmoderate/heavyloadconditions.Sincetheround-tripprop-agationdelaysinoursimulationtopologyvaryfrom30msecto110msec,weviewthetimescaleof10msecasbelowthetypicalRTT,100msecasroughlyequaltotheRTT,and1secaslargerthantheRTT.TheresultsofFigure8alsosuggestthatthedifferenceinthevarianceofthetwomodelsismoresignicantwhenthetimescaleisaroundtheRTTorhigher.Inlightloadconditionsthetwomodelsarepracticallyequivalent,asthereisnosignicantqueueingorpacketlossesandtransfersareonlylimitedbyTCP'sslow-start.Astheofferedloadincreasesbeyondroughly50%ofthecapacity,congestionepisodesstarttooccur.IntheTCP-OLmodel,newowsarriveindependentofwhetherthebot-tleneckiscongestedornot.IntheTCP-CLmodel,whenaowslowsdownbecauseofcongestionitalsodelaysthegenerationofthenextowfromthesameuser.Thisreducesthedurationandmagnitudeofcongestionevents,leadingtolowertrafcvariabilitythanintheTCP-OLmodel.TheresponselatencyoftheTCP-CLmodelcannotbefasterthanTCP'sRTThowever;thisexplainswhythetwomodels“look”thesameinsub-RTTtimescales.0100200300400500050100150VarianceTCP-CLTCP-OL01020304050Offered Load (Mbps)0255075Time Scale = 10 msecFigure8.VarianceoftheofferedloadwiththeTCP-OLandTCP-CLmodelsforthreeaverag-ingtimescales.0102030405000.10.20.30.40.5TCP-CLTCP-OL0102030405000.10.20.30.40.501020304050Offered Load (Mbps)00.10.20.30.40.5�Fracion of time offered load Capacity01020304050Offered Load (Mbps)00.10.20.30.40.5Time Scale = 10msecTime Scale = 100msecTime Scale = 1 secTime Scale = 10 secFigure9.Fractionoftimetheofferedloadisgreaterthanthecapacityforfouraveragingtimescales.ofurtherillustratethepreviousexplanation,Figure9showsthefractionoftimetheofferedloadexceedsthelinkcapacityinfouraveragingtimescales.Hereweseethatinthesub-RTTtimescaleof10msec,bothmodelsexperienceoverloadforpracticallythesamefractionoftime.WhenweexaminethetrafcathighertimescalesthantheRTT,however,weconrmthattheTCP-OLisoverloadedmorefrequently.TheTCP-CLmodelexperiencesoverloadlessoftenbecauseitsowarrivalratereducesupontheoccur-renceofpacketlosses.Sincethetwomodelshavethesameaverageofferedload,thehigheroverloadfrequencyinTCP-OLiscompensatedwithtimeperiodsinwhichtheTCP-OL offeredloadislessthanthatinTCP-CL.Thesewideruc-tuationsmakethevarianceofTCP-OLhigher,aslongasthetheofferedloadandtimescalearesufcientlylarge.02468101200.20.40.60.81CDF02468101200.20.40.60.8102468101200.20.40.60.81CDFTCP-OLTCP-CL024681012Number of Consecutive Congestion Periods00.20.40.60.81Time Scale = 10 msecTime Scale = 100 msecTime Scale = 10 secTime Scale = 1 secFigure10.TheCDFofthelengthofcon-secutiveoverloadperiodsforfouraveragingtimescales.Theaverageofferedloadis95%ofthecapacity.Itisnotjustthefrequencyofoverloadeventsthatdif-fersbetweenthetwomodels,butalsotheirduration.ThisisshowninFigure10,whereweplottheCDFofthedurationofoverloadeventsatdifferenttimescalesforanaverageof-feredloadof47.5Mbps.Thisdurationismeasuredasthenumberofconsecutivetimeperiods(withlengthequaltotheaveragingtimescale)inwhichtheofferedloadishigherthanthecapacity.Inthesub-RTTtimescalebothmodelshavethesamedistribution.Asthetimescaleincreases,how-ever,thegapbetweenthetwodistributionsincreases,astheTCP-OLmodelisunabletoself-regulateitsofferedloadbe-lowthecapacity.Forinstance,whenwelookatthetrafcinsuccessiveintervalsof10seconds,about85%oftheover-loadeventsinTCP-CLlastforonlyoneinterval.Thecor-respondingpercentageisonly40%intheTCP-OLmodel.9NumberofActiveFlowsInthissection,weexaminethenumberofactiveowscreatedbytheTCP-OLandTCP-CLmodels.WeshowthatthenumberofactiveowsinthesetwoTCPmodelsismuchlargerthanthatpredictedbythePSmodel,andthatTCP-OLproduceshighervariabilityinthenumberofactiveowsthantheTCP-CLmodel,inheavyloadcondi-tions.Thelatterimpliesthattheper-owthroughputintheTCP-OLmodelisalsolesspredictable.Figure11showstheCDFoftheaveragenumberofac-tiveowswhentheofferedloadis70%and95%ofthecapacity.Thenumberofactiveowsisaveragedover1-secintervals.Werstnotethatthenumberofactiveowsin5010015020025000.20.40.60.81CDFTCP-CLTCP-OL50100150200250Average Number of Active Flows00.20.40.60.81CDF70% Offered Load 95% Offered Load Figure11.TheCDFoftheaveragenumberofactiveows,measuredat1-secintervals,fromtheTCP-OLandTCP-CLmodelswhentheofferedloadis70%and95%oftheca-pacity.bothmodelsismuchhigherthanthatpredictedbythepro-cessorsharingmodel(seeEquations2and6).Specically,thePS-OLmodelpredictsabout3and20owsforofferedload70%and95%,respectively.Thecorrespondingaver-agesfromtheTCP-OLsimulationsare70and131.ForthePS-CLmodel,ontheotherhand,Equation6predictsanav-erageof102activeowsfor95%offeredload,whiletheaveragefromtheTCP-CLsimulationsis115.Thesediffer-encescanbeattributedtothefactthat,withTCP,thereisalargenumberofsmallowsthatarenotalwayscompetingforavailablecapacitybecauseofslow-start,retransmissiontimeouts,orotherlimitations.AlsonoticethattheTCP-OLmodelresultsinmuchhighervariabilityinthenumberofactiveowsinheavyloadconditions.Again,thisisbecausetheTCP-OLmodeldoesnotreducetheowarrivalrateuponcongestion.ThenumberofactiveowsintheTCP-CLmodel,ontheotherhand,isalwaysboundedbyN.Theincreasedvariabil-ityinthenumberofactiveowswiththeTCP-OLmodelmeansthattheper-owthroughputwiththatmodelislesspredictablethanwithTCP-CL.10CongestionResponsivenessSofarwehavefocusedonthesteady-statebehaviorofthetwomodels.Inthissection,weexaminetheirtransientresponsetoindividualcongestionevents.Werefertoatrafcaggregateascongestionresponsiveifitreducesitsofferedloaduponoverloadtoapointthatthereisnolongercongestion.ThespeciccongestioneventthatweconsiderhereisaperiodicUDPstreamwithratethatishigherthantheavailablecapacityinthebottleneck.GiventhattheUDPstreamdoesnotreacttocongestion, theeventthatwesimulaterepresentsasuddenreductionoftheavailablecapacityfortheTCPaggregatefromCtoC0=(1f)C,wherefCistherateoftheUDPstream.Inthefollowing,wemaketheofferedloadCbeforethecongestioneventtobeatthesamelevelintheTCP-OLandTCP-CLmodels.Weset1f1,sothatthebottle-neckbecomescongestedwhentheUDPstreamstarts.100200300400Time (sec.)3040506070Offered Load (Mbps)TCP-OLTCP-CL15Mbps UDP Stream Figure12.Theresponseofthetrafcag-gregateintheTCP-OLandTCP-CLmodels,whenacongestioneventiscausedbyaUDPstreamofrate15Mbps.Thecapacityis50Mbpsandtheofferedload(beforethecon-gestionevent)is47.5Mbps.Figure12showstheofferedloadfromthetwotrafcmodelsin1-secintervals.Thecongestioneventiscausedbya15MbpsCBRUDPstreamanditlastsfrom200secto275sec.Theeffectsofthecongestioneventcanbeex-aminedinthreestages:rst,justafterthecongestioneventstarts,second,duringthecongestionevent,andthird,afterthecongestioneventnishes.Beforethestartofthecongestionevent,bothTCP-OLandTCP-CLhavethesameaverageofferedload.TheirresponsewhentheUDPstreamstartsisthat,becauseofTCP'scongestioncontrol,thetrafcfrombothmodelsdropsatalevelthatisclosetothenewavailablecapacity(35Mbps).Thesimilaritybetweenthetwomodels,how-ever,endsthere.AfewsecondslatertheofferedloadintheTCP-OLmodelstartsincreasing,asmoreandmorenewowsarriveandcompeteforthroughput.TheofferedloadintheTCP-CLmodel,ontheotherhand,isself-regulatedattheleveloftheavailablecapacity,becauseanewowcan-notstartunlessanexistingowhascompleted.Thus,thenumberofactiveowsintheTCP-OLmodelkeepsincreas-ing,whilethecorrespondingnumberintheTCP-CLmodelstaysroughlythesame(alsoseeFigure13).Finally,afterthecongestioneventends,theofferedloadfrombothmodelsincreasestocapturetheavailablecapacitythathasbeenreleasedbytheUDPstream.IntheTCP-CLmodel,thisprocessiscompletedwithinafewseconds.IntheTCP-OLmodel,however,thereisalargebacklogofac-tiveowsthatneedstobeclearedbeforetheofferedloadreturnsatitspre-congestionlevel.AsFigure13shows,thiseffectlastsforhundredsofseconds(thisdependsofcourseonthedurationandmagnitudeofthecongestioneventandontheTCPofferedloadbeforecongestion).Figure13fur-thershowsthequeueingdelayinthebottleneckwitheachmodel.Noticethateventhoughthecongestioneventendsatt=275sec,thequeueremainsalmostfullforhundredsofsecondswiththeTCP-OLmodel.1001502002503003504000500100015002000Num. of Active FlowsTCP-OLTCP-CL100150200250300350400Time (sec)00.020.040.060.08Queuing Delay (sec.)15Mbps UDP streamFigure13.ThetimeseriesofthenumberofactiveowsandofthequeueingdelaywiththeTCP-OLandTCP-CLmodelswhenacongestioneventiscausedbyaCBRUDPstream.enifthelong-termofferedloadatalinkisbelowthecapacity,therecanbeoverloadeventsthatlastforafewtensofseconds.Theimportantlessonfromthepreviousdiscussionisthatduringsucheventsanopen-looptrafcaggregateiseffectivelycongestionunresponsivedespitethefactthatitconsistsofTCPows.Further,theconsequencesofanexternallyimposedcongestionevent(sayalargeUDPstreamoraDOSattack)canlastformuchlongerthanthedurationoftheeventitself,ifthetrafcisopen-loop.11DiscussionInthispaper,weexaminedtwobasicmodelsofnon-persistentowarrivals,andexplainedhowtheyleadtodif-ferenttrafccharacteristics,intermsofofferedload,vari-abilityindifferenttimescales,queueingperformance,num-berofactiveows,congestionresponsivenessandelastic-ity.Inthefollowing,wediscusssomemoreimplicationsofthisworkinotherareasofnetworkingresearchandpractice.AQMandnetworkstability:Activequeuemanage-ment(AQM)mechanisms,suchasRED,REM,PIcon-trollers,etc.,havebeenproposedasawaytostabilizecon-gestioncontrol.Itisimportanttonotethatsuchstudiesas-sumepersistentTCPconnections.Withthatmodel,AQM mechanismscancontrolthequeuelengthandthebottle-necklinkutilization.TheeffectivenessofAQMmecha-nismswithnon-persistenttrafc,however,ismuchlessun-derstood.TheofferedloadofTCP-OLtrafcdoesnotde-pendonnetworkstate.AQMmechanismscannotregulatesuchanaggregate,andtheyareunabletoavoidpersistentoverloadiftheofferedloadexceedsthecapacity.Isadmissioncontrolnecessary?Severalresearchersadvocatetheuseofadmissioncontrolastheonlywaytoregulatetheofferedloadandavoidcongestioncollapse.Weagree,ifthetrafcismostlyOL.Withoutadmissioncontrol,theonlywaytoavoidcongestioncollapseistoexpectthatuserswillbeimpatientandabandonslowongoingtransfers.Admissioncontrolcanlimitthenumberofactivesessionsorowsinthenetwork.Admissioncontrolmaynotbenec-essary,however,ifmostofthetrafcfollowstheCLmodel.TCP-friendlycongestioncontrol:TheuseofTCP-friendlycongestioncontrolhasbeenencouragedinallnon-TCPprotocolsandapplications.ThebasicmotivationforsuchproposalsisthatTCP-friendlytransferscanavoidcon-gestioncollapse.Itshouldbeclearhowever,thatevenifatrafcaggregateconsistsentirelyofTCPows,itcanstillcausecongestioncollapseorpersistentoverloadifitisOL.ThesameisobviouslytrueforTCP-friendlytrafc.There-fore,theuseofTCP-friendlycongestioncontrolisnotsuf-cienttoguaranteestability.Trafcengineeringandnetworkprovisioning:Traf-cengineering,aswellasotherprovisioningmecha-nisms,requireanestimatefortheofferedloadbetweenanyingress/egresspair.Furthermore,suchmechanismsassumethatifagiventrafcaggregateisswitchedfromoneroutetoanother,thenthethroughputofthataggregatewillnotchange.ThisassumptionisnottrueforTCP-CLtrafc.TheofferedloadfromsuchaggregatesdependsontheRTTandlossrateintheunderlyingpath.Ontheotherhand,theof-feredloadfromTCP-OLtrafcdoesnotdependontheun-derlyingpath(ignoringretransmissions),makingsuchtraf-cconsistentwithcommonassumptionsintrafcengineer-ing.Sessionlayercongestioncontrol:Atthemorepracti-calside,werecommendthatallnetworkapplicationsusesomeformofcongestioncontrolatthesessionlayer.Thiscanbeassimpleasadoptingoneofthefollowingrules:donotgenerateanewsessionuntiltheprevioussessionhascompleted,slowdownthegenerationofnewsessionsifthenetworkiscongested,ordonotkeepmorethanacertainnumberofsessionsactive.Itisalsoimportantthatsessionlayercongestioncontrolisimplementedinapplicationsthatgeneratetransfersautomatically,withoutuserintervention.Forexample,NNTPserverstransfernewstotheirpeerspe-riodically,independentofwhethertheunderlyingnetworkiscongestedornot.Effectively,suchapplicationsgenerateTCP-OLtrafc.References[1]A.BondiandW.Whitt.TheInuenceofService-TimeVari-abilityinaClosedNetworkofQueues.PerformanceEvalu-ation,6:219–234,1986.[2]A.BergerandY.Kogan.DimensioningBandwidthforElas-ticTrafcinHigh-SpeedDataNetworks.IEEE/ACMTrans.onNetworking,8(5):643–654,2000.[3]T.Bonald,P.Olivier,andJ.Roberts.DimensioningHighSpeedIPAccessNetworks.In18thITC,2003.[4]G.deVeciana,T.Lee,andT.Konstantopoulos.StabilyandPerformanceAnalysisofNetworksSupportingServices.IEEE/ACMTrans.onNetworking,9(1),2001.[5]A.DhamdhereandC.Dovrolis.BufferSizingforCongestedInternetLinks.InIEEEInfocom,2005.[6]A.Feldmann.CharacteristicsofTCPConnectionArrivals.TechnicalReport,AT&TLabsResearch,1998.[7]S.B.Fredj,T.Bonald,A.Proutiere,G.Regnie,andJ.W.Roberts.StatisticalBandwidthSharing:AStudyofCon-gestionatFlowLevel.InACMSigcomm,2001.[8]D.Heyman,T.V.Lakshman,andA.L.Neidhardt.ANewMethodforAnalysisFeedback-BasedProtocolswithAp-plicationstoEngineeringWebTrafcovertheInternet.InACMSigmetrics,1997.[9]M.JainandC.Dovrolis.End-to-endEstimationoftheAvail-ableBandwidthVariationRange.InACMSigmetrics,2005.[10]Y.Joo,V.Riberio,A.Feldmann,A.Gilbert,andW.Will-inger.TCP/IPtrafcdynamicsandnetworkperformance:Alessoninworkloadmodeling,owcontrol,andtracedrivensimulations.ACMCCR,Apr2001.[11]F.P.Kelly,A.Maulloo,andD.Tan.RateControlinCom-municationNetworks:ShadowPrices,ProportionalFairnessandStability.JournaloftheOperationalResearchSociety,49:237–252,1998.[12]A.A.KheraniandA.Kumar.StochasticModelsforThroughputAnalysisofRandomlyArrivingElasticFlowsintheInternet.InIEEEInfocom,2002.[13]L.Kleinrock.Time-sharedSystems:ATheoreticalTreat-ment.JournaloftheACM,14(2):242–261,1967.[14]S.KunniyurandR.Srikant.Stable,Scalable,FairCon-gestionControlandAQMSchemesthatAchieveHighUti-lizationintheInternet.IEEETrans.onAutomaticControl,49:2024–2029,2004.[15]S.H.Low,F.Paganini,J.Wang,S.Adlakha,andJ.Doyle.DynamicsofTCP/REDandaScalableControl.InIEEEInfocom,2002.[16]R.S.PrasadandC.Dovrolis.MeasuringtheCongestionResponsivenessofInternetTrafc.InPAM,2007.[17]J.Roberts.ASurveyonStatisticalBandwidthSharing.ComputerNetworks,45:319–332,2004.[18]B.Schroeder,A.Wierman,andM.Harchol-Balter.ClosedVersusOpen:ACautionaryTale.InNSDI,2006.[19]X.Tian,J.Wu,andC.Ji.AUniedViewofHeterogeneousNetworkTrafc:ImpactofNetworkLoad.InIEEEInfo-com,2002.[20]Y.Zhang,S.Kang,andD.Loguinov.DelayedStabilityandPerformanceofDistributedCongestionControl.InACMSigcomm,2004.