Exploring Device-to-Device Communication for Mobile Cloud Computing

Size: px
Start display at page:

Download "Exploring Device-to-Device Communication for Mobile Cloud Computing"

Transcription

1 Explorng Devce-to-Devce Communcaton for Moble Cloud Computng YujnL,LeSun,andWenyeWang Department of Electrcal and Computer Engneerng North Carolna State Unversty, Ralegh, NC, USA. Abstract Wth the popularty of smartphones and exploson of moble applcatons, moble devces become the prevalent computng platform for convenent communcaton and rch entertanment. Moble cloud computng(mcc) s proposed to overcome the lmted resources of moble systems. However, when users access MCC through wreless networks, cellular network s lkely to be overloaded and W-F connectvty s ntermttent. Therefore, devce-to-devce(d2d) communcaton s exploted as an alternatve for MCC. An mportant ssue n explorng D2D communcaton for MCC s how users can detect and utlze the computng resources on other moble devces. In ths paper, we propose two moble cloud access schemes: optmal and perodc access schemes, and study the correspondng performance of moble cloud computng(.e., moble cloud sze, node s servceable tme percentage, and task success rate). We fnd that optmally, node s servceable tme percentage and task success rate approach 1. Usng more practcal perodc access scheme, node s servceable tme percentage and task success rate are determned by the rato of contact and nter-contact tme between two nodes. I. INTRODUCTION Moble devces(such as smartphones and tablets) are becomng an nseparable part of our lves for convenent communcaton and entertanment. Wth the popularty of moble devces, there s also an exploson of moble applcatons n varous categores, such as terrestral navgaton, emal and web browsng, moble games, moble healthcare, moble commerce, and socal networkng. Ths ndcates that moble devces are quckly becomng the domnant computng platform, whch enables seamless work or entertanment for users regardless of user moblty. Nonetheless, moble systems are stll lmted n ther resources(e.g., processor power, storage sze, and battery lfe) and communcatons(e.g., bandwdth, connectvty, and securty)[1]. Such resource scarceness sgnfcantly hnders the development of moble applcatons and the mprovement of moble servce qualtes. Recently, ths problem has been addressed by researchers through moble cloud computng(mcc). MCC provdes servces for resource constraned moble devces to partton and offload ther computatonally ntensve and storage demandng jobs to the cloud wth vast computatonal resources[2]. In moble cloud computng, computng-ntensve moble applcatons, such as vdeo decodng, speech recognton, and augmented realty, can to be offloaded to the cloud for processng. Ths work s supported by the NSF Award CNS Computaton offloadng can save energy and mprove performance of moble applcatons thereby overcomng lmted resource capactes of moble devces. MCC can also enable moble users to store/access large data on the cloud through wreless networks, whch can save data storage capacty and processng power on moble devces. In MCC, moble users need access computng servces on the cloud through hgh-speed and ubqutous wreless connecton. The computatonal resources n the cloud are feasble only f the nformaton exchange between the cloud and moble devces through wreless networks s fast, relable, and secure. The most wdely used network access technologes are cellular and W-F networks. Cellular network provdes the nearubqutous coverage. But cellular network s under sgnfcant pressure and lkely to be overloaded due to the ncreasng moble data traffc[3], whch may ncur long latences and slow data transfers. Although W-F has hgh data rate, W-F connectons are ntermttent. Hence, the drawback of moble cloud computng s that the performance of cloud servces depends strongly on wreless communcaton networks. In order to overcome the drawbacks of accessng MCC through cellular and W-F networks, devce-to-devce(d2d) communcaton s exploted for moble cloud computng whle avodng global network bottlenecks[4]. The ncreasng densty of moble devces produces an abundance of contact opportuntes[5]. When offloadng to remote clouds fals n low connectvty scenaros, moble devces can employ local resources on moble devces n the vcnty for computng a shared task. By explotng D2D communcaton, users could mprove the performance of moble cloud computng n terms of computng speedup and money savng on smartphone dataroamng charges[4, 6, 7]. An mportant ssue n explorng D2D communcaton for MCCshowuserscanaccessthecomputngresourceson other moble devces. Because of user moblty, D2D connecton s ntermttent. Under such ntermttent connectvty, access scheme needs to be carefully developed such that users can utlze computng resources of nearby moble devces as muchaspossblewhlenotwastngtoomuchenergyondevce dscovery. In ths paper, we propose two access schemes,.e., optmal and perodc access algorthms, n whch the ntator optmally or perodcally performs node dscovery, subtask dstrbuton and retreval wth or wthout knowledge of other nodes moblty, respectvely. We study the followng MCC performance metrcs under

2 both access schemes: moble cloud sze, servceable tme percentage, and task success rate. More specfcally, moble cloud sze s the number of nodes that an ntator dscovers and utlzes for computng; servceable tme percentage s the percentage of tme that a devce computes tasks for an ntator; tasksuccessratestheprobabltythatatasktransmttedtoa devce s executed and successfully retreved by the ntator. Optmal access scheme provdes the optmal performance of MCC based on D2D communcaton. Usng perodc access scheme, performance of moble cloud s greatly affected by contact and nter-contact tme between two nodes. The more frequent a node meets the ntator and the longer ther contacts are, the hgher the node s servceable tme percentage and the task success rate are. The remander of ths paper s organzed as follows. We present a succnct summary on the exstng work n Secton II. We gve the network model, contact process, and access schemes n Secton III. The performance of MCC s analyzed nsectoniv.weconcludensectonv. II. RELATED WORK Wth the support of cloud computng of varous servces for moble users, moble cloud computng(mcc) s ntroduced to facltate moble users to take full advantages of cloud computng. Moble users can access cloud servces through wreless networks, ncludng cellular and W-F networks. However, the ncreasng moble data traffc has put a sgnfcant stran on cellular network[3]. Overloaded cellular network may ncur long latences and slow data transfers, whch make the data uploadng and downloadng expensve. At the same tme, W- F connecton coverage s ntermttent. In order to access cloud computng seamlessly, D2D communcaton s proposed to assst exstng wreless communcaton systems. Marnell [4] ponts out that n many cases, processng moble data(such as sensor logs and multmeda data) n-place and transferrng t drectly between smartphones would be more effcent and less susceptble to network lmtatons than offloadng data and processng to remote servers. Therefore, Marnell develops Hyrax, a platform derved from Hadoop that supports cloud computng on Androd smartphones. A central server wth access to each moble devce coordnates data and jobs and smartphones communcate wth each other on an solated 82.11g network. Although the performance of HyraxspoorforCPU-boundtasks,tsshowntotolerate node-departure and offer reasonable performance n data sharng. A dstrbuted multmeda search and sharng applcaton s mplemented to qualtatvely evaluate Hyrax. Smlarly, Huerta-Canepa and Lee[8] observe that moble devces can be a vrtual cloud computng provder because ther pervasveness means the ncreasng avalablty of nearby devces; they are more powerful over the tme; they nclude dfferent network nterfaces allowng devces to communcate wtheachother(wthnomoneycost);moreovertheyallowus to create communtes n whch we can execute shared tasks. Huerta-Canepa and Lee propose a vrtual cloud computng platform, n whch a context manager montors the locaton andnumberofnearbydevces.akoreanocrthatreadsan mage, scans for the Korean characters, and then presents a Romanze verson of them was developed for testng purposes. Paper[6] proposes a framework that uses local resources on moble devces for computng when offloadng to remote clouds fals n low connectvty scenaros. Experments are conducted n Bluetooth transmsson and an ntal prototype s also presented. The authors also dscuss a prelmnary analytcal model to determne whether or not a speedup wll be possble n offloadng. Sh et al.[7] nvestgates the scenaro that a moble devce uses the avalable, potentally ntermttently connected, computaton resources of other moble devces to mprove ts computatonal experence, e.g., mnmzng local power consumpton and/or decreasng computaton completon tme. The authors propose and mplement Serendpty on moble devces to leverage the frequent contacts between moble devces n order to speedup computng and conserve energy. A speech-to-text applcaton s mplemented to evaluate Serendpty, showng that Serendpty reduces job completon tme comparng wth executng locally. The authors also mplement a prelmnary prototype of Serendpty on the Androd platforms wth two computatonally complex applcatons(.e., a face detecton applcaton and a speechto-text applcaton). One fundamental ssue n usng moble devces for cloud computng s that an ntator needs to frst detect moble devces n proxmty, then perform task dstrbuton and retreval. Therefore, we propose two access schemes n ths paper and study moble cloud computng performance under them. III. MODELS AND DEFINITIONS Assumethat nmobledevcesaremovngnanetwork Ω n = [, n λ ], where λ s the spatal densty of moble users. Each moble devce has a transmsson radus r. Denote by X t = {X 1 (t),...,x n (t)}thepostonsofusersattme t. Nodes are movng accordng to Moblty Process M. We assumethatthemobltyprocessofanodesstatonaryand ergodcthatanode slocaton X ( )hasunformstatonary dstrbuton n the network area [9]. Moblty processes of nodes are ndependent and dentcally dstrbuted(..d.). Wthout loss of generalty, we assume that a moble user ntates to offload computatonal tasks to nearby moble devces attme.asshownnfg.1,thentatorcanconnecttonodes n ts transmsson range through drect D2D communcaton lnks, formng a moble cloud for computng. We assume that all nodes are wllng to support moble computng because of fast computaton of a common task or ncentves offered by the ntator. A. Contact Process Dynamcs: Apparently, node moblty affects connectvty of D2D communcaton. How frequently nodesmeetandhowlongtheystayconnectedaffectthesze and stablty of a moble cloud, n turn, nfluence the computngcapactyofamoblecloud.acontacteventbetweenapar ofusersoccurswhentwousersarecloseenoughtocommuncateandexchangecontentwtheachother.let X u (t)and X v (t)denotethelocatonsofusers uand vattme t,wecall

3 executedsubtasksfrom vattme t e.user vcanperformtask computatondurngthewholetme [t h,t e ]. Inrealty,tsdffcultforamobledevcetoobtanthe moblty nformaton of other devces due to prvacy ssue. A more practcal access scheme s the followng perodc access scheme, n whch an ntator moble devce perodcally performs devce detecton, task dstrbuton and retreval. Fg. 1. Devces n the proxmty form moble cloud. thatonecontactevent T C betweenusers uand voccursdurng [t,t 1 )f X u (t ) X v(t ) > rand X u(t) X v (t) r forall t [t,t 1 ),and X u (t 1 ) X v (t 1 ) > r.thenumber ofcontacteventsbetweenaparofuserswthntme tsa countng process called the contact process. We refer to the tme between the end and the start of two consecutve contact events between the same par of users as the nter-contact tme T I. As task dssemnaton and retreval can only be performed when there s a communcaton lnk between two nodes, contact and nter-contact tme between nodes affect moble cloud computng performance. Obtanng complete knowledge of contact processe can be extremely dffcult. Also mathematcally characterzng moble cloud computng performance s ntractable for arbtrary contact process. Thus, we assume that thecontactprocessofaparofuserssapossonprocess, whchhasbeenshowntobeagoodapproxmatonandused by other exstng studes [1, 11]. In other words, contact and nter-contact tme follow exponental dstrbutons wth parameters λ C and λ I,respectvely. B. Moble Cloud Access Schemes: In order to enable moble cloud, an ntator moble devce frst needs to dscover devces n proxmty. Then, the ntator can dspatch/retreve tasks to/from moble devces for MCC. Clearly, how an ntator detects other devces and employs them for computng determne moble cloud performance. Hence, we gve two moble cloud access schemes n the followng. Ideally, f an ntator has perfect knowledge of ts future contact wth other devces, the ntator can maxmally explot other devces for computng, resultng n the optmal performance of moble cloud. Therefore, we propose an optmal access scheme to evaluate the optmal performance of MCC based on D2D communcatons. Defnton 1(Optmal Access Scheme). Intally, a moble devce uhasataskthatneedstobecomputedwthntme τ.denoteby t h ( t h τ)thefrsthttngtmewhen ntator ufrstmeetsuser vwthntmeperod [,τ],and t e ( t e τ)thelastexttmethat uand vareoutofeach other stransmssonrangedurng [t e,τ].user uparttonsthe task,sendssomesubtasksto vattme t h,andretrevesthe Defnton 2(Perodc Access Scheme). Intator u perodcallyscanstsneghborngdevces.supposeat t,thesetofts neghborss N t = {v 1,...,v k }.Node uwllsendasubtask toeachoftsneghbors.attme t+, udetectstsneghbors N t+ = {v 1,...,v k }.Ifnode v k N t, uwllretrevethe subtasksentto v k attme tandsendanewsubtaskto v k for process;otherwse, uwllsendasubtaskto v k. Note that the node dscovery nterval depends on subtask computaton tme and devce s battery level. If battery s suffcent, hgh node dscovery frequency would ensure better utlzaton of moble cloud. When, an ntator can use a moble devce for computng durng all ther contact tme.ifbatterylevelslow,large canreduceenergyconsumpton wth performance compromse. A reasonable settng s lettng equal to the computatonal tme of a subtask, whch endures lttle performance compromse wthout too much energy consumpton. In ths paper, we assume equal tothecomputatonaltmeofasubtaskforouranalyss.in addton, f an ntator has multple neghbors n proxmty, t can use multple access scheme(e.g.,[12]) to dspatch and retrevesubtaskstoallofthematthesametme. C. Moble Cloud Performance Crtera: We seek to evaluate the D2D computng performance n terms of the sze of moble cloud, and the percentage of a moble devce s servceable tme, and the success rate of a task computaton. Moble cloud sze s the number of moble devces that an ntator detects wthn task delay tolerance τ. Servceable tme percentage s defned as the percentage oftmethatamobledevcesemployedbyanntator to provde computng servces. Task success rate represents the probablty that an ntatorcansuccessfullysendatasktoamobledevcefor computng and retreve the task back before t expres. IV. MOBILE CLOUD PERFORMANCE ANALYSIS We analyze the performance of moble cloud (.e., moble cloud sze, servceable tme percentage, task success rate) under optmal and perodc access schemes, respectvely. Analyss results under optmal and perodc access schemes wll provde the optmal and achevable cloud computng performance based on D2D communcaton, respectvely. A. Optmal Access Scheme Under optmal access scheme, an ntator can employ every node that t meets for cloud computng. Thus, moble cloud szesthenumberofmobledevcesthatanntatormeets wthntaskdelaytolerance τ.denoteby N o τ themoblecloud sze,andwehavethefollowngtheoremon N o τ.

4 ( Theorem1. [ Themoblecloudsze ( ) ]) Nτ o followsbnomal n 1, 1 1 πr2 e λiτ. Proof: Assume at t =, there are N nodes n an ntator s transmsson range, moble cloud sze ncrement Nτ o N sthesuperpostonof n N 1numberof-1 processes 1 { TI f τ},where T I stheresdualnter-contacttme. n N 1 n N Nτ o = N + 1 { TI f τ} = n { f TI>τ}. Itsworthnotngthat N sarandomvarabledependngon ntalnodedstrbutonnthenetwork.rgorously, P(Nτ o = k) = E(P(Nτ o = k N ))and E(Nτ o ) = E(E(Nτ o N )). Therefore, Nτ o s determned by the ntal node dstrbuton and the resdual nter-contact tme between two nodes. In homogeneous ( ) networks, N satsfes P(N = m) = m ( n 1 m.then, ( m n 1 πr ) 2 1 ) πr2 k ( ) πr P(Nτ o = k) = ( m n 1 2 m ) n 1 m ) (1 πr2 m=1 ) k m ( ( n m 1 k m (F ) fti (τ) 1 F fti (t) ( )) πr = ( n 1 2 k k ) + F TI f(τ) (1 πr2 ) n 1 k ( (1 πr2 n k 1 1 F fti (τ)), ) n k 1 whchsabnomaldstrbutonwthparameters ( ) n 1and πr 2 + F TI f(τ) 1 πr2,where F fti (τ) = P( T I τ).thus, ( ) ) πr E(Nτ o 2 ) = (n 1) (1 + πr2 F fti (τ). (1) Thedenstyfunctonof T I s λ I [1 F TI (x)],where F TI (x) sthecdfof T I and λ 1 I = x F TI (dx) = (1 F TI (x))dx.whenthenter-contacttme T I followsexponentaldstrbutonwthparameter λ I, T I sdentcallydstrbuted wth T I.Hence,wecompleteourproof. Under the optmal access scheme, an ntator can schedule tosendsubtaskstoothermobledevcesnadvancesothat theycanperformcomputngevenwhentheyarenotncontact wth the ntator. Thus, the servceable tme for a moble devcesfromthefrsthttngtme t h tothelastexttme t e. Inotherwords,theservceabletmepercentages (t e t h )/τ, for t h t e τ. Theorem 2. The servceable tme percentage of a node s shownneq.(2),whchsapproachng 1when τslarge. Proof: In a contact process between two nodes, denote by ξ(t) = 1whentwonodesarencontactattme t, ξ(t) = otherwse. ()When ξ() = ξ(τ) = 1, t h = and t e = τ.clearly,ts servceabletme ST o τ = τ. ()When ξ() = and ξ(τ) = 1, t h = T I and t e = τ. ST o τ = τ T I 1 { f TI<τ}. ()When ξ() = 1and ξ(τ) =, t h = and t e = τ T I, where T I s the backward recurrence tme of T I. ST o τ = τ T I 1 { c TI<τ}. (v) When ξ() = and ξ(τ) =, f the ntatornever encounters the node wthn tme τ, the node s servceable tme s. Otherwse, t h = T I and t e = τ T I. Thus, ST o τ = [τ ( T I + T I ) 1 { f TI+ c T I<τ} ] 1 { f T I<τ}. Denote by π j (t) the equlbrum probablty, gven that ξ() =,that ξ(t) = j(,j =,1).Let p and p 1 denote P(ξ() = )and P(ξ() = 1),respectvely.Because T I and T C areexponentalrandomvarableswthparameters λ I and λ C,respectvely, T I and T I havethesamedstrbutonas T I, and T I + T I followserlang-2dstrbutonerlang(2,λ I ).Thus, E(ST o τ )/τ = τλ I e λiτ π (τ)p (2) + [1 + (π 1 (τ)p + π 1 (τ)p 1 + π (τ)p )e λiτ ] 1 λ I τ (1 e λiτ )(π 1 (τ)p + π 1 (τ)p 1 + 2π (τ)p ), where p 1 = πr2 and p = 1 p 1, and the equlbrum probablty π j (τ)canbedervedbasedoncox srenewal Theory(Chapter7.4)[13]: π (τ) = β+γe βτ/λc, π 1 (τ) = γ γe βτ/λc, π 1 (τ) = β βe βτ/λc, and π 11 (τ) = γ + βe βτ/λc,where β = λc and γ = λi.when τ slarge, E(STτ o )/τ 1,.e.,themeanservceabletme percentage approaches 1 n the long run. Smlarly, when an ntator has full knowledge of ts contact and nter-contact events wth other devces, t can make sure dssemnatngtaskstoamobledevceonlyftheycanbe successfully retreved. Thus, the task success rate of optmal access scheme s 1. In practce, t s dffcult for an ntator to obtan full nformaton of ts contact wth other users. To make the optmal access scheme practcal, we can use the followng heurstc access scheme by explotng the regularty of human moblty. Human moblty shows a very hgh degree of temporal and spatal regularty[14] and can be predcted wth hgh probablty[15]. Beneftng from the predctablty of human moblty, an ntator u can estmate ts contact tme wth other users based on ther contact hstory. Heurstc Access Scheme: Intator u records the hstory of tscontactwthotherusersoveraperodoftmeandusesths nformatonfortaskcomputng.foragveperod [t,t+τ]of a day d, ntator u estmates ts contact and nter-contact tme (e.g.,frsthttngtme t h andlastexttme t e )wthauser v basedonmobltyhstoryofday d c,where csasmall nteger(usually1or2).then, uapplestheoptmalaccess scheme to utlze the computng resource of user v. Remark 1. When an ntator has pre-knowledge of node moblty or can predct other nodes moblty based on moblty hstory, an ntator can utlze computng resources on other devces through optmal or heurstc access schemes. Under the optmal access scheme, the expected number of nodes that an ntator can use wthn tme τ s (n

5 [ ( ] 1) 1 1 πr2 )e λiτ. The long-term servceable tme percentage and task success rate are approachng 1. B. Perodc Access Scheme Suppose an ntator perodcally detects devces n proxmty wth frequency 1/. Wthn tme [,τ], the ntator performs devce dscovery at tme {,,2,..., τ }. In otherwords,adevcesdetectedbythentatoronlyft s n contact wth the ntator for at least one tme pont of {,,2,..., τ }.Applyngrenewalprocesstheory,we derve the followng theorem on the sze of moble cloud. Theorem3. Themoblecloudsze N p τ followsbnomal ( n 1,1 P),where PcanbefoundnEq.(5). Proof:Ifadevcesnotdetectedbyanntatorwthn tme τ, t s n nter-contact wth the ntator at all tme ponts {,,2,..., τ }.Letusconsderthecontactprocess betweenanntatorandamobledevceandlet F TC (f TC ) and F TI (f TI )denotethedstrbuton(densty)functonsof the contact and nter-contact tme. Defne renewal functons H 2 (t) = F (n) T I F (n) T C (t)andrenewaldensty h 2 (t) = dh 2 (t)/dt,where F (n) (F (n) T C )sthe n-foldconvolutonof T I F TI (F TC )tself. Cox[13] derves the probablty that the system s at ntercontactstateattme t.condtonngonthentalstate ξ() = (.e., nter-contact state) IT (t) = 1 F TI (t) + (1 F TI ) H 2 (t). (3) Further, Baxter [16] derves the jont probablty that the system s at nter-contact state at m dstnct tme ponts {t 1,t 2,...,t m }.Let m = τ, t 1 =,...,t =,...,t m = τ, m 1 IT (m) (t 1,t 2,...,t m ) = R (t m t 1,t 1 ) + IT (t 1 ) t+1 t 1 t t 1 (4) φ (x,t 1 )IT (m ) (t +1 t 1 u,...,t m t 1 u)dx, and condtonng on ξ() = 1(.e., contact state) R (x,t) = 1 F TI (t+x)+ t φ (x,t) = 1 [ f TI (t + x) + IT (t) h 2 (u)(1 F TI (t+x u))du, t ] h 2 (u)f TI (t + x u)du. IT (m) (t 1,t 2,...,t m )canbecomputedrecursvelyfromeq. (3).Thus,theprobabltythatanodesnotdetectedbythe ntator s P = p IT (m) (t 1,t 2,...,t m ), (5) where p = 1 πr2.hence,thetotalnumberofnodesdetected by the ntator follows Bnomal dstrbuton wth parameters (n 1,1 P). ( ) Remark2. Clearly, P > 1 πr2 e λiτ.thus,themoble cloud sze under perodc access scheme s stochastcally domnated by that under optmal access scheme. Whenever an ntator senses a devce n proxmty, t transmts a subtask to the devce for computng, whch takes tme to fnsh. A devce computes all subtasks that t receves no matter whether the subtasks are retreved. Thus, thetotalservngtmeofadevces tmesthenumberof task transmssons. We have the followng theorem on the servceable tme percentage by studyng the number of task transmssons between an ntator and a devce. Theorem 4. A moble devce s servceable tme percentage s approachng when τslargeand ssmall. λ I Proof: Let us consder a contact event between an ntator andadevcedurng [t,t 1 ].Dvdng [t,t 1 ]ntotmeslots [t,t +],[t +,t +2],...,wehave (t 1 t )/ number ofsubntervalswtheachslotequalsto exceptthelastone. Durng each tme slot, the ntator must perform one and only one node detecton. In the best scenaro, the ntator performs nodedetectonandtransmtsthetasktoaneghboratthe begnnngofeachtmeslot,resultngn (t 1 t )/ number of task transmssons. In the worst scenaro, the ntator performs node detecton and transmts the task to a neghbor attheendofeachtmeslot,resultngn (t 1 t )/ number of task transmssons. Denoteby T C thecontacttmerandomvarableand the number of contacts between an ntator and a devce wthntmeduraton τ.therefore,thetotalnumberoftasksa devcecomputedsupperboundedby T C andlower boundedby T C.Hence,theservcetmesatsfes E T C E(STτ p ) E T C. Basedonrenewaltheory, condtonngonthental state ξ() = (.e., nter-contact state) E(N (τ)) = F TI (τ) + E(N 1 (τ)) = F TC (τ) + τ τ E(N (τ))df TI+T C (s); E(N 1 (τ))df TI+T C (s). Takng the Laplace transform of these two equatons, L E(N (τ))(s) = L TI (s)/s + L N (τ)(s)l TI+T C (s), L E(N 1 (τ))(s) = L TC (s)/s + L N 1 (τ)(s)l TI+T C (s). Because T C and T I haveexponentaldstrbutonswthparameters λ C and λ I,respectvely, L E(N (τ))(s) = λ I(s + λ C ) s 2 (s + λ I + λ C ), L E(N 1 (τ))(s) = λ C(s + λ I ) s 2 (s + λ I + λ C ). Takng the nverse Laplace transform, we then have E(N (τ)) = λ Iλ C τ λ 2 I + λ I + λ C (λ I + λ C ) 2 (1 e (λi+λc)τ ),

6 E(N 1 (τ)) = λ Iλ C τ λ 2 C + λ I + λ C (λ I + λ C ) 2 (1 e (λi+λc)τ ). Therefore, the expected number of contact between two nodes wthn tme duraton τ satsfes E() = E( I = )p + E( I = 1)p 1, (6) = λ Iλ C τ λ I + λ C + p λ 2 I + p 1λ 2 C (λ I + λ C ) 2 (1 e (λi+λc)τ ), where p 1 = πr2 and p = 1 p 1. Applyng ths result to the servce tme, we have E()[E(T C ) ] E(ST p τ ) E()[E(T C ) + ]. When τbecomeslargeand ssmall, E(STτ p ) λ I lm =. (7) τ, τ λ I + λ C Remark 3. Usng the perodc access scheme, an ntator can λ utlze a moble devce for approxmately I percentage oftme,whchsdetermnedby λc λ I.Thelongeradevceand an ntator are n contact and the more frequently they meet, the hgher utlzaton of the devce s computng resources s. After an ntator dspatches a subtask to a moble devce, t can retreve ths subtask f the ntator detects the moble devce agan before the task expres. Suppose the ntator detectsamobledevce M τ tmesdurngtmeperod τ,the ntator only fals to retreve the last dspatched subtask. Hence, the task success rate s 1 1/M τ. Followng ths methodology, we have the followng theorem on the task success rate. Theorem 5. Task success rate satsfes P p s 1 1 E()( 1 (8) λ C + 1). Proof:Todervethetasksuccessrate,weneedtofndout the total number of transmtted subtasks from an ntator to a moble devce. From our proof of servceable tme percentage, we have E T C E(M τ ) E T C. Asthenversefunctonsconvexonthenterval (,+ ),the task falure rate satsfes ( ) 1 E 1/E T C 1 M τ E()( 1 λ + 1), C where E()canbefoundnEq.(6).Hence,wehavethe tasksuccessrateneq.(8). Remark 4. Usng perodc access scheme, the task success rate supperboundedbyafunctonof τ, λ I, λ C,and.Themore frequently an ntator meets a devce and the longer they stay n contact, the closer ths upper bound approaches 1. V. CONCLUSION In ths paper, we have studed the performance of moble cloud computng based on D2D communcaton, n whch an ntator dstrbutes tasks to other nearby devces and retreves tasks after executon. We propose optmal and perodc access schemes that an ntator detects devces n proxmty and dstrbutes tasks to them for computng optmally or perodcally. Optmal access scheme results n optmal moble cloud performance wth servceable tme percentage and task success rate approachng 1. Usng more practcal perodc access scheme, an ntator moble devce can employ a moble λ I devce for computng n percentageoftme,andthe tasksuccessratesupperboundedbyafunctonof λ I and λ C. In summary, moblty patterns of users have sgncant mpact on performance of moble cloud, whch can be measured by λ C λi.inourfuturework,wewllusemobleapplcatonsto evaluate the moble cloud computng performance. REFERENCES [1] A. K. Gupta, Challenges of moble computng, n 2nd Natonal Conference on Challenges& Opportuntes n Informaton Technology(COIT-28),(Mand Gobndgarh), 28. [2] N. Fernando, S. W. Loke, and W. Rahayu, Moble cloud computng: A survey, Future Generaton Computer Systems, vol.29,no.1,pp.84 16,213. [3] A.Ajaz,H.Aghvam,andM.Aman, Asurveyonmobledata offloadng: techncal and busness perspectves, IEEE Wreless Communcatons, vol. 2, no. 2, pp , 213. [4] E. E. Marnell, Hyrax: Cloud computng on moble devces usng mapreduce, Master s thess, Carnege Mellon Unversty, 29. [5] S. Lu and A. D. Stregel, Explorng the potental n practce for opportunstc networks amongst smart moble devces, n Proc. of the ACM MobCom, 213. [6] N. Fernando, S. Loke, and W. Rahayu, Dynamc moble cloud computng: Ad hoc and opportunstc job sharng, n Proc. of IEEE UCC, 211. [7] C. Sh, V. Lakafoss, M. H. Ammar, and E. W. Zegura, Serendpty: enablng remote computng among ntermttently connected moble devces, n Proc. of ACM MobHoc, 212. [8] G. Huerta-Canepa and D. Lee, A vrtual cloud computng provder for moble devces, n ACM Workshop on Moble Cloud Computng& Servces(MCS 1), 21. [9] L.SunandW.Wang, Onlatencydstrbutonandscalng:from fnte to large cogntve rado networks under general moblty, n Proc. of IEEE INFOCOM, 212. [1] Y.LandW.Wang, Theunheraldedpowerofcloudletcomputng n the vcnty of moble devces, n Proc. of IEEE GLOBECOM, 213. [11] Y. L and W. Wang, Can moble cloudlets support moble applcatons?, n Proc. of IEEE INFOCOM, 214. [12] R. Mao and H. L, A novel multple access scheme va compressed sensng wth random data traffc, Journal of Communcatons and Networks, vol. 12, no. 4, pp , 21. [13] D.Cox,RenewalTheory.Methuen&Co,1962. [14] Y. L, M. Zhao, and W. Wang, Internode moblty correlaton for group detecton and analyss n vanets, Vehcular Technology, IEEE Transactons on, vol. 62, no. 9, pp , 213. [15] M. C. Gonzalezl, C. A. Hdalgo1, and A.-L. Barabás, Understandng ndvdual human moblty patterns, Letters to Nature, 28. [16] L. A. Baxter, Avalablty measures for a two-state system, Journal of Appled Probablty, vol. 18, no. 1, 1981.

Performance Analysis of Energy Consumption of Smartphone Running Mobile Hotspot Application

Performance Analysis of Energy Consumption of Smartphone Running Mobile Hotspot Application Internatonal Journal of mart Grd and lean Energy Performance Analyss of Energy onsumpton of martphone Runnng Moble Hotspot Applcaton Yun on hung a chool of Electronc Engneerng, oongsl Unversty, 511 angdo-dong,

More information

denote the location of a node, and suppose node X . This transmission causes a successful reception by node X for any other node

denote the location of a node, and suppose node X . This transmission causes a successful reception by node X for any other node Fnal Report of EE359 Class Proect Throughput and Delay n Wreless Ad Hoc Networs Changhua He changhua@stanford.edu Abstract: Networ throughput and pacet delay are the two most mportant parameters to evaluate

More information

Efficient On-Demand Data Service Delivery to High-Speed Trains in Cellular/Infostation Integrated Networks

Efficient On-Demand Data Service Delivery to High-Speed Trains in Cellular/Infostation Integrated Networks IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, VOL. XX, NO. XX, MONTH 2XX 1 Effcent On-Demand Data Servce Delvery to Hgh-Speed Trans n Cellular/Infostaton Integrated Networks Hao Lang, Student Member,

More information

Fault tolerance in cloud technologies presented as a service

Fault tolerance in cloud technologies presented as a service Internatonal Scentfc Conference Computer Scence 2015 Pavel Dzhunev, PhD student Fault tolerance n cloud technologes presented as a servce INTRODUCTION Improvements n technques for vrtualzaton and performance

More information

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.

More information

Data Broadcast on a Multi-System Heterogeneous Overlayed Wireless Network *

Data Broadcast on a Multi-System Heterogeneous Overlayed Wireless Network * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 24, 819-840 (2008) Data Broadcast on a Mult-System Heterogeneous Overlayed Wreless Network * Department of Computer Scence Natonal Chao Tung Unversty Hsnchu,

More information

Enabling P2P One-view Multi-party Video Conferencing

Enabling P2P One-view Multi-party Video Conferencing Enablng P2P One-vew Mult-party Vdeo Conferencng Yongxang Zhao, Yong Lu, Changja Chen, and JanYn Zhang Abstract Mult-Party Vdeo Conferencng (MPVC) facltates realtme group nteracton between users. Whle P2P

More information

M3S MULTIMEDIA MOBILITY MANAGEMENT AND LOAD BALANCING IN WIRELESS BROADCAST NETWORKS

M3S MULTIMEDIA MOBILITY MANAGEMENT AND LOAD BALANCING IN WIRELESS BROADCAST NETWORKS M3S MULTIMEDIA MOBILITY MANAGEMENT AND LOAD BALANCING IN WIRELESS BROADCAST NETWORKS Bogdan Cubotaru, Gabrel-Mro Muntean Performance Engneerng Laboratory, RINCE School of Electronc Engneerng Dubln Cty

More information

A Replication-Based and Fault Tolerant Allocation Algorithm for Cloud Computing

A Replication-Based and Fault Tolerant Allocation Algorithm for Cloud Computing A Replcaton-Based and Fault Tolerant Allocaton Algorthm for Cloud Computng Tork Altameem Dept of Computer Scence, RCC, Kng Saud Unversty, PO Box: 28095 11437 Ryadh-Saud Araba Abstract The very large nfrastructure

More information

An Interest-Oriented Network Evolution Mechanism for Online Communities

An Interest-Oriented Network Evolution Mechanism for Online Communities An Interest-Orented Network Evoluton Mechansm for Onlne Communtes Cahong Sun and Xaopng Yang School of Informaton, Renmn Unversty of Chna, Bejng 100872, P.R. Chna {chsun,yang}@ruc.edu.cn Abstract. Onlne

More information

An Alternative Way to Measure Private Equity Performance

An Alternative Way to Measure Private Equity Performance An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate

More information

A 2 -MAC: An Adaptive, Anycast MAC Protocol for Wireless Sensor Networks

A 2 -MAC: An Adaptive, Anycast MAC Protocol for Wireless Sensor Networks : An Adaptve, Anycast MAC Protocol for Wreless Sensor Networks Hwee-Xan Tan and Mun Choon Chan Department of Computer Scence, School of Computng, Natonal Unversty of Sngapore {hweexan, chanmc}@comp.nus.edu.sg

More information

How To Understand The Results Of The German Meris Cloud And Water Vapour Product

How To Understand The Results Of The German Meris Cloud And Water Vapour Product Ttel: Project: Doc. No.: MERIS level 3 cloud and water vapour products MAPP MAPP-ATBD-ClWVL3 Issue: 1 Revson: 0 Date: 9.12.1998 Functon Name Organsaton Sgnature Date Author: Bennartz FUB Preusker FUB Schüller

More information

Dynamic Mobile Cloud Computing: Ad Hoc and Opportunistic Job Sharing

Dynamic Mobile Cloud Computing: Ad Hoc and Opportunistic Job Sharing 2011 Fourth IEEE Internatonal Conference on Utlty and Cloud Computng Dynamc Moble Cloud Computng: Ad Hoc and Opportunstc Job Sharng Nroshne Fernando 1, Seng W. Loke 2 and Wenny Rahayu 3 Department of Computer

More information

Reinforcement Learning for Quality of Service in Mobile Ad Hoc Network (MANET)

Reinforcement Learning for Quality of Service in Mobile Ad Hoc Network (MANET) Renforcement Learnng for Qualty of Servce n Moble Ad Hoc Network (MANET) *T.KUMANAN AND **K.DURAISWAMY *Meenaksh College of Engneerng West K.K Nagar, Cheena-78 **Dean/academc,K.S.R College of Technology,Truchengode

More information

On File Delay Minimization for Content Uploading to Media Cloud via Collaborative Wireless Network

On File Delay Minimization for Content Uploading to Media Cloud via Collaborative Wireless Network On Fle Delay Mnmzaton for Content Uploadng to Meda Cloud va Collaboratve Wreless Network Ge Zhang and Yonggang Wen School of Computer Engneerng Nanyang Technologcal Unversty Sngapore Emal: {zh0001ge, ygwen}@ntu.edu.sg

More information

"Research Note" APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES *

Research Note APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES * Iranan Journal of Scence & Technology, Transacton B, Engneerng, ol. 30, No. B6, 789-794 rnted n The Islamc Republc of Iran, 006 Shraz Unversty "Research Note" ALICATION OF CHARGE SIMULATION METHOD TO ELECTRIC

More information

Dynamic Pricing for Smart Grid with Reinforcement Learning

Dynamic Pricing for Smart Grid with Reinforcement Learning Dynamc Prcng for Smart Grd wth Renforcement Learnng Byung-Gook Km, Yu Zhang, Mhaela van der Schaar, and Jang-Won Lee Samsung Electroncs, Suwon, Korea Department of Electrcal Engneerng, UCLA, Los Angeles,

More information

An Adaptive Cross-layer Bandwidth Scheduling Strategy for the Speed-Sensitive Strategy in Hierarchical Cellular Networks

An Adaptive Cross-layer Bandwidth Scheduling Strategy for the Speed-Sensitive Strategy in Hierarchical Cellular Networks An Adaptve Cross-layer Bandwdth Schedulng Strategy for the Speed-Senstve Strategy n erarchcal Cellular Networks Jong-Shn Chen #1, Me-Wen #2 Department of Informaton and Communcaton Engneerng ChaoYang Unversty

More information

A Secure Password-Authenticated Key Agreement Using Smart Cards

A Secure Password-Authenticated Key Agreement Using Smart Cards A Secure Password-Authentcated Key Agreement Usng Smart Cards Ka Chan 1, Wen-Chung Kuo 2 and Jn-Chou Cheng 3 1 Department of Computer and Informaton Scence, R.O.C. Mltary Academy, Kaohsung 83059, Tawan,

More information

Cloud-based Social Application Deployment using Local Processing and Global Distribution

Cloud-based Social Application Deployment using Local Processing and Global Distribution Cloud-based Socal Applcaton Deployment usng Local Processng and Global Dstrbuton Zh Wang *, Baochun L, Lfeng Sun *, and Shqang Yang * * Bejng Key Laboratory of Networked Multmeda Department of Computer

More information

LAMOR: Lifetime-Aware Multipath Optimized Routing Algorithm for Video Transmission over Ad Hoc Networks

LAMOR: Lifetime-Aware Multipath Optimized Routing Algorithm for Video Transmission over Ad Hoc Networks LAMOR: Lfetme-Aware Multpath Optmzed Routng Algorthm for Vdeo ransmsson over Ad Hoc Networks 1 Lansheng an, Lng Xe, Kng-m Ko, Mng Le and Moshe Zukerman Abstract Multpath routng s a key technque to support

More information

Joint Scheduling of Processing and Shuffle Phases in MapReduce Systems

Joint Scheduling of Processing and Shuffle Phases in MapReduce Systems Jont Schedulng of Processng and Shuffle Phases n MapReduce Systems Fangfe Chen, Mural Kodalam, T. V. Lakshman Department of Computer Scence and Engneerng, The Penn State Unversty Bell Laboratores, Alcatel-Lucent

More information

An Efficient Recovery Algorithm for Coverage Hole in WSNs

An Efficient Recovery Algorithm for Coverage Hole in WSNs An Effcent Recover Algorthm for Coverage Hole n WSNs Song Ja 1,*, Wang Balng 1, Peng Xuan 1 School of Informaton an Electrcal Engneerng Harbn Insttute of Technolog at Weha, Shanong, Chna Automatc Test

More information

Backpressure Meets Taxes: Faithful Data Collection in Stochastic Mobile Phone Sensing Systems

Backpressure Meets Taxes: Faithful Data Collection in Stochastic Mobile Phone Sensing Systems Backpressure Meets Taxes: Fathful Data Collecton n Stochastc Moble Phone Sensng Systems Shusen Yang Imperal College Lodon Emal: s.yang9@mperal.ac.uk Usman Adeel Imperal College London Emal: u.adeel9@mperal.ac.uk

More information

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT Toshhko Oda (1), Kochro Iwaoka (2) (1), (2) Infrastructure Systems Busness Unt, Panasonc System Networks Co., Ltd. Saedo-cho

More information

Calculating the high frequency transmission line parameters of power cables

Calculating the high frequency transmission line parameters of power cables < ' Calculatng the hgh frequency transmsson lne parameters of power cables Authors: Dr. John Dcknson, Laboratory Servces Manager, N 0 RW E B Communcatons Mr. Peter J. Ncholson, Project Assgnment Manager,

More information

A Design Method of High-availability and Low-optical-loss Optical Aggregation Network Architecture

A Design Method of High-availability and Low-optical-loss Optical Aggregation Network Architecture A Desgn Method of Hgh-avalablty and Low-optcal-loss Optcal Aggregaton Network Archtecture Takehro Sato, Kuntaka Ashzawa, Kazumasa Tokuhash, Dasuke Ish, Satoru Okamoto and Naoak Yamanaka Dept. of Informaton

More information

When Network Effect Meets Congestion Effect: Leveraging Social Services for Wireless Services

When Network Effect Meets Congestion Effect: Leveraging Social Services for Wireless Services When Network Effect Meets Congeston Effect: Leveragng Socal Servces for Wreless Servces aowen Gong School of Electrcal, Computer and Energy Engeerng Arzona State Unversty Tempe, AZ 8587, USA xgong9@asuedu

More information

Optimization Model of Reliable Data Storage in Cloud Environment Using Genetic Algorithm

Optimization Model of Reliable Data Storage in Cloud Environment Using Genetic Algorithm Internatonal Journal of Grd Dstrbuton Computng, pp.175-190 http://dx.do.org/10.14257/gdc.2014.7.6.14 Optmzaton odel of Relable Data Storage n Cloud Envronment Usng Genetc Algorthm Feng Lu 1,2,3, Hatao

More information

An Ad Hoc Network Load Balancing Energy- Efficient Multipath Routing Protocol

An Ad Hoc Network Load Balancing Energy- Efficient Multipath Routing Protocol 246 JOURNA OF SOFTWAR, VO. 9, NO. 1, JANUARY 2014 An Ad Hoc Network oad alancng nergy- ffcent Multpath Routng Protocol De-jn Kong Shanx Fnance and Taxaton College, Tayuan, Chna mal: dejnkong@163.com Xao-lng

More information

Effective Network Defense Strategies against Malicious Attacks with Various Defense Mechanisms under Quality of Service Constraints

Effective Network Defense Strategies against Malicious Attacks with Various Defense Mechanisms under Quality of Service Constraints Effectve Network Defense Strateges aganst Malcous Attacks wth Varous Defense Mechansms under Qualty of Servce Constrants Frank Yeong-Sung Ln Department of Informaton Natonal Tawan Unversty Tape, Tawan,

More information

INVESTIGATION OF VEHICULAR USERS FAIRNESS IN CDMA-HDR NETWORKS

INVESTIGATION OF VEHICULAR USERS FAIRNESS IN CDMA-HDR NETWORKS 21 22 September 2007, BULGARIA 119 Proceedngs of the Internatonal Conference on Informaton Technologes (InfoTech-2007) 21 st 22 nd September 2007, Bulgara vol. 2 INVESTIGATION OF VEHICULAR USERS FAIRNESS

More information

Sangam - Efficient Cellular-WiFi CDN-P2P Group Framework for File Sharing Service

Sangam - Efficient Cellular-WiFi CDN-P2P Group Framework for File Sharing Service Sangam - Effcent Cellular-WF CDN-P2P Group Framework for Fle Sharng Servce Anjal Srdhar Unversty of Illnos, Urbana-Champagn Urbana, USA srdhar3@llnos.edu Klara Nahrstedt Unversty of Illnos, Urbana-Champagn

More information

Efficient Bandwidth Management in Broadband Wireless Access Systems Using CAC-based Dynamic Pricing

Efficient Bandwidth Management in Broadband Wireless Access Systems Using CAC-based Dynamic Pricing Effcent Bandwdth Management n Broadband Wreless Access Systems Usng CAC-based Dynamc Prcng Bader Al-Manthar, Ndal Nasser 2, Najah Abu Al 3, Hossam Hassanen Telecommuncatons Research Laboratory School of

More information

Luby s Alg. for Maximal Independent Sets using Pairwise Independence

Luby s Alg. for Maximal Independent Sets using Pairwise Independence Lecture Notes for Randomzed Algorthms Luby s Alg. for Maxmal Independent Sets usng Parwse Independence Last Updated by Erc Vgoda on February, 006 8. Maxmal Independent Sets For a graph G = (V, E), an ndependent

More information

A Novel Adaptive Load Balancing Routing Algorithm in Ad hoc Networks

A Novel Adaptive Load Balancing Routing Algorithm in Ad hoc Networks Journal of Convergence Informaton Technology A Novel Adaptve Load Balancng Routng Algorthm n Ad hoc Networks Zhu Bn, Zeng Xao-png, Xong Xan-sheng, Chen Qan, Fan Wen-yan, We Geng College of Communcaton

More information

Recurrence. 1 Definitions and main statements

Recurrence. 1 Definitions and main statements Recurrence 1 Defntons and man statements Let X n, n = 0, 1, 2,... be a MC wth the state space S = (1, 2,...), transton probabltes p j = P {X n+1 = j X n = }, and the transton matrx P = (p j ),j S def.

More information

What is Candidate Sampling

What is Candidate Sampling What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble

More information

Analysis of Energy-Conserving Access Protocols for Wireless Identification Networks

Analysis of Energy-Conserving Access Protocols for Wireless Identification Networks From the Proceedngs of Internatonal Conference on Telecommuncaton Systems (ITC-97), March 2-23, 1997. 1 Analyss of Energy-Conservng Access Protocols for Wreless Identfcaton etworks Imrch Chlamtac a, Chara

More information

An Adaptive and Distributed Clustering Scheme for Wireless Sensor Networks

An Adaptive and Distributed Clustering Scheme for Wireless Sensor Networks 2007 Internatonal Conference on Convergence Informaton Technology An Adaptve and Dstrbuted Clusterng Scheme for Wreless Sensor Networs Xnguo Wang, Xnmng Zhang, Guolang Chen, Shuang Tan Department of Computer

More information

J. Parallel Distrib. Comput. Environment-conscious scheduling of HPC applications on distributed Cloud-oriented data centers

J. Parallel Distrib. Comput. Environment-conscious scheduling of HPC applications on distributed Cloud-oriented data centers J. Parallel Dstrb. Comput. 71 (2011) 732 749 Contents lsts avalable at ScenceDrect J. Parallel Dstrb. Comput. ournal homepage: www.elsever.com/locate/pdc Envronment-conscous schedulng of HPC applcatons

More information

Methodology to Determine Relationships between Performance Factors in Hadoop Cloud Computing Applications

Methodology to Determine Relationships between Performance Factors in Hadoop Cloud Computing Applications Methodology to Determne Relatonshps between Performance Factors n Hadoop Cloud Computng Applcatons Lus Eduardo Bautsta Vllalpando 1,2, Alan Aprl 1 and Alan Abran 1 1 Department of Software Engneerng and

More information

Automated information technology for ionosphere monitoring of low-orbit navigation satellite signals

Automated information technology for ionosphere monitoring of low-orbit navigation satellite signals Automated nformaton technology for onosphere montorng of low-orbt navgaton satellte sgnals Alexander Romanov, Sergey Trusov and Alexey Romanov Federal State Untary Enterprse Russan Insttute of Space Devce

More information

Dimming Cellular Networks

Dimming Cellular Networks Dmmng Cellular Networks Davd Tpper, Abdelmounaam Rezgu, Prashant Krshnamurthy, and Peera Pacharntanakul Graduate Telecommuncatons and Networkng Program, Unversty of Pttsburgh, Pttsburgh, PA 1526, Unted

More information

Cooperative Load Balancing in IEEE 802.11 Networks with Cell Breathing

Cooperative Load Balancing in IEEE 802.11 Networks with Cell Breathing Cooperatve Load Balancng n IEEE 82.11 Networks wth Cell Breathng Eduard Garca Rafael Vdal Josep Paradells Wreless Networks Group - Techncal Unversty of Catalona (UPC) {eduardg, rvdal, teljpa}@entel.upc.edu;

More information

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure

More information

An RFID Distance Bounding Protocol

An RFID Distance Bounding Protocol An RFID Dstance Boundng Protocol Gerhard P. Hancke and Markus G. Kuhn May 22, 2006 An RFID Dstance Boundng Protocol p. 1 Dstance boundng Verfer d Prover Places an upper bound on physcal dstance Does not

More information

Traffic State Estimation in the Traffic Management Center of Berlin

Traffic State Estimation in the Traffic Management Center of Berlin Traffc State Estmaton n the Traffc Management Center of Berln Authors: Peter Vortsch, PTV AG, Stumpfstrasse, D-763 Karlsruhe, Germany phone ++49/72/965/35, emal peter.vortsch@ptv.de Peter Möhl, PTV AG,

More information

1. Fundamentals of probability theory 2. Emergence of communication traffic 3. Stochastic & Markovian Processes (SP & MP)

1. Fundamentals of probability theory 2. Emergence of communication traffic 3. Stochastic & Markovian Processes (SP & MP) 6.3 / -- Communcaton Networks II (Görg) SS20 -- www.comnets.un-bremen.de Communcaton Networks II Contents. Fundamentals of probablty theory 2. Emergence of communcaton traffc 3. Stochastc & Markovan Processes

More information

Master s Thesis. Configuring robust virtual wireless sensor networks for Internet of Things inspired by brain functional networks

Master s Thesis. Configuring robust virtual wireless sensor networks for Internet of Things inspired by brain functional networks Master s Thess Ttle Confgurng robust vrtual wreless sensor networks for Internet of Thngs nspred by bran functonal networks Supervsor Professor Masayuk Murata Author Shnya Toyonaga February 10th, 2014

More information

METHODOLOGY TO DETERMINE RELATIONSHIPS BETWEEN PERFORMANCE FACTORS IN HADOOP CLOUD COMPUTING APPLICATIONS

METHODOLOGY TO DETERMINE RELATIONSHIPS BETWEEN PERFORMANCE FACTORS IN HADOOP CLOUD COMPUTING APPLICATIONS METHODOLOGY TO DETERMINE RELATIONSHIPS BETWEEN PERFORMANCE FACTORS IN HADOOP CLOUD COMPUTING APPLICATIONS Lus Eduardo Bautsta Vllalpando 1,2, Alan Aprl 1 and Alan Abran 1 1 Department of Software Engneerng

More information

Application of Multi-Agents for Fault Detection and Reconfiguration of Power Distribution Systems

Application of Multi-Agents for Fault Detection and Reconfiguration of Power Distribution Systems 1 Applcaton of Mult-Agents for Fault Detecton and Reconfguraton of Power Dstrbuton Systems K. Nareshkumar, Member, IEEE, M. A. Choudhry, Senor Member, IEEE, J. La, A. Felach, Senor Member, IEEE Abstract--The

More information

PAS: A Packet Accounting System to Limit the Effects of DoS & DDoS. Debish Fesehaye & Klara Naherstedt University of Illinois-Urbana Champaign

PAS: A Packet Accounting System to Limit the Effects of DoS & DDoS. Debish Fesehaye & Klara Naherstedt University of Illinois-Urbana Champaign PAS: A Packet Accountng System to Lmt the Effects of DoS & DDoS Debsh Fesehaye & Klara Naherstedt Unversty of Illnos-Urbana Champagn DoS and DDoS DDoS attacks are ncreasng threats to our dgtal world. Exstng

More information

ivoip: an Intelligent Bandwidth Management Scheme for VoIP in WLANs

ivoip: an Intelligent Bandwidth Management Scheme for VoIP in WLANs VoIP: an Intellgent Bandwdth Management Scheme for VoIP n WLANs Zhenhu Yuan and Gabrel-Mro Muntean Abstract Voce over Internet Protocol (VoIP) has been wdely used by many moble consumer devces n IEEE 802.11

More information

Network Aware Load-Balancing via Parallel VM Migration for Data Centers

Network Aware Load-Balancing via Parallel VM Migration for Data Centers Network Aware Load-Balancng va Parallel VM Mgraton for Data Centers Kun-Tng Chen 2, Chen Chen 12, Po-Hsang Wang 2 1 Informaton Technology Servce Center, 2 Department of Computer Scence Natonal Chao Tung

More information

Energy Efficient Routing in Ad Hoc Disaster Recovery Networks

Energy Efficient Routing in Ad Hoc Disaster Recovery Networks Energy Effcent Routng n Ad Hoc Dsaster Recovery Networks Gl Zussman and Adran Segall Department of Electrcal Engneerng Technon Israel Insttute of Technology Hafa 32000, Israel {glz@tx, segall@ee}.technon.ac.l

More information

A New Quality of Service Metric for Hard/Soft Real-Time Applications

A New Quality of Service Metric for Hard/Soft Real-Time Applications A New Qualty of Servce Metrc for Hard/Soft Real-Tme Applcatons Shaoxong Hua and Gang Qu Electrcal and Computer Engneerng Department and Insttute of Advanced Computer Study Unversty of Maryland, College

More information

Reliable State Monitoring in Cloud Datacenters

Reliable State Monitoring in Cloud Datacenters Relable State Montorng n Cloud Datacenters Shcong Meng Arun K. Iyengar Isabelle M. Rouvellou Lng Lu Ksung Lee Balaj Palansamy Yuzhe Tang College of Computng, Georga Insttute of Technology, Atlanta, GA

More information

Optmal Revocatons n Ephemeral Networks

Optmal Revocatons n Ephemeral Networks Optmal Revocatons n Ephemeral Networks: A Game-Theoretc Framework Igor Blogrevc, Mohammad Hossen Manshae, Maxm Raya and Jean-Perre Hubaux Laboratory for computer Communcatons and Applcatons (LCA1), EPFL,

More information

An Analysis of Central Processor Scheduling in Multiprogrammed Computer Systems

An Analysis of Central Processor Scheduling in Multiprogrammed Computer Systems STAN-CS-73-355 I SU-SE-73-013 An Analyss of Central Processor Schedulng n Multprogrammed Computer Systems (Dgest Edton) by Thomas G. Prce October 1972 Techncal Report No. 57 Reproducton n whole or n part

More information

Stochastic Games on a Multiple Access Channel

Stochastic Games on a Multiple Access Channel Stochastc Games on a Multple Access Channel Prashant N and Vnod Sharma Department of Electrcal Communcaton Engneerng Indan Insttute of Scence, Bangalore 560012, Inda Emal: prashant2406@gmal.com, vnod@ece.sc.ernet.n

More information

taposh_kuet20@yahoo.comcsedchan@cityu.edu.hk rajib_csedept@yahoo.co.uk, alam_shihabul@yahoo.com

taposh_kuet20@yahoo.comcsedchan@cityu.edu.hk rajib_csedept@yahoo.co.uk, alam_shihabul@yahoo.com G. G. Md. Nawaz Al 1,2, Rajb Chakraborty 2, Md. Shhabul Alam 2 and Edward Chan 1 1 Cty Unversty of Hong Kong, Hong Kong, Chna taposh_kuet20@yahoo.comcsedchan@ctyu.edu.hk 2 Khulna Unversty of Engneerng

More information

Availability-Based Path Selection and Network Vulnerability Assessment

Availability-Based Path Selection and Network Vulnerability Assessment Avalablty-Based Path Selecton and Network Vulnerablty Assessment Song Yang, Stojan Trajanovsk and Fernando A. Kupers Delft Unversty of Technology, The Netherlands {S.Yang, S.Trajanovsk, F.A.Kupers}@tudelft.nl

More information

A Self-Organized, Fault-Tolerant and Scalable Replication Scheme for Cloud Storage

A Self-Organized, Fault-Tolerant and Scalable Replication Scheme for Cloud Storage A Self-Organzed, Fault-Tolerant and Scalable Replcaton Scheme for Cloud Storage Ncolas Bonvn, Thanass G. Papaoannou and Karl Aberer School of Computer and Communcaton Scences École Polytechnque Fédérale

More information

J. Parallel Distrib. Comput.

J. Parallel Distrib. Comput. J. Parallel Dstrb. Comput. 71 (2011) 62 76 Contents lsts avalable at ScenceDrect J. Parallel Dstrb. Comput. journal homepage: www.elsever.com/locate/jpdc Optmzng server placement n dstrbuted systems n

More information

How To Detect An 802.11 Traffc From A Network With A Network Onlne Onlnet

How To Detect An 802.11 Traffc From A Network With A Network Onlne Onlnet IEEE TRANSACTIONS ON MOBILE COMPUTING, VOL. X, NO. X, XXX 2008 1 Passve Onlne Detecton of 802.11 Traffc Usng Sequental Hypothess Testng wth TCP ACK-Pars We We, Member, IEEE, Kyoungwon Suh, Member, IEEE,

More information

QOS DISTRIBUTION MONITORING FOR PERFORMANCE MANAGEMENT IN MULTIMEDIA NETWORKS

QOS DISTRIBUTION MONITORING FOR PERFORMANCE MANAGEMENT IN MULTIMEDIA NETWORKS QOS DISTRIBUTION MONITORING FOR PERFORMANCE MANAGEMENT IN MULTIMEDIA NETWORKS Yumng Jang, Chen-Khong Tham, Ch-Chung Ko Department Electrcal Engneerng Natonal Unversty Sngapore 119260 Sngapore Emal: {engp7450,

More information

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange

More information

DISTRIBUTED storage systems have been becoming increasingly

DISTRIBUTED storage systems have been becoming increasingly 268 IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, VOL. 28, NO. 2, FEBRUARY 2010 Cooperatve Recovery of Dstrbuted Storage Systems from Multple Losses wth Network Codng Yuchong Hu, Ynlong Xu, Xaozhao

More information

AN APPOINTMENT ORDER OUTPATIENT SCHEDULING SYSTEM THAT IMPROVES OUTPATIENT EXPERIENCE

AN APPOINTMENT ORDER OUTPATIENT SCHEDULING SYSTEM THAT IMPROVES OUTPATIENT EXPERIENCE AN APPOINTMENT ORDER OUTPATIENT SCHEDULING SYSTEM THAT IMPROVES OUTPATIENT EXPERIENCE Yu-L Huang Industral Engneerng Department New Mexco State Unversty Las Cruces, New Mexco 88003, U.S.A. Abstract Patent

More information

Open Access A Load Balancing Strategy with Bandwidth Constraint in Cloud Computing. Jing Deng 1,*, Ping Guo 2, Qi Li 3, Haizhu Chen 1

Open Access A Load Balancing Strategy with Bandwidth Constraint in Cloud Computing. Jing Deng 1,*, Ping Guo 2, Qi Li 3, Haizhu Chen 1 Send Orders for Reprnts to reprnts@benthamscence.ae The Open Cybernetcs & Systemcs Journal, 2014, 8, 115-121 115 Open Access A Load Balancng Strategy wth Bandwdth Constrant n Cloud Computng Jng Deng 1,*,

More information

DBA-VM: Dynamic Bandwidth Allocator for Virtual Machines

DBA-VM: Dynamic Bandwidth Allocator for Virtual Machines DBA-VM: Dynamc Bandwdth Allocator for Vrtual Machnes Ahmed Amamou, Manel Bourguba, Kamel Haddadou and Guy Pujolle LIP6, Perre & Mare Cure Unversty, 4 Place Jusseu 755 Pars, France Gand SAS, 65 Boulevard

More information

Ad-Hoc Games and Packet Forwardng Networks

Ad-Hoc Games and Packet Forwardng Networks On Desgnng Incentve-Compatble Routng and Forwardng Protocols n Wreless Ad-Hoc Networks An Integrated Approach Usng Game Theoretcal and Cryptographc Technques Sheng Zhong L (Erran) L Yanbn Grace Lu Yang

More information

Fair Virtual Bandwidth Allocation Model in Virtual Data Centers

Fair Virtual Bandwidth Allocation Model in Virtual Data Centers Far Vrtual Bandwdth Allocaton Model n Vrtual Data Centers Yng Yuan, Cu-rong Wang, Cong Wang School of Informaton Scence and Engneerng ortheastern Unversty Shenyang, Chna School of Computer and Communcaton

More information

The Load Balancing of Database Allocation in the Cloud

The Load Balancing of Database Allocation in the Cloud , March 3-5, 23, Hong Kong The Load Balancng of Database Allocaton n the Cloud Yu-lung Lo and Mn-Shan La Abstract Each database host n the cloud platform often has to servce more than one database applcaton

More information

A New Task Scheduling Algorithm Based on Improved Genetic Algorithm

A New Task Scheduling Algorithm Based on Improved Genetic Algorithm A New Task Schedulng Algorthm Based on Improved Genetc Algorthm n Cloud Computng Envronment Congcong Xong, Long Feng, Lxan Chen A New Task Schedulng Algorthm Based on Improved Genetc Algorthm n Cloud Computng

More information

Forecasting the Direction and Strength of Stock Market Movement

Forecasting the Direction and Strength of Stock Market Movement Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems

More information

Research on Privacy Protection Approach for Cloud Computing Environments

Research on Privacy Protection Approach for Cloud Computing Environments , pp. 113-120 http://dx.do.org/10.14257/jsa.2015.9.3.11 Research on Prvacy Protecton Approach for Cloud Computng Envronments Xaohu L 1,2, Hongxng Lang 3 and Dan Ja 1 1 College of Electrcal and Informaton

More information

A Game-Theoretic Approach for Minimizing Security Risks in the Internet-of-Things

A Game-Theoretic Approach for Minimizing Security Risks in the Internet-of-Things A Game-Theoretc Approach for Mnmzng Securty Rsks n the Internet-of-Thngs George Rontds, Emmanoul Panaouss, Aron Laszka, Tasos Daguklas, Pasquale Malacara, and Tansu Alpcan Hellenc Open Unversty, Greece

More information

Project Networks With Mixed-Time Constraints

Project Networks With Mixed-Time Constraints Project Networs Wth Mxed-Tme Constrants L Caccetta and B Wattananon Western Australan Centre of Excellence n Industral Optmsaton (WACEIO) Curtn Unversty of Technology GPO Box U1987 Perth Western Australa

More information

CloudMedia: When Cloud on Demand Meets Video on Demand

CloudMedia: When Cloud on Demand Meets Video on Demand CloudMeda: When Cloud on Demand Meets Vdeo on Demand Yu Wu, Chuan Wu, Bo L, Xuanja Qu, Francs C.M. Lau Department of Computer Scence, The Unversty of Hong Kong, Emal: {ywu,cwu,xjqu,fcmlau}@cs.hku.hk Department

More information

A Resource-trading Mechanism for Efficient Distribution of Large-volume Contents on Peer-to-Peer Networks

A Resource-trading Mechanism for Efficient Distribution of Large-volume Contents on Peer-to-Peer Networks A Resource-tradng Mechansm for Effcent Dstrbuton of Large-volume Contents on Peer-to-Peer Networks SmonG.M.Koo,C.S.GeorgeLee, Karthk Kannan School of Electrcal and Computer Engneerng Krannet School of

More information

Proactive Secret Sharing Or: How to Cope With Perpetual Leakage

Proactive Secret Sharing Or: How to Cope With Perpetual Leakage Proactve Secret Sharng Or: How to Cope Wth Perpetual Leakage Paper by Amr Herzberg Stanslaw Jareck Hugo Krawczyk Mot Yung Presentaton by Davd Zage What s Secret Sharng Basc Idea ((2, 2)-threshold scheme):

More information

AN EFFICIENT GROUP AUTHENTICATION FOR GROUP COMMUNICATIONS

AN EFFICIENT GROUP AUTHENTICATION FOR GROUP COMMUNICATIONS Internatonal Journal of Network Securty & Its Applcatons (IJNSA), Vol.5, No.3, May 2013 AN EFFICIENT GROUP AUTHENTICATION FOR GROUP COMMUNICATIONS Len Harn 1 and Changlu Ln 2 1 Department of Computer Scence

More information

VRT012 User s guide V0.1. Address: Žirmūnų g. 27, Vilnius LT-09105, Phone: (370-5) 2127472, Fax: (370-5) 276 1380, Email: info@teltonika.

VRT012 User s guide V0.1. Address: Žirmūnų g. 27, Vilnius LT-09105, Phone: (370-5) 2127472, Fax: (370-5) 276 1380, Email: info@teltonika. VRT012 User s gude V0.1 Thank you for purchasng our product. We hope ths user-frendly devce wll be helpful n realsng your deas and brngng comfort to your lfe. Please take few mnutes to read ths manual

More information

Relay Secrecy in Wireless Networks with Eavesdropper

Relay Secrecy in Wireless Networks with Eavesdropper Relay Secrecy n Wreless Networks wth Eavesdropper Parvathnathan Venktasubramanam, Tng He and Lang Tong School of Electrcal and Computer Engneerng Cornell Unversty, Ithaca, NY 14853 Emal : {pv45, th255,

More information

Adaptive Sampling for Energy Conservation in Wireless Sensor Networks for Snow Monitoring Applications

Adaptive Sampling for Energy Conservation in Wireless Sensor Networks for Snow Monitoring Applications Adaptve Samplng for Energy Conservaton n Wreless Sensor Networks for Snow Montorng Applcatons Cesare Alpp *, Guseppe Anastas, Crstan Galpert *, Francesca Mancn, Manuel Rover * * Dp. d Elettronca e Informazone

More information

Schedulability Bound of Weighted Round Robin Schedulers for Hard Real-Time Systems

Schedulability Bound of Weighted Round Robin Schedulers for Hard Real-Time Systems Schedulablty Bound of Weghted Round Robn Schedulers for Hard Real-Tme Systems Janja Wu, Jyh-Charn Lu, and We Zhao Department of Computer Scence, Texas A&M Unversty {janjaw, lu, zhao}@cs.tamu.edu Abstract

More information

Secure Walking GPS: A Secure Localization and Key Distribution Scheme for Wireless Sensor Networks

Secure Walking GPS: A Secure Localization and Key Distribution Scheme for Wireless Sensor Networks Secure Walkng GPS: A Secure Localzaton and Key Dstrbuton Scheme for Wreless Sensor Networks Q M, John A. Stankovc, Radu Stoleru 2 Department of Computer Scence, Unversty of Vrgna, USA 2 Department of Computer

More information

Network Security Situation Evaluation Method for Distributed Denial of Service

Network Security Situation Evaluation Method for Distributed Denial of Service Network Securty Stuaton Evaluaton Method for Dstrbuted Denal of Servce Jn Q,2, Cu YMn,2, Huang MnHuan,2, Kuang XaoHu,2, TangHong,2 ) Scence and Technology on Informaton System Securty Laboratory, Bejng,

More information

A DATA MINING APPLICATION IN A STUDENT DATABASE

A DATA MINING APPLICATION IN A STUDENT DATABASE JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 005 VOLUME NUMBER (53-57) A DATA MINING APPLICATION IN A STUDENT DATABASE Şenol Zafer ERDOĞAN Maltepe Ünversty Faculty of Engneerng Büyükbakkalköy-Istanbul

More information

Coordinated Denial-of-Service Attacks in IEEE 802.22 Networks

Coordinated Denial-of-Service Attacks in IEEE 802.22 Networks Coordnated Denal-of-Servce Attacks n IEEE 82.22 Networks Y Tan Department of ECE Stevens Insttute of Technology Hoboken, NJ Emal: ytan@stevens.edu Shamk Sengupta Department of Math. & Comp. Sc. John Jay

More information

RequIn, a tool for fast web traffic inference

RequIn, a tool for fast web traffic inference RequIn, a tool for fast web traffc nference Olver aul, Jean Etenne Kba GET/INT, LOR Department 9 rue Charles Fourer 90 Evry, France Olver.aul@nt-evry.fr, Jean-Etenne.Kba@nt-evry.fr Abstract As networked

More information

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..

More information

How To Plan A Network Wide Load Balancing Route For A Network Wde Network (Network)

How To Plan A Network Wide Load Balancing Route For A Network Wde Network (Network) Network-Wde Load Balancng Routng Wth Performance Guarantees Kartk Gopalan Tz-cker Chueh Yow-Jan Ln Florda State Unversty Stony Brook Unversty Telcorda Research kartk@cs.fsu.edu chueh@cs.sunysb.edu yjln@research.telcorda.com

More information

A role based access in a hierarchical sensor network architecture to provide multilevel security

A role based access in a hierarchical sensor network architecture to provide multilevel security 1 A role based access n a herarchcal sensor network archtecture to provde multlevel securty Bswajt Panja a Sanjay Kumar Madra b and Bharat Bhargava c a Department of Computer Scenc Morehead State Unversty

More information

A Novel Problem-solving Metric for Future Internet Routing Based on Virtualization and Cloud-computing

A Novel Problem-solving Metric for Future Internet Routing Based on Virtualization and Cloud-computing www.ijcsi.org 159 A Novel Problem-solvng Metrc for Future Internet Routng Based on Vrtualzaton and Cloud-computng Rujuan Zheng, Mngchuan Zhang, Qngtao Wu, Wangyang We and Haxa Zhao Electronc & Informaton

More information

LIFETIME INCOME OPTIONS

LIFETIME INCOME OPTIONS LIFETIME INCOME OPTIONS May 2011 by: Marca S. Wagner, Esq. The Wagner Law Group A Professonal Corporaton 99 Summer Street, 13 th Floor Boston, MA 02110 Tel: (617) 357-5200 Fax: (617) 357-5250 www.ersa-lawyers.com

More information

Efficient Striping Techniques for Variable Bit Rate Continuous Media File Servers æ

Efficient Striping Techniques for Variable Bit Rate Continuous Media File Servers æ Effcent Strpng Technques for Varable Bt Rate Contnuous Meda Fle Servers æ Prashant J. Shenoy Harrck M. Vn Department of Computer Scence, Department of Computer Scences, Unversty of Massachusetts at Amherst

More information