Reducing Energy Consumption for Reconfiguration in Cloud Data Centers

Size: px
Start display at page:

Download "Reducing Energy Consumption for Reconfiguration in Cloud Data Centers"

Transcription

1 Reducng Energy Consumpton for Reconfguraton n Cloud Data Centers Invted Paper Omar Chakroun, Soumaya Cherkaou INTERLAB Research Laboratory, Unversté de Sherbrooke, Canada {omar.chakroun, soumaya.cherkaou}@usherbrooke.ca Abstract Moble Cloud Computng (MCC) leverages moble devces and nfrastructure equpment to ncrease servces accessblty. It uses ncreased devces computng capablty to enhance servces usablty and ensure hgh avalablty. Ths growth n performances results n an ncreased nterest for platforms use to accommodate a multtude of applcatons. To support such an ncrease n demand, new desgns for resource management have to be mplemented n order to reach usage optmalty. In ths work, we propose to desgn new algorthms to optmse MCC resources management technques based on stochastc networks optmzaton. Our approach s focused on energy consumpton optmzaton on the cloud data center sde whle ensurng resources elastcty to adapt to users demands and nsure a hghly avalable platform. We elected an overclockng technque to enhance servers capabltes and Lyapunov optmsaton to ensure desgn stablty and to mnmse the energy cost. We perform extensve smulatons under dfferent charge condtons n order to prove the desgn effectveness n ensurng the servce wth lower power consumpton. Smulatons results confrm the effectveness of the proposed resources management desgn. Index Terms MCC, resource management, energy, elastcty and hgh avalablty, Lyapunov optmzaton. I. INTRODUCTION Moble cloud computng (MCC) denotes the convergence between two well nvestgated concepts: a) cloud computng, whch provdes computatonal and storage capacty for users applcatons and b) moble computng whch allows portable devces to access dstant resources wth ad hoc or nfrastructurebased wreless communcaton technologes. The motvaton behnd MCC s the need to accommodate resource-ntensve applcatons wthn moble devces wth comparatvely very lmted capacty. The ultmate goal s to enable the executon of rch moble applcatons on a set of mobles devces by leveragng dstant platforms for almost unrestrcted capacty and functonalty. To ensure hgh servce avalablty, cloud provders deploy huge and costly nfrastructures comprsng a large number of data centers. Once these nfrastructures are deployed, servers energy consumpton consttutes a sgnfcant proporton of operatng costs [1]. Reducng the energy cost can translate nto a huge gan for cloud provders. Statstc studes conducted by cloud provders conclude that coolng and processng energy consttutes up to 50% of the total energy used n a data center [2]. Energy effcency can be acheved wth more effcent hardware and ntegrated thermal management [3, 4, 5]. However, desgns for resource management and network reconfguraton polces can also acheve sgnfcant gans n energy savngs. Many researchers tred to reduce energy cost of such platforms by proposng new desgns for resource management based on optmsaton processes. These optmzaton processes range from smple optmzaton-under-constrants [6] to complex algorthms leveragng game theory and stochastc analyss [7]. Cloud resource management has to be both hghly effcent and adaptve. Adaptablty here means the capablty to manage resources effcently, when facng rapd demand changes n term of resource requests, whle supportng heterogeneous applcatons. In ths work, we use a stochastc approach for resource management n order to optmze energy consumpton n cloud data centers whle mantanng servce avalablty. We defne resource management as the process of allocatng computng, storage, and networkng capabltes n order to meet both user demand and moble cloud provder obectves. Resource management n MCC uses vrtualzaton technques to facltate resource multplexng. Vrtualzaton combned wth moblty, allows Vrtual Machne (VM) mgraton and /or consoldaton. VM Mgraton can be used to move resources closer to the end user so as to reduce response tme. VM consoldaton s usually promoted to save on energy consumpton. Movng VMs strewn over multple Physcal Machnes (PM) toward a smaller set of PM can reduce energy usage. Our approach s bult on the followng fndngs: (1) VM mgraton consumes an mportant amount of physcal server resources especally on the source PM. The resources needed for VM mgraton account for 10%-20% of the CPU and memory resources of PMs [8, 9]. Based on that observaton, PMs are only run at 90% of ther capacty n the most optmstc scenaro. The other 10% of the resources are reserved for possble VM mgratons. (2) A PM whch s started and s not handlng any requests, consumes an approxmate energy of 45% of ts maxmum energy consumpton at full charge. The above value s called the nomnal power consumpton. (3) VM consoldaton consttutes a good approach to reduce overall data center power consumpton, whch gves cloud provders the ablty to turn off unused PMs /16/$ IEEE

2 Based on the prevously mentoned remarks, we elected an overclockng technque to accommodate VM mgraton requests whle makng an effcent use of servers resources and reducng the overall cloud data center power consumpton. We show that overclockng allows usng PMs to a better capacty. We also show that at the small expense of energy cost due to overclockng, we can acheve much more sgnfcant savngs on overall servers energy consumpton. The remander of ths paper s organzed as follows; Secton II presents desgn prncples for our overclockng approach. Secton III ntroduces the system model to ensure resource allocaton optmzaton. Secton IV presents the smulaton envronment and an overvew of the results. Fnally, Secton V concludes the paper. II. OVERCLOCKING TECHNIQUE Overclockng s the fact of confgurng a computer to operate at a faster rate (clock frequency) than the one that was certfed for by the manufacturer. The man purpose from overclockng s to gan extra performance from a gven component by ncreasng ts operatng speed. Overclockng s usually appled on maor components such as man processors and graphc controllers. Most components are desgned wth a safety margn to deal wth operatng condtons outsde the manufacturers control, and overclockng s the acton of settng the devce to run n the hgher end of that margn wth the understandng that temperature and voltage must be controlled as the safety margn s reduced. Whle most modern devces are farly tolerant of overclockng, all devces have fnte lmts - generally for any gven voltage most parts wll have a maxmum "stable" speed where they stll operate correctly. A. Overclockng extent and desgn consderatons In our desgn, we make use of overclockng n servers whle stayng n the safety operatng range n order not to decrease the components lfetme, nvolve the need for extra nvestment n coolng systems, or ncrease voltage requests. Thus, we use overclockng up to a certan extent, not to exceed 15% of the processng speed, and wthout any modfcaton to the processor Vcore voltage or the coolng system. We use overclockng only f a VM mgraton s needed and on the source PM sde only. Upon completng the VM mgraton, the processor speed s retuned down to the maxmum value specfed by the manufacturer and overclockng s turned off. Authors n [10] present some results of overclocked processors performances wthout the need of extra nvestments on coolng or modfcatons on the hardware. They conclude that a gan n processor speed up to 26% s achevable wthout any changes. Of course, runnng a processor over ts maxmum speed can make the system consume more power, especally for heat dsspaton. However, studes n [11] showed that the extra power consumed when overclockng s actvated s relatvely low and ranges from 2W - 6W per processor and per 200 MHz overclockng step up to 600 MHz. Over 600 MHz overclockng related power consumpton can ncrease rapdly to reach up to 40W per 200 MHz step. Thus, we are consderng a maxmum of 15% overclockng n order to lmt the power consumpton overhead and we are actvatng the overclockng for short perods of tme correspondng to VM lve mgraton duratons n order not to degrade the servers performances and relablty. B. Reducng the mpact of reconfguraton There exsts a multtude of reconfguraton technques, for better resources management, such as VM reszng and lve mgraton. Modern hypervsors nvolve reduced overhead whch allows resources enttlements to be changed on a runnng VM. Researchers n [12] studed the mpact of VM mgraton on the cloud performances and partcularly on the source server sde. VM mgraton s usually useful for clustered applcatons and t s for hgh nterest to data centers ether to consoldate VM to reduce the number of actve servers to save power or to ensure hgher resources for resources ntensve tasks. The need of extra resources on the source server s related to the need of more actve memory usually due to cache contenton between colocated VMs. In ths perspectve, temporarly actvatng the overclockng when a VM mgraton s needed can be benefcal n reducng the mpact on coexstent VM that share the same physcal memory, and can speed up the mgraton process. We wll take such an approach on the source Data Center (DC) server sde only and we wll measure ts mpact on power consumpton whch we denote by the reconfguraton cost. Theoretcally, the gan n processor speed translates n a gan on the number of tasks processed and can mpact the memory speed. Algorthm 1 depcts the steps for computng resources allocaton and the actvaton of overclockng when VM mgraton s requested. C. Power consumpton characterzaton We focus on servers n our energy model. For servers, we adopt the model from [4] that characterzes the ndvdual server power consumpton functon of the processng speed as an affne functon as n equaton Eq.(1) where P dle, P peak and U denotes respectvely the power consumpton n dle state, power consumpton when the server s fully utlzed and the utlzaton level rangng from 0 to 1. Equaton Eq.(2) presents an extenson of the equaton Eq.(1) when the overclockng s supported. P over denotes the maxmum power consumed when overclockng s at ts maxmum tolerable value and U over denotes the rate of overclockng functon of the maxmum processor speed. P P = P + ( P P ) U (1) Cons dle peak dle * Cons _ over + ( P over = P + ( P P ) * U (2) P dle peak ) * U peak over Fgure 1 llustrates the power consumpton wth and wthout overclockng actvaton and the gan n power consumpton for a 2.8GHz processor. We are takng nto consderaton 6W extrapower consumpton for every 200MHz overclockng step up to 600 MHz and a 45W over consumpton above that threshold for every step [8]. In Fgure 1, standard approach refers to the case where no overlockng s actvated and servers are workng at a maxmum of 90% of ther capacty. Overclockng approach refers to the overclockng approach where servers are workng at a maxmum rate of 100% and usage of overclockng s lmted to the case where a VM mgraton s needed. dle

3 (c) In the DC, the set of runnng VMs are strewn over multple PMs. In our approach, we am to consoldate the maxmum number of VMs on the mnmum number of PM to reduce the global DC power consumpton. Ths wll help us reduce the number of actve PMs whch at the end reduces the overall power consumpton (see algorthm 1). Algorthm 1 VM consoldaton FIGURE I OVERCLOCKING VS STANDARD APPROACH POWER CONSUMPTION D. Power consumpton optmzaton Our desgn of a power-effcent data center s based on two deas; (1) consoldatng the maxmum number of VM nto the mnmum number of PM to ensure the lowest power consumpton and (2) make use of 100% of servers resources wthout pre-reservng resources for possble VM mgratons. The resources assocated wth VM mgraton n our desgn wll be ensured by actvatng the overclockng technque on the source server sde when needed. Thus, we descrbe our approach n three scenaros: (a) new request arrval, (b) VM mgraton request and (c) VM consoldaton to reduce the number of actve PM. (a) Assume that a new resource request s receved on the admsson controller sde of our cloud data center. The applcaton profler wll dagnose how much computng resources are needed to accommodate that request and dependng on the servers state, wll route the request to the optmal server. In case there are not enough resources on the set of actve servers handlng that applcaton, the resources handler wll actvate a new server and nstantate the VM on t before routng the request to the newly actvated server. Thus power consumpton on the new actvated server wll be P dle +(P peak - P dle )*U where U desgnates the utlzaton level needed to accommodate the demand. Otherwse, f one of the actve servers s able to handle the request, ts power consumpton wll be ncreased by a factor correspondng to the extra utlzaton needed U+uextra. It s worth notng that n the tradtonal approach, the maxmum utlzaton does not exceed 90%. In our approach, we use the server resources at a full extent (100%). (b) In case of a VM mgraton request, the tradtonal approach does not ntroduce any extra usage or resources reservaton snce VM mgraton resources account for 10% of the PM resources and these resources are always pre-reserved. On the other hand, n our approach we are makng use of 100% of PM resources for request handlng and an overclockng actvaton s needed before proceedng to the VM mgraton. Overclockng deactvaton s needed after VM mgraton completon. III. δs : workload of server δ max : maxmum workload on a server TSU: table contanng all actve servers workloads ordered ncreasngly except servers at δ max,: ndexes Begn: Whle (<=szeof(tsu)) For =+1 to szeof (TSU) f (δs + δs <= δ max ) actvate overclockng on S allocate resources on S update δs = δs + δs mgrate VM(S ) to S deactvate overclockng on S shutdown S remove S from TSU and Shft table elements to the left Szeof(TSU) Else ++ End f End for End whle PROBLEM FORMULATION AND THEORETICAL ANALYSIS A. Problem formulaton We are consderng a data center wth S servers that hosts a set of N applcatons denoted by A. each server hosts a subset of applcatons. It uses one VM per applcatons n order to ensure applcatons severablty and an applcaton can have multple nstances runnng across the data center. We defne ndcator functon e as equal 1 f applcaton s hosted on server, 0 otherwse. We assume a tme slotted system where at every tmeslot new requests arrve for applcaton wth a rate λ accordng to a random process whch s ndependent from the amount of unfnshed work and we suppose that we have no knowledge of the statstcs of these arrvals. Let W (t) denote the router buffer contanng all admtted requests after the admsson controller. R (t) the requests for applcaton that are routed to server n slot t and R (t) the newly admtted requests. Thus the router dynamc can be characterzed by (3). W ( t + 1) = W R + R Let S (t) denote the set of actve servers capable of handlng the applcaton at slot t thus the routng decson must satsfy the followng constrants (4) and (5) at every slot. (3)

4 0 R = 0 f e = 0 (4) e S ( t ) R W Let us denote the set of control acton avalable at the server level at the nstant t under any control polcy by I (t) and let P (t) the correspondng power consumpton. Then the queung dynamcs of the requests of the applcaton on server follows (6) where μ (I (t)) denotes the servce rate for the applcaton at server under the control decson I (t). U [ U ( I ),0] R ( ) (5) ( t + 1) = max μ t (6) + We assume that the expected value of the servce rate can be known snce, as dscussed n secton II, we can derve the experenced power consumpton based on the processor frequency assgnment. Thus at every slot t, the followng decsons have to be made: (1) Routng decson for the admtted requests R (t). (2) Resource allocaton decson I (t) ncludng resources dstrbuton among VMs and actvatng of the overclockng. Let us denote the average expected rate of admtted requests for n the applcaton under control polcy by r and the average n expected power under the same condtons by p whch expressons are as follows. r 1 = lm t t t 1 τ = 0 E { R ( )} { P ( τ )} τ (7) t 1 1 p = lm E (8) t t τ = 0 Thus consderng a collecton of non-negatve weghtsα, β, our obectve s to desgn a control polcy that solves the followng stochastc optmzaton problem. Maxmze: α r β p A S (9) S.T: 0 r λ Thus the obectve problem s a general weghted lnear combnaton of the sum throughput of the applcatons and the sum of the average power consumpton n the data center. B. Control Algorthm based on Lyapunov optmzaton We use Lyapunov optmzaton n order to acheve stablty of the system. Let V>=0 be a control parameter that has to be chosen by the system admnstrator to ensure the desred tradeoff between the performance and the power consumpton. Let W (t) and U (t) be the router and the server queue backlog at tmeslot t. As the backlog values evolve over tme as descrbed n (3) and (6), the algorthm adapts to the system changes and solves the problem n (9) leveragng a sequence of optmzaton problems over tme on three dstnct steps. Request routng: let denote the server that s havng the smallest queue backlog and belongng to the set of servers that are able to process the requests for applcaton. thus, a routng polcy can redrect all requests for applcaton to such a server under the condton that W (t)>u (t). Resources allocaton: at each server, choose the resource allocaton I (t) that solves the Lyapunov optmzaton process where p max denotes the maxmum power consumpton per server. Maxmze: U E{ μ ( I ) } Vp A ST: p p max (10) IV. RESULT OVERVIEW We chose to mplement our approach under Matlab snce t offers good computatonal capablty and offers a multtude of optmzaton frameworks. We mplemented three man approaches: (1) the nomnal approach whch uses servers capabltes up to 100%, (2) the standard approach whch uses servers up to 90% of ther capactes and leaves 10% of t for VM mgraton purposes and (3) our overclockng approach whch uses servers up to 100% for processng and overclocks servers CPU n case of VM mgraton up to 15%. A. Smulaton envronment We smulated a data center consttuted of 100 servers usng homogeneous processors that have a mnmum speed of 1.4GHz and a maxmum speed of 2.8GHz whle power consumpton ranges from 45 watts to 95 watts when server s actvated. The number of request arrvng to the DC s randomzed and ranges between 0 and 100 requests per server per tmeslot. Each request s charactersed by the needed processng power expressed as a rato from the server maxmum processng capacty. Servers processng capabltes range from 5 to 10 requests per server per tmeslot. The smulaton duraton s 4000 TS. We fxed the control parameter V to a value of 1 to ensure a far trade-off between power consumpton and performance n term of processed requests. Table I below summarzes the man smulaton parameters TABLE I GLOBAL SIMULATION PARAMETERS Parameter Value Number of servers 100 Number of actve servers at the 10 start Number of request arrvng to the per TS DC Servers processng frequency GHz Processng capabltes 5-10 requests per server per TS Servers power range watts Overclockng maxmum rate 15% (up to 3.2GHz) Smulaton duraton 4000 TS B. Results overvew and analyss We are manly nterested n assessng the gan n DC power

5 consumpton ensured by our desgned overclockng approach whle subectng the DC to dfferent requests admsson rates. We also make use of a VM consoldaton approach n order to reduce the number of actve PM and consequently ensure the same processng rate whle consumng less power. Fgure II shows the number of admtted requests accepted by the admsson controller dependng on the servers processng charge over the whole smulaton duraton. The number of admtted requests per server per TS range from 7 to 27 wth a mean value of 20 requests per server per TS. Fgure III shows the mean servers charge over tme. It shows that based on our model, we make use of servers capabltes to the maxmum extent tryng to use the power more effcently. The mean charge per server s around 92% of the maxmum capactes and most of the tme servers are workng at rate hgher than 90%. Ths s reflected by the left hand sde of the formula n Eq. (10), we are tryng to maxmze the porton U (t)e{μ (I (t))} whch corresponds to the server processng charge where U (t) corresponds to the number of request routed to server and μ (I (t)) s the server servce rate under the control decson I (t). Also the resulted charge shows the effectveness of proposed VM consoldaton approach to reduce the number of actve servers and consequently the total DC power consumpton. accommodate the same requests. The latter approach ensures a gan n the number of actvated servers compared to the nomnal approach of 23% and 13.5% compared to the standard approach. FIGURE III MEAN SERVERS CHARGE RATE OVER TIME FIGURE II ADMITTED REQUEST TO THE DATA CENTER OVER TIME The second step of the smulaton s to assess the performances of our approach compared to a nomnal approach where servers are used to a full extent but wthout VM mgraton support and compared to the standard approach whch uses up to 90% of the servers capabltes and leaves 10% for VM mgraton purposes. Our approach, on the other hand, uses the servers capabltes to the maxmum extent and actvates overclockng to a maxmum of 15% when a VM mgraton s needed. Fgure IV shows the performances evaluaton between the three approaches n term of actve servers to accommodate the admtted requests. We notce that the nomnal approach needs to actvate approxmatvely 43 servers per tmeslot to accommodate the admtted requests shown n Fgure II. The standard approach, uses approxmatvely 37 servers per tmeslot to accommodate the same requests and fnally the overclockng technque uses only 33 servers per tmeslot to FIGURE IV NUMBER OF ACTIVE SERVERS FOR OVERCLOCKING, NOMINAL AND STANDARD APPROACHES (SERVERS PER TS) Snce the combnaton of VM consoldaton and overclockng ensures a gan n term of actve servers compared to both other approaches,that gan should translate n gan n power consumpton. Fgure V shows the mean DC power consumpton over tme. It shows a comparson for power consumpton for the smulated DC between the standard approach and the overclockng approach. The overclockng approach consumes a mean 3638 Watts per tmeslot whle the standard approach uses approxmatvely 4042 Watts per tmeslot. Thus, the overclockng technque ensures a gan n power consumpton of 10% n every tmeslot whch shows the effectveness of the proposed scheme. Another mportant remark s, snce we are usng Lyapunov optmzaton, the system behavor and performances are stablzed, whch s reflected n Fgures IV and V. In Fgure V, the standard devaton from the mean number of servers usng the nomnal approach s 2.25%. Where, t s respectvely 2.27% and 2.35% for the overclockng and the standard approach. In Fgure V, the standard devaton for the power consumpton on

6 the DC for the standard approach s Watts per tmeslot whle t s Watts per tmeslot for the overclockng approach whch corresponds to 2.28% of the mean power consumpton for both approaches. resources, therefore, the combned complexty s lnear on the number of total hosts. V. CONCLUSION AND FUTURE WORK In ths paper, we present an analytcal and smulaton based study on the mpact of an overclockng technque on reducng data centers power consumpton. We presented a new scheme for VM consoldaton to reduce the number of actve servers on the DC. The results of the study present the mpact of the combnaton of the VM consoldaton and overclockng technque on the DC performance n term of actve servers and by consequence on the total power consumpton. Smulatons show that, even at hgh servers charge and hgh requests volume, our desgn allows stablzng system behavour whle ensurng a gan up to 23% n the number of actve servers and of 10% n total energy consumpton. REFERENCES FIGURE V DATA CENTER ENERGY CONSUMPTION FOR OVERCLOCKING AND STANDARD APPROACHES (WATTS PER TS) Fgure VI shows a comparson between the gan n term of energy and servers usage ensured by our overclockng approach (A) compared to the ADMM approach n [2] denoted by (B) and IMAPP proposed by Chen et al n [4] denoted by (C). On one hand, we notce that the overclockng approach presents relatvely low gan n term of energy compared to the other two approaches (10% compared to 35% and 20% for the ADMM and IMAPP respectvely), but on the other hand, t ensures a hgh level of servers utlzaton up to 90% compared to 80% and not a sgnfcant gan for ADMM and IMAPP respectvely. FIGURE VI APPROACHES COMPARISON IN TERM OF POWER GAIN AND SERVERS USAGE From the computatonal complexty pont of vew, our proposed approach ensure a complexty of O(M*N) f we are consderng M servers deployed on the data center and N request per TS admtted to the system for processng. Snce on every TS, the table contanng all servers states s sorted n term of computng usage, ths extra computaton wll cost up to O(M) for the worst case. Whch n total results n a worst case complexty of O(M*N)+O(M). Snce the number of VMs that can be hosted on a sngle host s lmted by the physcal [1] P. X. Gao, A. R. Curts, B. Wong, and S. Keshav, It s not easy beng green, n Proc. ACM SIGCOMM 2012 Conf. Appl., Technol., Archt, Protocols Comput. Commun., 2012, pp [2] H. Xu, C. Feng, and B. L, Temperature aware workload management n geo-dstrbuted datacenters, SIGMETRICS Perform. Eval. Rev. 41, 1 (June 2013), DOI= [3] C. Bash and G.Forman, Cool ob allocaton: measurng the power savngs of placng obs at coolng-effcent locatons n the data center, In 2007 USENIX Annual Techncal Conference on Proceedngs of the USENIX Annual Techncal Conference (ATC'07), Jeff Chase and Srnvasan Seshan (Eds.). USENIX Assocaton, Berkeley, CA, USA,, Artcle 29, 6 pages. [4] Y. Chen, D. Gmach, C. Hyser,W. Zhku, C. Bash, C. Hoover,S. Snghal, Integrated management of applcaton performance, power and coolng n data centers, n Network Operatons and Management Symposum (NOMS), 2010 IEEE, vol., no., pp , Aprl 2010 do: /NOMS [5] X. Fan, W.D. Weber, L. A. Barroso, Power provsonng for a warehouse-szed computer, SIGARCH Comput. Archt. News 35, 2 (June 2007), DOI= [6] S. Boyd, N. Parkh, E. Chu, B. Peleato, and J. Ecksten, Dstrbuted optmzaton and statstcal learnng va the alternat- ng drecton method of multplers, Found. Trends Mach. Learn., vol. 3, no. 1, pp , [7] X. Xu and H.Yu, A Game Theory Approach to Far and Effcent Resource Allocaton n Cloud Computng, Mathematcal Problems n Engneerng, vol. 2014, Artcle ID , 14 pages, do: /2014/ [8] I. Takouna, R. Roas-Cessa, K. Sachs,C. Menel, Communcaton-Aware and Energy-Effcent Schedulng for Parallel Applcatons n Vrtualzed Data Centers, n Utlty and Cloud Computng (UCC), 2013 IEEE/ACM 6th Internatonal Conference on, vol., no., pp , 9-12 Dec do: /UCC [9] Susmt Bagch, Emergng Research n Cloud Dstrbuted Computng Systems, [10] [11] [12] A. Verma, G. Kumar,R. Koller, A. Sen, CosMg: Modelng the Impact of Reconfguraton n a Cloud, n Modelng, Analyss & Smulaton of Computer and Telecommuncaton Systems (MASCOTS), 2011 IEEE 19th Internatonal Symposum on, vol., no., pp.3-11, July 2011, do: /MASCOTS

Wishing you all a Total Quality New Year!

Wishing you all a Total Quality New Year! Total Qualty Management and Sx Sgma Post Graduate Program 214-15 Sesson 4 Vnay Kumar Kalakband Assstant Professor Operatons & Systems Area 1 Wshng you all a Total Qualty New Year! Hope you acheve Sx sgma

More information

Dynamic Bandwidth Provisioning with Fairness and Revenue Considerations for Broadband Wireless Communication

Dynamic Bandwidth Provisioning with Fairness and Revenue Considerations for Broadband Wireless Communication Ths full text paper was peer revewed at the drecton of IEEE Communcatons Socety subject matter experts for publcaton n the ICC 008 proceedngs. Dynamc Bandwdth Provsonng wth Farness and Revenue Consderatons

More information

An Entropy-Based Approach to Integrated Information Needs Assessment

An Entropy-Based Approach to Integrated Information Needs Assessment Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology

More information

Motivation. EE 457 Unit 4. Throughput vs. Latency. Performance Depends on View Point?! Computer System Performance. An individual user wants to:

Motivation. EE 457 Unit 4. Throughput vs. Latency. Performance Depends on View Point?! Computer System Performance. An individual user wants to: 4.1 4.2 Motvaton EE 457 Unt 4 Computer System Performance An ndvdual user wants to: Mnmze sngle program executon tme A datacenter owner wants to: Maxmze number of Mnmze ( ) http://e-tellgentnternetmarketng.com/webste/frustrated-computer-user-2/

More information

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling , pp.40-45 http://dx.do.org/10.14257/astl.2017.143.08 Applcaton of Improved Fsh Swarm Algorthm n Cloud Computng Resource Schedulng Yu Lu, Fangtao Lu School of Informaton Engneerng, Chongqng Vocatonal Insttute

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Virtual Memory. Background. No. 10. Virtual Memory: concept. Logical Memory Space (review) Demand Paging(1) Virtual Memory

Virtual Memory. Background. No. 10. Virtual Memory: concept. Logical Memory Space (review) Demand Paging(1) Virtual Memory Background EECS. Operatng System Fundamentals No. Vrtual Memory Prof. Hu Jang Department of Electrcal Engneerng and Computer Scence, York Unversty Memory-management methods normally requres the entre process

More information

Advanced radio access solutions for the new 5G requirements

Advanced radio access solutions for the new 5G requirements Advanced rado access solutons for the new 5G requrements Soumaya Hamouda Assocate Professor, Unversty of Carthage Tuns, Tunsa Soumaya.hamouda@supcom.tn IEEE Summt 5G n Future Afrca. May 3 th, 2017 Pretora,

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

A Genetic Algorithm Based Dynamic Load Balancing Scheme for Heterogeneous Distributed Systems

A Genetic Algorithm Based Dynamic Load Balancing Scheme for Heterogeneous Distributed Systems Proceedngs of the Internatonal Conference on Parallel and Dstrbuted Processng Technques and Applcatons, PDPTA 2008, Las Vegas, Nevada, USA, July 14-17, 2008, 2 Volumes. CSREA Press 2008, ISBN 1-60132-084-1

More information

FAHP and Modified GRA Based Network Selection in Heterogeneous Wireless Networks

FAHP and Modified GRA Based Network Selection in Heterogeneous Wireless Networks 2017 2nd Internatonal Semnar on Appled Physcs, Optoelectroncs and Photoncs (APOP 2017) ISBN: 978-1-60595-522-3 FAHP and Modfed GRA Based Network Selecton n Heterogeneous Wreless Networks Xaohan DU, Zhqng

More information

S1 Note. Basis functions.

S1 Note. Basis functions. S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type

More information

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique //00 :0 AM Outlne and Readng The Greedy Method The Greedy Method Technque (secton.) Fractonal Knapsack Problem (secton..) Task Schedulng (secton..) Mnmum Spannng Trees (secton.) Change Money Problem Greedy

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

Pricing Network Resources for Adaptive Applications in a Differentiated Services Network

Pricing Network Resources for Adaptive Applications in a Differentiated Services Network IEEE INFOCOM Prcng Network Resources for Adaptve Applcatons n a Dfferentated Servces Network Xn Wang and Hennng Schulzrnne Columba Unversty Emal: {xnwang, schulzrnne}@cs.columba.edu Abstract The Dfferentated

More information

Distributed Resource Scheduling in Grid Computing Using Fuzzy Approach

Distributed Resource Scheduling in Grid Computing Using Fuzzy Approach Dstrbuted Resource Schedulng n Grd Computng Usng Fuzzy Approach Shahram Amn, Mohammad Ahmad Computer Engneerng Department Islamc Azad Unversty branch Mahallat, Iran Islamc Azad Unversty branch khomen,

More information

AADL : about scheduling analysis

AADL : about scheduling analysis AADL : about schedulng analyss Schedulng analyss, what s t? Embedded real-tme crtcal systems have temporal constrants to meet (e.g. deadlne). Many systems are bult wth operatng systems provdng multtaskng

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Cost-efficient deployment of distributed software services

Cost-efficient deployment of distributed software services 1/30 Cost-effcent deployment of dstrbuted software servces csorba@tem.ntnu.no 2/30 Short ntroducton & contents Cost-effcent deployment of dstrbuted software servces Cost functons Bo-nspred decentralzed

More information

Extending Network Life by Using Mobile Actors in Cluster-based Wireless Sensor and Actor Networks

Extending Network Life by Using Mobile Actors in Cluster-based Wireless Sensor and Actor Networks Extendng Networ Lfe by Usng Moble Actors n Cluster-based Wreless Sensor and Actor Networs Nauman Aslam, Wllam Phllps, Wllam Robertson and S. Svaumar Department of Engneerng Mathematcs & Internetworng Dalhouse

More information

THere are increasing interests and use of mobile ad hoc

THere are increasing interests and use of mobile ad hoc 1 Adaptve Schedulng n MIMO-based Heterogeneous Ad hoc Networks Shan Chu, Xn Wang Member, IEEE, and Yuanyuan Yang Fellow, IEEE. Abstract The demands for data rate and transmsson relablty constantly ncrease

More information

DESIGNING TRANSMISSION SCHEDULES FOR WIRELESS AD HOC NETWORKS TO MAXIMIZE NETWORK THROUGHPUT

DESIGNING TRANSMISSION SCHEDULES FOR WIRELESS AD HOC NETWORKS TO MAXIMIZE NETWORK THROUGHPUT DESIGNING TRANSMISSION SCHEDULES FOR WIRELESS AD HOC NETWORKS TO MAXIMIZE NETWORK THROUGHPUT Bran J. Wolf, Joseph L. Hammond, and Harlan B. Russell Dept. of Electrcal and Computer Engneerng, Clemson Unversty,

More information

Efficient Distributed File System (EDFS)

Efficient Distributed File System (EDFS) Effcent Dstrbuted Fle System (EDFS) (Sem-Centralzed) Debessay(Debsh) Fesehaye, Rahul Malk & Klara Naherstedt Unversty of Illnos-Urbana Champagn Contents Problem Statement, Related Work, EDFS Desgn Rate

More information

Routing in Degree-constrained FSO Mesh Networks

Routing in Degree-constrained FSO Mesh Networks Internatonal Journal of Hybrd Informaton Technology Vol., No., Aprl, 009 Routng n Degree-constraned FSO Mesh Networks Zpng Hu, Pramode Verma, and James Sluss Jr. School of Electrcal & Computer Engneerng

More information

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION 24 CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION The present chapter proposes an IPSO approach for multprocessor task schedulng problem wth two classfcatons, namely, statc ndependent tasks and

More information

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

More information

Analysis of Collaborative Distributed Admission Control in x Networks

Analysis of Collaborative Distributed Admission Control in x Networks 1 Analyss of Collaboratve Dstrbuted Admsson Control n 82.11x Networks Thnh Nguyen, Member, IEEE, Ken Nguyen, Member, IEEE, Lnha He, Member, IEEE, Abstract Wth the recent surge of wreless home networks,

More information

Video Proxy System for a Large-scale VOD System (DINA)

Video Proxy System for a Large-scale VOD System (DINA) Vdeo Proxy System for a Large-scale VOD System (DINA) KWUN-CHUNG CHAN #, KWOK-WAI CHEUNG *# #Department of Informaton Engneerng *Centre of Innovaton and Technology The Chnese Unversty of Hong Kong SHATIN,

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

Virtual Machine Placement Based on the VM Performance Models in Cloud

Virtual Machine Placement Based on the VM Performance Models in Cloud Vrtual Machne Placement Based on the VM Performance Models n Cloud Hu Zhao, Qnghua Zheng, Member, IEEE, Wezhan Zhang Member, IEEE, Yuxuan Chen, Yunhu Huang SPKLSTN Lab, Department of Computer Scence and

More information

A Sub-Critical Deficit Round-Robin Scheduler

A Sub-Critical Deficit Round-Robin Scheduler A Sub-Crtcal Defct ound-obn Scheduler Anton Kos, Sašo Tomažč Unversty of Ljubljana, Faculty of Electrcal Engneerng, Ljubljana, Slovena E-mal: anton.kos@fe.un-lj.s Abstract - A scheduler s an essental element

More information

Adaptive Energy and Location Aware Routing in Wireless Sensor Network

Adaptive Energy and Location Aware Routing in Wireless Sensor Network Adaptve Energy and Locaton Aware Routng n Wreless Sensor Network Hong Fu 1,1, Xaomng Wang 1, Yngshu L 1 Department of Computer Scence, Shaanx Normal Unversty, X an, Chna, 71006 fuhong433@gmal.com {wangxmsnnu@hotmal.cn}

More information

Support Vector Machines

Support Vector Machines /9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.

More information

Game Based Virtual Bandwidth Allocation for Virtual Networks in Data Centers

Game Based Virtual Bandwidth Allocation for Virtual Networks in Data Centers Avaable onlne at www.scencedrect.com Proceda Engneerng 23 (20) 780 785 Power Electroncs and Engneerng Applcaton, 20 Game Based Vrtual Bandwdth Allocaton for Vrtual Networks n Data Centers Cu-rong Wang,

More information

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated.

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated. Some Advanced SP Tools 1. umulatve Sum ontrol (usum) hart For the data shown n Table 9-1, the x chart can be generated. However, the shft taken place at sample #21 s not apparent. 92 For ths set samples,

More information

Achieving Energy Proportionality In Server Clusters

Achieving Energy Proportionality In Server Clusters Achevng Energy Proportonalty In Server Clusters Xnyng Zheng Ph.D Canddate /Electrcal and Computer Engneerng Mchgan Technologcal Unversty Houghton, 49931, US Yu Ca Assocate Professor /School of Technology

More information

Optimizing Document Scoring for Query Retrieval

Optimizing Document Scoring for Query Retrieval Optmzng Document Scorng for Query Retreval Brent Ellwen baellwe@cs.stanford.edu Abstract The goal of ths project was to automate the process of tunng a document query engne. Specfcally, I used machne learnng

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual Machine Migration based on Trust Measurement of Computer Node Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

Distributed Middlebox Placement Based on Potential Game

Distributed Middlebox Placement Based on Potential Game Int. J. Communcatons, Network and System Scences, 2017, 10, 264-273 http://www.scrp.org/ournal/cns ISSN Onlne: 1913-3723 ISSN Prnt: 1913-3715 Dstrbuted Mddlebox Placement Based on Potental Game Yongwen

More information

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

More information

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

More information

Avoiding congestion through dynamic load control

Avoiding congestion through dynamic load control Avodng congeston through dynamc load control Vasl Hnatyshn, Adarshpal S. Seth Department of Computer and Informaton Scences, Unversty of Delaware, Newark, DE 976 ABSTRACT The current best effort approach

More information

Improved Energy-Efficiency in Cloud Datacenters with Interference-Aware Virtual Machine Placement

Improved Energy-Efficiency in Cloud Datacenters with Interference-Aware Virtual Machine Placement Improved Energy-Effcency n Cloud Datacenters wth Interference-Aware Vrtual Machne Placement Ismael Sols Moreno 1, Renyu Yang 2, Je Xu 1, 2, Tanyu Wo 2 School of Computng 1 Unversty of Leeds Leeds, UK {scsm,

More information

Energy-Efficient Workload Placement in Enterprise Datacenters

Energy-Efficient Workload Placement in Enterprise Datacenters COVER FEATURE CLOUD COMPUTING Energy-Effcent Workload Placement n Enterprse Datacenters Quan Zhang and Wesong Sh, Wayne State Unversty Power loss from an unnterruptble power supply can account for 15 percent

More information

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz Compler Desgn Sprng 2014 Regster Allocaton Sample Exercses and Solutons Prof. Pedro C. Dnz USC / Informaton Scences Insttute 4676 Admralty Way, Sute 1001 Marna del Rey, Calforna 90292 pedro@s.edu Regster

More information

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Overvew 2 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Introducton Mult- Smulator MASIM Theoretcal Work and Smulaton Results Concluson Jay Wagenpfel, Adran Trachte Motvaton and Tasks Basc Setup

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

An Approach to Optimized Resource Scheduling Algorithm for Open-source Cloud Systems

An Approach to Optimized Resource Scheduling Algorithm for Open-source Cloud Systems The Ffth Annual ChnaGrd Conference An Approach to Optmzed Resource Schedulng Algorthm for Open-source Cloud Systems Ha Zhong 1, 2, Kun Tao 1, Xueje Zhang 1, 2 1 School of Informaton Scence and Engneerng,

More information

Internet Traffic Managers

Internet Traffic Managers Internet Traffc Managers Ibrahm Matta matta@cs.bu.edu www.cs.bu.edu/faculty/matta Computer Scence Department Boston Unversty Boston, MA 225 Jont work wth members of the WING group: Azer Bestavros, John

More information

Delay Variation Optimized Traffic Allocation Based on Network Calculus for Multi-path Routing in Wireless Mesh Networks

Delay Variation Optimized Traffic Allocation Based on Network Calculus for Multi-path Routing in Wireless Mesh Networks Appl. Math. Inf. Sc. 7, No. 2L, 467-474 2013) 467 Appled Mathematcs & Informaton Scences An Internatonal Journal http://dx.do.org/10.12785/ams/072l13 Delay Varaton Optmzed Traffc Allocaton Based on Network

More information

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

More information

The Data Warehouse in a Distributed Utility Environment

The Data Warehouse in a Distributed Utility Environment The Data Warehouse n a Dstrbuted Utlty Envronment Charles A. Mllgan Dstngushed Engneer, Sun Mcrosystems Charles.mllgan@sun.com Abstract Utlty provsonng, Grd resource management, nstant copy kosks, and

More information

Energy Aware Virtual Machine Migration Techniques for Cloud Environment

Energy Aware Virtual Machine Migration Techniques for Cloud Environment Energy Aware rtual Machne Mgraton Technques for Cloud Envronment Kamal Gupta Department of CSE MMU, Sadopur jay Katyar, PhD Department of CSE MMU, Mullana ABSTRACT Cloud Computng offers ndspensable nfrastructure

More information

Research of Dynamic Access to Cloud Database Based on Improved Pheromone Algorithm

Research of Dynamic Access to Cloud Database Based on Improved Pheromone Algorithm , pp.197-202 http://dx.do.org/10.14257/dta.2016.9.5.20 Research of Dynamc Access to Cloud Database Based on Improved Pheromone Algorthm Yongqang L 1 and Jn Pan 2 1 (Software Technology Vocatonal College,

More information

Empirical Distributions of Parameter Estimates. in Binary Logistic Regression Using Bootstrap

Empirical Distributions of Parameter Estimates. in Binary Logistic Regression Using Bootstrap Int. Journal of Math. Analyss, Vol. 8, 4, no. 5, 7-7 HIKARI Ltd, www.m-hkar.com http://dx.do.org/.988/jma.4.494 Emprcal Dstrbutons of Parameter Estmates n Bnary Logstc Regresson Usng Bootstrap Anwar Ftranto*

More information

An Optimal Bandwidth Allocation and Data Droppage Scheme for Differentiated Services in a Wireless Network

An Optimal Bandwidth Allocation and Data Droppage Scheme for Differentiated Services in a Wireless Network Purdue Unversty Purdue e-pubs ECE Techncal Reports Electrcal and Computer Engneerng 3--7 An Optmal Bandwdth Allocaton and Data Droppage Scheme for Dfferentated Servces n a Wreless Network Waseem Shekh

More information

Adaptive Resource Allocation Control with On-Line Search for Fair QoS Level

Adaptive Resource Allocation Control with On-Line Search for Fair QoS Level Adaptve Resource Allocaton Control wth On-Lne Search for Far QoS Level Fumko Harada, Toshmtsu Usho, Graduate School of Engneerng Scence Osaka Unversty {harada@hopf, usho@}sysesosaka-uacjp Yukkazu akamoto

More information

Scheduling Remote Access to Scientific Instruments in Cyberinfrastructure for Education and Research

Scheduling Remote Access to Scientific Instruments in Cyberinfrastructure for Education and Research Schedulng Remote Access to Scentfc Instruments n Cybernfrastructure for Educaton and Research Je Yn 1, Junwe Cao 2,3,*, Yuexuan Wang 4, Lanchen Lu 1,3 and Cheng Wu 1,3 1 Natonal CIMS Engneerng and Research

More information

Real-Time Guarantees. Traffic Characteristics. Flow Control

Real-Time Guarantees. Traffic Characteristics. Flow Control Real-Tme Guarantees Requrements on RT communcaton protocols: delay (response s) small jtter small throughput hgh error detecton at recever (and sender) small error detecton latency no thrashng under peak

More information

Solution Brief: Creating a Secure Base in a Virtual World

Solution Brief: Creating a Secure Base in a Virtual World Soluton Bref: Creatng a Secure Base n a Vrtual World Soluton Bref: Creatng a Secure Base n a Vrtual World Abstract The adopton rate of Vrtual Machnes has exploded at most organzatons, drven by the mproved

More information

Evaluation of Parallel Processing Systems through Queuing Model

Evaluation of Parallel Processing Systems through Queuing Model ISSN 2278-309 Vkas Shnde, Internatonal Journal of Advanced Volume Trends 4, n Computer No.2, March Scence - and Aprl Engneerng, 205 4(2), March - Aprl 205, 36-43 Internatonal Journal of Advanced Trends

More information

Explicit Formulas and Efficient Algorithm for Moment Computation of Coupled RC Trees with Lumped and Distributed Elements

Explicit Formulas and Efficient Algorithm for Moment Computation of Coupled RC Trees with Lumped and Distributed Elements Explct Formulas and Effcent Algorthm for Moment Computaton of Coupled RC Trees wth Lumped and Dstrbuted Elements Qngan Yu and Ernest S.Kuh Electroncs Research Lab. Unv. of Calforna at Berkeley Berkeley

More information

An Investigation into Server Parameter Selection for Hierarchical Fixed Priority Pre-emptive Systems

An Investigation into Server Parameter Selection for Hierarchical Fixed Priority Pre-emptive Systems An Investgaton nto Server Parameter Selecton for Herarchcal Fxed Prorty Pre-emptve Systems R.I. Davs and A. Burns Real-Tme Systems Research Group, Department of omputer Scence, Unversty of York, YO10 5DD,

More information

Multi-objective Virtual Machine Placement for Load Balancing

Multi-objective Virtual Machine Placement for Load Balancing Mult-obectve Vrtual Machne Placement for Load Balancng Feng FANG and Bn-Bn Qu,a School of Computer Scence & Technology, Huazhong Unversty Of Scence And Technology, Wuhan, Chna Abstract. The vrtual machne

More information

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009.

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009. Farrukh Jabeen Algorthms 51 Assgnment #2 Due Date: June 15, 29. Assgnment # 2 Chapter 3 Dscrete Fourer Transforms Implement the FFT for the DFT. Descrbed n sectons 3.1 and 3.2. Delverables: 1. Concse descrpton

More information

SAO: A Stream Index for Answering Linear Optimization Queries

SAO: A Stream Index for Answering Linear Optimization Queries SAO: A Stream Index for Answerng near Optmzaton Queres Gang uo Kun-ung Wu Phlp S. Yu IBM T.J. Watson Research Center {luog, klwu, psyu}@us.bm.com Abstract near optmzaton queres retreve the top-k tuples

More information

Adaptive Network Resource Management in IEEE Wireless Random Access MAC

Adaptive Network Resource Management in IEEE Wireless Random Access MAC Adaptve Network Resource Management n IEEE 802.11 Wreless Random Access MAC Hao Wang, Changcheng Huang, James Yan Department of Systems and Computer Engneerng Carleton Unversty, Ottawa, ON, Canada Abstract

More information

Available online at ScienceDirect. Procedia Computer Science 46 (2015 )

Available online at  ScienceDirect. Procedia Computer Science 46 (2015 ) Avalable onlne at www.scencedrect.com ScenceDrect Proceda Computer Scence 46 (2015 ) 558 565 Internatonal Conference on Informaton and Communcaton Technologes (ICICT 2014) A Novel Famly Genetc Approach

More information

Priority-Based Scheduling Algorithm for Downlink Traffics in IEEE Networks

Priority-Based Scheduling Algorithm for Downlink Traffics in IEEE Networks Prorty-Based Schedulng Algorthm for Downlnk Traffcs n IEEE 80.6 Networks Ja-Mng Lang, Jen-Jee Chen, You-Chun Wang, Yu-Chee Tseng, and Bao-Shuh P. Ln Department of Computer Scence Natonal Chao-Tung Unversty,

More information

A fair buffer allocation scheme

A fair buffer allocation scheme A far buffer allocaton scheme Juha Henanen and Kalev Klkk Telecom Fnland P.O. Box 228, SF-330 Tampere, Fnland E-mal: juha.henanen@tele.f Abstract An approprate servce for data traffc n ATM networks requres

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

More information

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.15 No.10, October 2015 1 Evaluaton of an Enhanced Scheme for Hgh-level Nested Network Moblty Mohammed Babker Al Mohammed, Asha Hassan.

More information

Neural Network Control for TCP Network Congestion

Neural Network Control for TCP Network Congestion 5 Amercan Control Conference June 8-, 5. Portland, OR, USA FrA3. Neural Network Control for TCP Network Congeston Hyun C. Cho, M. Sam Fadal, Hyunjeong Lee Electrcal Engneerng/6, Unversty of Nevada, Reno,

More information

Burst Round Robin as a Proportional-Share Scheduling Algorithm

Burst Round Robin as a Proportional-Share Scheduling Algorithm Burst Round Robn as a Proportonal-Share Schedulng Algorthm Tarek Helmy * Abdelkader Dekdouk ** * College of Computer Scence & Engneerng, Kng Fahd Unversty of Petroleum and Mnerals, Dhahran 31261, Saud

More information

A New Transaction Processing Model Based on Optimistic Concurrency Control

A New Transaction Processing Model Based on Optimistic Concurrency Control A New Transacton Processng Model Based on Optmstc Concurrency Control Wang Pedong,Duan Xpng,Jr. Abstract-- In ths paper, to support moblty and dsconnecton of moble clents effectvely n moble computng envronment,

More information

Fast Retransmission of Real-Time Traffic in HIPERLAN/2 Systems

Fast Retransmission of Real-Time Traffic in HIPERLAN/2 Systems Fast Retransmsson of Real-Tme Traffc n HIPERLAN/ Systems José A Afonso and Joaqum E Neves Department of Industral Electroncs Unversty of Mnho, Campus de Azurém 4800-058 Gumarães, Portugal {joseafonso,

More information

Queueing Network-based Optimisation Techniques for Workload Allocation in Clusters of Computers *

Queueing Network-based Optimisation Techniques for Workload Allocation in Clusters of Computers * Queueng Network-based Optmsaton Technques for Workload Allocaton n Clusters of Computers * Lgang He, Stephen A. Jarvs, Davd Bacgalupo, Danel P. Spooner, Xnuo Chen and Graham R. Nudd Department of Computer

More information

Channel-Quality Dependent Earliest Deadline Due Fair Scheduling Schemes for Wireless Multimedia Networks

Channel-Quality Dependent Earliest Deadline Due Fair Scheduling Schemes for Wireless Multimedia Networks Channel-Qualty Dependent Earlest Deadlne Due Far Schedulng Schemes for Wreless Multmeda Networks Ahmed K. F. Khattab Khaled M. F. Elsayed ahmedkhattab@eng.cu.edu.eg khaled@eee.org Department of Electroncs

More information

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments Comparson of Heurstcs for Schedulng Independent Tasks on Heterogeneous Dstrbuted Envronments Hesam Izakan¹, Ath Abraham², Senor Member, IEEE, Václav Snášel³ ¹ Islamc Azad Unversty, Ramsar Branch, Ramsar,

More information

VRT012 User s guide V0.1. Address: Žirmūnų g. 27, Vilnius LT-09105, Phone: (370-5) , Fax: (370-5) ,

VRT012 User s guide V0.1. Address: Žirmūnų g. 27, Vilnius LT-09105, Phone: (370-5) , Fax: (370-5) , 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

A Model Based on Multi-agent for Dynamic Bandwidth Allocation in Networks Guang LU, Jian-Wen QI

A Model Based on Multi-agent for Dynamic Bandwidth Allocation in Networks Guang LU, Jian-Wen QI 216 Jont Internatonal Conference on Artfcal Intellgence and Computer Engneerng (AICE 216) and Internatonal Conference on etwork and Communcaton Securty (CS 216) ISB: 978-1-6595-362-5 A Model Based on Mult-agent

More information

On Achieving Fairness in the Joint Allocation of Buffer and Bandwidth Resources: Principles and Algorithms

On Achieving Fairness in the Joint Allocation of Buffer and Bandwidth Resources: Principles and Algorithms On Achevng Farness n the Jont Allocaton of Buffer and Bandwdth Resources: Prncples and Algorthms Yunka Zhou and Harsh Sethu (correspondng author) Abstract Farness n network traffc management can mprove

More information

Efficient Content Distribution in Wireless P2P Networks

Efficient Content Distribution in Wireless P2P Networks Effcent Content Dstrbuton n Wreless P2P Networs Qong Sun, Vctor O. K. L, and Ka-Cheong Leung Department of Electrcal and Electronc Engneerng The Unversty of Hong Kong Pofulam Road, Hong Kong, Chna {oansun,

More information

A Proactive Non-Cooperative Game-theoretic Framework for Data Replication in Data Grids

A Proactive Non-Cooperative Game-theoretic Framework for Data Replication in Data Grids Eghth IEEE Internatonal Symposum on Cluster Computng and the Grd A Proactve Non-Cooperatve Game-theoretc Framewor for Data Replcaton n Data Grds Al H. Elghran, Student Member, IEEE, Ry Subrata, Member,

More information

Use of Genetic Algorithms in Efficient Scheduling for Multi Service Classes

Use of Genetic Algorithms in Efficient Scheduling for Multi Service Classes Use of Genetc Algorthms n Effcent Schedulng for Mult Servce Classes Shyamale Thlakawardana and Rahm Tafazoll Centre for Communcatons Systems Research (CCSR), Unversty of Surrey, Guldford, GU27XH, UK Abstract

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Module Management Tool in Software Development Organizations

Module Management Tool in Software Development Organizations Journal of Computer Scence (5): 8-, 7 ISSN 59-66 7 Scence Publcatons Management Tool n Software Development Organzatons Ahmad A. Al-Rababah and Mohammad A. Al-Rababah Faculty of IT, Al-Ahlyyah Amman Unversty,

More information

MobileGrid: Capacity-aware Topology Control in Mobile Ad Hoc Networks

MobileGrid: Capacity-aware Topology Control in Mobile Ad Hoc Networks MobleGrd: Capacty-aware Topology Control n Moble Ad Hoc Networks Jle Lu, Baochun L Department of Electrcal and Computer Engneerng Unversty of Toronto {jenne,bl}@eecg.toronto.edu Abstract Snce wreless moble

More information

DEAR: A DEVICE AND ENERGY AWARE ROUTING PROTOCOL FOR MOBILE AD HOC NETWORKS

DEAR: A DEVICE AND ENERGY AWARE ROUTING PROTOCOL FOR MOBILE AD HOC NETWORKS DEAR: A DEVICE AND ENERGY AWARE ROUTING PROTOCOL FOR MOBILE AD HOC NETWORKS Arun Avudanayagam Yuguang Fang Wenjng Lou Department of Electrcal and Computer Engneerng Unversty of Florda Ganesvlle, FL 3261

More information

SRB: Shared Running Buffers in Proxy to Exploit Memory Locality of Multiple Streaming Media Sessions

SRB: Shared Running Buffers in Proxy to Exploit Memory Locality of Multiple Streaming Media Sessions SRB: Shared Runnng Buffers n Proxy to Explot Memory Localty of Multple Streamng Meda Sessons Songqng Chen,BoShen, Yong Yan, Sujoy Basu, and Xaodong Zhang Department of Computer Scence Moble and Meda System

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints Australan Journal of Basc and Appled Scences, 2(4): 1204-1208, 2008 ISSN 1991-8178 Sum of Lnear and Fractonal Multobjectve Programmng Problem under Fuzzy Rules Constrants 1 2 Sanjay Jan and Kalash Lachhwan

More information

Simulation Based Analysis of FAST TCP using OMNET++

Simulation Based Analysis of FAST TCP using OMNET++ Smulaton Based Analyss of FAST TCP usng OMNET++ Umar ul Hassan 04030038@lums.edu.pk Md Term Report CS678 Topcs n Internet Research Sprng, 2006 Introducton Internet traffc s doublng roughly every 3 months

More information

Needed Information to do Allocation

Needed Information to do Allocation Complexty n the Database Allocaton Desgn Must tae relatonshp between fragments nto account Cost of ntegrty enforcements Constrants on response-tme, storage, and processng capablty Needed Informaton to

More information

Enhanced Signaling Scheme with Admission Control in the Hybrid Optical Wireless (HOW) Networks

Enhanced Signaling Scheme with Admission Control in the Hybrid Optical Wireless (HOW) Networks Enhanced Sgnalng Scheme wth Admsson Control n the Hybrd Optcal Wreless (HOW) Networks Yng Yan, Hao Yu, Henrk Wessng, and Lars Dttmann Department of Photoncs Techncal Unversty of Denmark Lyngby, Denmark

More information

A Load-balancing and Energy-aware Clustering Algorithm in Wireless Ad-hoc Networks

A Load-balancing and Energy-aware Clustering Algorithm in Wireless Ad-hoc Networks A Load-balancng and Energy-aware Clusterng Algorthm n Wreless Ad-hoc Networks Wang Jn, Shu Le, Jnsung Cho, Young-Koo Lee, Sungyoung Lee, Yonl Zhong Department of Computer Engneerng Kyung Hee Unversty,

More information

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

More information

Kent State University CS 4/ Design and Analysis of Algorithms. Dept. of Math & Computer Science LECT-16. Dynamic Programming

Kent State University CS 4/ Design and Analysis of Algorithms. Dept. of Math & Computer Science LECT-16. Dynamic Programming CS 4/560 Desgn and Analyss of Algorthms Kent State Unversty Dept. of Math & Computer Scence LECT-6 Dynamc Programmng 2 Dynamc Programmng Dynamc Programmng, lke the dvde-and-conquer method, solves problems

More information