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

Save this PDF as:
 WORD  PNG  TXT  JPG

Size: px
Start display at page:

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

Transcription

1 Send Orders for Reprnts to The Open Cybernetcs & Systemcs Journal, 2014, 8, Open Access A Load Balancng Strategy wth Bandwdth Constrant n Cloud Computng Jng Deng 1,*, Png Guo 2, Q L 3, Hazhu Chen 1 1 Department of Computer, Chongqng College of Electronc Engneerng, Chongqng, , Chna; 2 College of Computer Scence, Chongqng Unversty, Chongqng, , Chna; 3 Chna Telecom Corporaton Lmted Chongqng Branch, Chongqng, , Chna Abstract: The schedulng strategy on load balancng, used by data center n cloud computng, plays an mportant role on computng performance, and t s a key technque for the hgh-performance servce. It drectly controls the total performance and the effcency of resource n cloud computng. In ths paper, we ntroduce seven recent patents n the area of load balancng of cloud computng and dscuss some classcal load balancng algorthms (especally Mn-Mn algorthm). Based on Mn-Mn algorthm, a new mproved algorthm named BCLL-Mn-Mn s proposed. It can satsfy the bandwdth constrant and mplement the relatve load balancng schedulng. The smulated experments show that BCLL-Mn-Mn algorthm s wdely avalable for the dverse and uncertan tasks n cloud computng. It mproves the load balance n data center and enhances the throughput n the cluster. Keywords: Cloud computng, load balance, Mn-Mn algorthm, BCLL-Mn-Mn algorthm. 1. INTRODUCTION Cloud computng s a model for enablng ubqutous, convenent, on-demand network access to a shared pool of confgurable computng resources (e.g., networks, servers, storage, applcatons, and servces) that can be rapdly provsoned and released wth mnmal management effort or servce provder nteracton [1]. Cloud computng enables data centers to operate lke the Internet by the process of makng computng and storage resources to be accessed and shared as vrtual resources n a secure and scalable manner. Cloud data centers accommodate a lot of computng and storage equpments, and they provde servces by combnng mult-node servers as a cluster [2]. In the cluster, the balance s dspatched to each node for promotng resource utlzaton and reducng the watng-tme of users. The advanced load balancng strategy s one of the key technques for hghperformance servce, cost savngs and mprovng the cluster throughput [3]. Up to now, several load balance strateges have been presented nto cloud computng. Patent US 0,031,550, ttle Method for mprovng the performance of hgh performance computng applcatons on cloud usng ntegrated load balancng [4], provdes an expected cost set assocated wth an applcaton-specfc task of an applcaton executng on a processng resource n a cloud computng envronment, and communcatng the expected cost set from the processng resource to a cloud management system. Then a task to VM (vrtual machne) assgnment s determned based on the assgnment of the applcaton-specfc task to the specfc computatonal resource. Patent US 0,217,100, ttle Method and system for load balancng content delvery servers [5], presents a cloud computng content delvery system and t ncludes multple content delvery servers (CDSs) confgured to delver content to multple clent devces. The clent devces send requests to the CDS for the mrror lst. Then they send content requests to the frst entry n the lst. Each CDS can update the mrror lst by applyng a load balancng algorthm and provde the mrror lst to a clent devce n the event that one or more CDSs are unavalable. Patent US 0,166,645, ttle Method and apparatus for load balancng n mult-level dstrbuted computatons [6], provdes load balancng n mult-level dstrbuted computatons. A dstrbuted computaton control platform determnes closure capablty data assocated wth respectve levels of a computatonal archtecture, wheren the respectve levels nclude a devce level, an nfrastructure level, and a cloud computng level. The dstrbuted computaton control platform further determnes to cause processng the closure capablty data. Patent CN , ttle Cloud computng load balancng method based on layerng multple agents [7], relates to a cloud computng load balancng method based on layerng multple agents. Two of a pluralty of nodes whch are connected wth a cloud computng platform through the network are used as a task montorng agent and a resource montorng agent, agents are ont management nodes of the cloud computng platform, each management node performs task allocaton accordng to load condtons, dfferent management nodes respectvely take charge of montorng, resource allocatng and the lke. So that a pluralty of cloud computng tasks can be concurrently and effectvely processed, and task processng capacty of the cloud computng platform s mproved. Patent CN , ttle Cloud computng load balancng method and equpment [8], provdes a cloud computng load balancng method and equpment. The load capacty of the server can be changed adaptvely; and the proper servce X/ Bentham Open

2 116 The Open Cybernetcs & Systemcs Journal, 2014, Volume 8 Deng et al. copy s selected accordng to the load capacty of the server to ensure comparatvely unform load dstrbuton on each copy and realze adaptve load balance of the server. The current schedulng algorthms takes short tme, hgh degree of satsfacton and load balancng as the optmzaton goals and ther algorthms can be classfed nto two types; statc and dynamc. The statc type, whch s based on Posson dstrbuton of the tasks and exponental dstrbuton of response tme, ncludes RR [9], WRR [10]. They are avalable for the statc server systems wth small sze and smple confguraton snce the resources utlzaton s descrbed by a lttle statc feature nformaton and the resources are allocated to the comng task n proper sequence. When the tasks becomes dverse and uncertan, the effect of load balancng wll be undesrable [11] wth a dfference of 10 to 100 tmes. The type of dynamc algorthms s presented subsequently, such as LC, WLC [10]. They wll compute the load of the servers n a perod of tme accordng to dfferent factors before the tasks arrve, so the comng task wll be assgned to a sutable sever. The most dffcult problem n ths type of algorthm s how to choose an approprate coeffcent to compute the load of the servers. Patent CN , ttle Cloud calculatng load balancng schedulng algorthm based on double-weghted least-connecton algorthm [12], dscloses a cloud calculatng load balancng schedulng algorthm based on a double-weghted least-connecton algorthm. In the algorthm, no relatvely large nclnaton of a load of each node s guaranteed when a system s n a long tme operaton state, summaton of all task weghts of each server and weght rato of performances of the servers are calculated by a scheduler before task dstrbuton, new tasks are dstrbuted to the servers wth smallest ratos. The algorthm shortens average accomplshment tme of the cloud calculatng servce system, mproves system effcency and further mproves a load balancng degree of each resource server n a cloud data center. Mn-Mn and TD-Mn-Mn are heurstc schedulng algorthms [13, 14], and shortenng the total completon tme of all tasks s ther optmzaton goal: Mn-Mn algorthm assgns the task accordng to the mappng between vrtual machne and the task whose completon tme s the shortest; whle TD-Mn-Mn algorthm uses the mappng between vrtual machne and the task whose completon tme s the longest. Comparng wth the statc algorthms, the performance of the dynamc ones s better, for they know the realtme load of the servers. But ther performance wll be poor n cloud computng because they are not avalable for the tasks wth dfferent sze and the resources wth bg dversty. The remander of ths paper s organzed as follows: Secton 2 ntroduces the schedulng modes n cloud computng, Mn-Mn and LL-Mn-Mn algorthms [15]; n secton 3, we present BCLL-Mn-Mn that can satsfy the bandwdth constrant and mplement the relatve load balancng schedulng; smulated experments are analyzed n Secton 4; the last secton concludes ths paper. 2. CLASSIC SCHEDULING MODEL AND ALGO- RITHM IN CLOUD COMPUTING The archtecture of cloud computng conssts of three layers: applcaton, platform and nfrastructure layers [16]. Ths archtecture makes the load schedulng n cloud computng a two-level mode [17]. The frst level s the assgnment between user applcaton and vrtual machne, and the task wll be assgned to a sutable vrtual machne accordng to the performance requrements or other lmted factors of the task. Whle the second one s the assgnment between vrtual machne and host, t means that the second level selects the approprate one from the physcal hosts accordng to resource request of each task n the vrtual machne and dynamcally balances the loads of the physcal machnes. Ths model can satsfy all performance requrements of dfferent tasks and the lmted factors. What s more, t can avod ncreasng the executon tme for short of computng resource or wastng the resources snce the dstrbuted resource s more than the task needs. Thanks to the vrtualzaton technology, we can only concern ourselves wth the frst level schedulng of the model n cloudng computng The Task Parameter Model n Cloud Computng Let C = { C1, C2, C3,... Cn} be a gven task sets of cloud computng. And each task C can be represented as: C = { ID, length, ExpB, Bwsat} (1) where, ID unquely dentfes the task, and length s gven as ts estmated completon tme. ExpB s the expected bandwdth and t s the unque measure of the users' satsfacton. Obvously, a task s assgned to a vrtual machne that can perform the task. In partcular, Bwsat s the measure of the satsfyng bandwdth and t can be calculated by: 1 f ExpB <= Bw Bwsat = 0 otherwse where, Bw s the bandwdth of the vrtual machne. Eq.(2) means, f the resource of a vrtual machne can be used to perform the task, Bwsat s set by 1. Otherwse, t set by The Vrtual Machne Resource Model n Cloud Computng Let V = { V1, V2, V3,... Vm} be the set of vrtual machnes n cloud computng data center, and each vrtual machne V can be represented as: V = { ID, PE, mps, Ram, Bw, VL} (3) where, ID unquely dentfes the vrtual machne. PE s the number of executve unt n the vrtual machne. mps s the executon speed of the vrtual machne. Ram s the memory sze. Bw s the bandwdth of the vrtual machne and t s compared wth ExpB. VL s the workloads of the vrtual machne. Whle some resource, such as external storage, are not consdered, because they have lttle effect on the workloads of the vrtual machne. (2)

3 A Load Balancng Strategy wth Bandwdth Constrant n Cloud Computng The Open Cybernetcs & Systemcs Journal, 2014, Volume Based on the parameters of the vrtual machnes and the task parameter model, our new algorthm presented bellow wll select the vrtual machne n Eq.(3) for the tasks n Eq.(1) by a sutable load schedulng strategy The Load Model n Cloud Computng Assume that an accurate estmaton of the expected completon tme for each task on each machne s known before the executon and contaned wthn an ETC (namely, expected tme to compute) matrx. ETC[ ][ ] s the estmated completon tme of task on vrtual machne. ETC[ ][ ] s nfluenced by many factors. In ths paper, we assume that ETC[ ][ ] s only nfluenced by length, the length of task, and mps s the executon speed of the vrtual machne. To smplfy the model, we have two conventons as follows: 1) The fnshbg tme of all tasks s fxed when many tasks are executed n a vrtual machne smultaneously. 2) If executng tme of a task s the mnmum on a vrtual machne, the task s executng tme would be the mnmum on other vrtual machne. 3) If the executon speed of a vrtual machne s the maxmum, no matter whch task, ts executon speed s the maxmum. Namely, the executon speed s not related to the task. ETC[ ][ ] can be calculated by: T = length / mps (4) T ETC [ ][ ] = (5) Assume that there are n tasks and m vrtual machnes. The estmated completon tme of n tasks can be calculated by Eqs. (4) and (5) and the result can be expressed by a matrx: T11 T = 21 ETC Tn1 T1 m T 2m Tnm The tasks of dfferent users have nothng n common wth the processng ablty of vrtual machnes n cloud computng data centers and they are dffer from one another. All these ncrease the dffcultes of defnng the workload. In ths paper, two assumptons are gven as followng shows. The frst assumpton, the workload of a task s only related to length of the task. Namely, the longer the length s, the heaver the workload s. The second assumpton, the processng ablty of a vrtual machne s only related to mps, the executon speed of vrtual machne, wthout consderng the bandwdth, the memory sze and so on. mps can be determned to weght accordng to ts hstorcal record. The workload of vrtual machne can be defned as VL and the workload caused by task of vrtual machne can be calculated by: (6) VL = length / mps (7) We know from Eq.(4), the length / mps s equal to the T. So, the workload of vrtual machne s equal to the total sum of all tasks processed n the vrtual machne: VL = T (8) So the load balancng schedulng can be descrbed as all the vrtual machnes have equvalent executng tme of tasks. And a standard measurng load balancng s defned as: = T /T mn max (9) where, T s the mnmal and mn T max s the maxmal completon tme of all vrtual machnes. The results were obtaned as follows accordng to Eq.(9). 1) The tasks are not scheduled when T s equal to 0. max 2) There are dle vrtual machnes when s equal to 0 and T s not equal to 0. max 3) There s the hghest load balance degree when s equal to one, namely, the maxmum s equal to mnmum of workload. Moreover, the closer to 1 s, the hgher the load balance degree s Mn-Mn [13] and LL-Mn-Mn [15] Up tll now, many schedulng algorthm derved from Mn-Mn algorthm. Mn_Mn heurstc begns wth the set U of all unmapped tasks, and then the set of mnmum completon tmes s found. Next, the task wth the overall mnmum completon tme s selected and assgned to the correspondng machne (hence the name Mn_Mn). Last, the newly mapped task s removed from U, and the process repeats untl all tasks are mapped (.e., U s empty). Mn_Mn maps the tasks n the order that changes the machne avalablty status by the least amount that any assgnment could. The expectaton s that a smaller makespan can be obtaned f more tasks are assgned to the machnes that complete them the earlest and also execute them the fastest. LL-Mn-Mn s one of the mproved versons of Mn-Mn and t mplements the relatve load balancng schedulng. In ths algorthm, the task wth the relatvely largest load and the mnmum completon tme s chosen, so each task has an opportunty to be performed n dfferent vrtual machne parallel and the utlzaton percentage of the vrtual machnes can be promoted. The relatve load can descrbe the dfference of the completon tmes of each task n dfferent vrtual machnes, so choosng the maxmum dfferent one from the current task can avod ncreasng the load or the makespan. 3. BCLL-MIN-MIN ALGORITHM When users use cloud computng servce and ask for vrtual machne resource, they rase some vrtual machne performance requests. For example, bandwdth request of tasks, obvously servce provder should satsfy ts users and meet the user demands by dstrbutng suffcent vrtual machne resource. Smultaneously, the completon tme must be short

4 118 The Open Cybernetcs & Systemcs Journal, 2014, Volume 8 Deng et al. Table 1. An example of BCETC matrx (unt: ms). M 1 M 2 M 3 M 1 C C 2 N C 3 N N N 22 C 4 N C 5 N N enough, because t relates to the user's feelng drectly. In concluson, basng on LL-Mn-Mn algorthm and bandwdth constrant, we propose a load balancng strategy wth bandwdth constrant n cloud computng, named as BCLL-Mn- Mn. BCLL-Mn-Mn algorthm's optmstc goal s: loadng balance; satsfy dfferent task bandwdth request; short completon tme. For smplcty, we appont task schedulng that meet two condtons: 1) There s no relaton between two tasks; 2) When a task s dstrbuted to the vrtual machne, other tasks must wat untl t s accomplshed; Base on the above schedulng, we rase schedulng dscplne to realze BCLL-Mn-Mn algorthms optmze goal: 1) If a vrtual machne satsfes the bandwdth requrements, the task wll assgn to the vrtual machne. 2) If there are multple vrtual machnes that meet bandwdth requrements, the task wll be assgned to the one whose executon tme s mnmal The dea of BCLL-Mn-Mn BCLL-Mn-Mn algorthm should meet user s demand for bandwdth and guarantee a certan load balance. The bandwdth requrements can be clarfed by the user s request or by queryng the hstorcal nformaton, and n BCLL-Mn-Mn algorthm, the choce of the bandwdth s based on the user s consderaton. For the bandwdth-demand tasks, ETC that wll meet the bandwdth constrant matrces are named BCETC, and the core of the BCLL-Mn-Mn algorthm s BCETC. The estmated executon tme n BCETC matrx s the same as before when vrtual machne resource meet the user s demand. However, the task cannot be assgned to the vrtual machne and the value of estmated executon tme wll be set N n the same place of BCETC matrx f t does not meet user s need BCETC matrx as shown n the Table 1, the bandwdth n vrtual machne M 1, M 2, M 3, M 4 ncreases successvely. Due to the lower bandwdth requrements of the task C 1, these 4 vrtual machnes satsfy the condton, the frst lne unchanged. But n the second lne, M 1 does not meet the requrement, the value n the [ C 1, M ] wll be set to N, that s 1 not mapped. Smlarly, we can conclude the map between the other tasks and vrtual machnes. Meanwhle, n order to acheve a certan level of load balance, the fewer vrtual machnes wll be gven Prorty schedulng f they satsfy the bandwdth requrements, the procedure of ths sort of schedulng s gven below: Step1: Only one vrtual machne that meet ther requrements. Step2: At least two vrtual machnes that meet ther requrements. Step3: All vrtual machnes that meet ther requrements. Step4: All vrtual machnes that do not meet ther requrements. If we never adopt these schedulng, the tasks of greater coverage wll be performed n the vrtual machne wth a low bandwdth, and t wll result n a serously uneven load. In order to ensure the task and vrtual machnes correspondng to the N n matrx BCETC never be assgned, we set N wth a large value (greater than the sum of all the task completon tme). Therefore, a task wth largest gap n average and mnmum executed tme wll be executed frstly. The less vrtual machnes meet the requrement, the greater the D- value s. Ths algorthm wll preferentally select the task and meet these characterstcs Algorthm Descrpton Algorthm: BCLL-Mn-Mn Input: vrtual machne parameter, tasks parameter Output: mappng scheme Procedure: Step1: generate C to record all tasks; modfy V to record all vrtual machne; defnte CTOV to record current mappng scheme; generate VMLoad to record all vrtual machnes' loadng; Los s an array whch has relatvely loadng of each task; Step2: accordng to tasks' expected nstructon length, vrtual machnes processng speed and bandwdth-demand tasks, we can get the ETC[ ][ ] ; Step3: foreach C n C ; add VMLoad[] to BCETC [][]; foreach C n C ; foreach V n V ;

5 A Load Balancng Strategy wth Bandwdth Constrant n Cloud Computng The Open Cybernetcs & Systemcs Journal, 2014, Volume fnd mnmum completon tme of each task; calculate average tme for each task that remove the mnmum tme; get LL by calculatng the D-value from average tme and mnmum tme; end foreach end foreach choose the task-resource mappng of bggest D-value, and keep n CTOV; Accordng to ETC array refresh VMLoad, delete task that have done from C. end foreach End. BCLL-Mn-Mn algorthm not only dstrbutes tasks preferentally to whose relatve loadng s heavy but also adds user satsfacton. It solves Mn-mn algorthm's problems for optmze goal uncty and load mbalance. 4. SIMULATION EXPERIMENTAL RESULTS AND ANALYSIS In order to verfy the performance of the BCLL-Mn-Mn algorthm, ths secton uses cloud computng smulaton tools CloudSm [9] to do a comparatve experment among BCLL- Mn-Mn algorthm, Round-Robn (CloudSm platform comes wth round-robn schedulng algorthm, referred to as RR algorthm) and Mn-Mn schedulng algorthm (referred to as MM algorthm) n the completon tme of task, load of the vrtual machne and completon of the task bandwdth requrement classes. Patent CN , ttle Cloud computng load balancng evaluaton system and evaluaton method [18], nvents a cloud computng load balancng evaluaton system. In the system, a sgnal output end of a cloud cluster load nformaton collecton module s connected wth a sgnal nput end of an mage converson module, and the sgnal output end of the mage converson module s connected wth a sgnal nput end of a cluster balance analyss module. Accordng to the nventon, the load converson pcture can be generated by adoptng the method for mappng the node comprehensve load value to the grayscale map and s analyzed accordng to the load mage analyss method, thus achevng the purpose of accurately and wholly evaluatng a load. In our prevous work, we take experment and verfcaton n terms of LL-Mn-Mn algorthm for the case of heterogeneous task and unfxed length of the tasks n heterogeneous envronments. Ths paper compares and verfes the case of tasks wth unfxed length based on the strength of Mn-Mn algorthm, observng the mplementaton of tasks n the bandwdth constrants. Ths paper selects the followng two sets of expermental data based on the standard of the total executon tme of the task and load balancng of the vrtual machne: The frst group: 100, 200, 300 tasks and 10 vrtual machnes load schedulng. The man references are task span, vrtual machne load and completon of the task n bandwdth requrements. All parameters are randomly generated, dfference between tasks and vrtual machne performance heterogeneous s lttle, and the rato of bandwdth requrement task s 50%. The second group: adustng the rato of the bandwdth requrement task, 40%, 60% and 80% respectvely; observng the executon tme of three algorthms wth the effect of dfferent rato bandwdth requrement task. As shown n Fg. (1), RR algorthm takes the longest completon tme, BCLL-mn algorthm followed; Mn-mn algorthm s slghtly better than the BCLL-mn algorthm n tme span. RR algorthm s the clearly worst because t does not consder the characterstcs of the vrtual machne and tasks, and t assgns tasks to a vrtual machne sequentally. Mn-mn algorthm has good results n the neat tasks; and t does not consder the bandwdth needs of the users, whch means that t assgns the unsatsfed resources to users; as a result, Mn-mn algorthm s better than BCLL-mn algorthm n executon tme span. Overall, BCLL-mn algorthm meets the basc need n bandwdth requrement, and t guarantees the completon tme. Fg. (1). Comparson of completon tme. Fg. (2). Comparson of loadng balance. The comparson of load balancng of the vrtual machne s shown n Fg. (2). It can be seen that BCLL-mn algorthm has the hghest load balancng vrtual machne under the bandwdth requrements at 50%. Because the bandwdth requrements classes of the task takes only 50%, and the remanng tasks make up for load nequalty caused by bandwdth requrements to a certan extent based on the algorthm characterstcs, achevng optmzaton goal based on load balancng. Performance of Mn-Mn algorthm s good under tasks n certan condtons. But Mn-Mn algorthm s stll worse than BCLL-mn algorthm, whle load balance of these two algorthms perform well when the task ncreases. However, RR algorthm s the worst.

6 120 The Open Cybernetcs & Systemcs Journal, 2014, Volume 8 Deng et al. If tasks wth bandwdth constrants can be performed by some vrtual machnes, the value of Eq.(2) s set by 1. 50% of the bandwdth requrement classes tasks, whch the maxmum s 50, all meet under the case of 100 tasks. Smlarly, 200 tasks are 100 and 300 tasks are 150. The comparson of the completon of the bandwdth tasks s shown n Fg. (3). As Fg. (3) shows, BCLL-Mn algorthm can satsfy bandwdth requrement classes. Whle Mn-Mn algorthm ust can meet a lttle snce t has not the optmzaton goal of bandwdth requrement. However, the RR algorthm wll defntely have some tasks to meet the needs because of the allocaton of a fxed rotaton, and t equally matches Mn- Mn algorthm under the satsfacton of bandwdth requrement. Therefore, compared wth a slght tme dfference n BCLL-mn algorthm, BCLL-mn algorthm acheves a bg satsfacton dfference forthe user tasks. Fg. (5) shows that BCLL-mn algorthm makespan s ncreased wth the lmt of bandwdth requrements constrants, because the satsfed machne lessens after ncreasng the bandwdth lmtng, and t sacrfces some completon tme to meet the tasks. In contrast, Mn-Mn algorthm does not consder bandwdth requrements, so completon tme wth dfferent rato s not much dfferent. However, n general, there wll not be so much tasks of type of bandwdth requrement. Fg. (3). Comparng the bandwdth satsfacton of the tasks. In order to observe tasks wth dfferent rato bandwdth constrants mpact on load schedulng tasks, we adust the rato of bandwdth requrement tasks and ncrease bandwdth for tasks requrement n the second experments. We desgn 200 heterogeneous and lttle dfferent tasks and 10 heterogeneous vrtual machne resources to reflect the comparson between BCLL-mn algorthm and Mn-Mn algorthm based on Mn-Mn algorthm strengths. All parameters are stll randomly generated. The experments results of bandwdth satsfacton wth three ratos are shown n Fg. (4). Fg. (4). Comparson of 200 dfferent proportons tasks satsfacton. From Fg. (4), we can see that BCLL-mn algorthm can bascally meet the bandwdth requrement of users. The growth rate of Mn-Mn algorthm and the RR algorthm s not sgnfcant wth the ncrease n bandwdth rato, and they do not meet bandwdth requrement well. However, wth the rato of bandwdth requrement tasks ncreasng, requrement of bandwdth constrants and lmtng ncreases, meetng the bandwdth requrements wll nevtably lose some tme span. Fg. (5). Comparson of 3 proportons knds of the tme span. Overall, BCLL-mn algorthm s the best under varous condtons, load balance and task completon satsfacton. But task completon tme of BCLL-mn algorthm wll be slghtly reduced wth rato of bandwdth requrement tasks ncreasng. As clearly obtaned from the experments, BCLL-mn algorthm s better than the other two algorthms n heterogeneous task and heterogeneous envronments, and t meets bandwdth requrement. The followng conclusons can be drawn from smulaton experments: 1) Under the number of tasks wth lttle dfference, the load balance of BCLL-mn algorthm s the best. In order to meet bandwdth requrement, the total completon tme of BCLL-mn algorthm s not better than that of Mn-Mn algorthm, not consderng the bandwdth requrement, but much better than that of RR algorthm. 2) Under the number of tasks wth lttle dfference, BCLL-mn algorthm s the best n optmzaton goals and guarantees the load balancng, snce addng bandwdth lmtatons. 3) BCLL-mn algorthm wll have some mpact on task executon tme wth bandwdth constrants condton ncreasng, but t can meet bandwdth requrements tasks at any rato. Meanwhle, BCLL-mn algorthm wll be as effcent as LL-Mn-Mn algorthm f there s no bandwdth requrement. 5. CONCLUSION The computng tasks n cloud computng s not only complcated but also dverse. Consderng on the heterogenety of the vrtual machnes and dversty of the tasks n cloud computng, we mprove classcal Mn-Mn algorthm and LL-Mn-Mn algorthm and present BCLL-Mn-Mn algorthm, whch can satsfy the bandwdth constrants and mplement the relatve load balancng schedulng. The experments performed on smulaton platform CloudSm show that BCLL-Mn-Mn algorthm s more avalable for schedulng the tasks n cloud computng and t can mprove the

7 A Load Balancng Strategy wth Bandwdth Constrant n Cloud Computng The Open Cybernetcs & Systemcs Journal, 2014, Volume load balance n data center and enhances the throughput n the cluster. CONFLICT OF INTEREST The authors confrm that ths artcle content has no conflct of nterest. ACKNOWLEDGEMENTS Ths work s supported by Natural Scence Foundaton Proect of CQ CSTC 2012A40022) and the Natonal Scence Foundaton for Young Scholars of Chna (Grant No ). REFERENCES [1] P. Mell and T. Grance, The NIST defnton of cloud computng, Commun. ACM, vol. 53, pp , [2] H. L. Zeng, B. F. Zhang and L. H. Zhang, Vrtual cluster constructng based on cloud computng platform, Mcroelectron. Comp., vol. 27, pp , 2010 (n Chnese). [3] R. Buyya, Hgh performance cluster computng: Systems and archtectures, Mchgan: Prentce Hall PTR, [4] A. R. Choudhury, T. George, M. Keda, Y. Sabharwal and V.Saxena, Method for mprovng the performance of hgh performance computng applcatons on cloud usng ntegrated load balancng, U.S. Patent 0,031,550, January 31, 2013 [5] P. Goerner, G. Breen, R. H. Smth, S. C. Dandy and A. H. Brdge, Method and system for load balancng content delvery servers, U. S. Patent 0,217,100, August 22, 2013 [6] S. Boldyrev, H. E. Lane, J. H. Kaaa, J. Honkola, V. Luukkala and I. J. Olver, Method and apparatus for load balancng n multlevel dstrbuted computatons, U. S. Patent 0,166,645, June 28, [7] X. L. Tao, Y. Wang, Y. Pe, P. H. L and Q. L. Zhou, Cloud computng load balancng method based on layerng multple agents, C. N. Patent CN , May 22, [8] C. Jn and X. Zhang, Cloud computng load balancng method and equpment, C. N. Patent CN , October 27, 2010 [9] The clouds lab, CloudSm: a novel framework for model-ng and smulaton of cloud computng nfrastructures and servces, cloudsm/. September 2, [10] E. Cho, Performance test and analyss for an adaptve load balancng mechansm on dstrbuted server cluster systems, Future Generaton Computer Systems, vol. 20, pp , [11] E. Casslccho and S. Tucc, Statc and Dynamc schedulng algorthm for scalable Web server farm, In the IEEE 9th Euromcro Workshop on Parallel and Dstrbuted Processng, IEEE Conference Publcatons, 2001, pp [12] L. Y. Zhou, X. P. Cu and J. Zheng, Cloud calculatng load balancng schedulng algorthm based on double-weghted leastconnecton algorthm, C. N. Patent CN , October 2, 2013 [13] T. D. Braun, H. J. Segel, N. Beck, A comparson of eleven statc heurstcs for mappng a class of ndependent tasks onto heterogeneous dstrbuted computng systems, Journal of Parallel and Dstrbuted computng, Vol. 61, pp , [14] A. Iyengar, E. MacNar and T. Nguyen, An analyss of Web server performance, In Global Telecommuncatons Conference, IEEE Conference Publcatons, 1997, pp. 1943~1947. [15] P. Guo, T. L and Q. L, A schedulng strategy on load balancng n cloud computng (n Chnese) (Accepted). [16] S. Sadhasvam, N. Nagaven, R. Jayaran, R.V. Ram, Desgn and mplementaton of an effcent two-level scheduler for cloud computng envronment, In Advances n Recent Technologes n Communcaton and Computng, IEEE Conference Publcatons, 2009, pp [17] G. Lu, J. L and J. C. Xu, An mproved mn-mn algorthm n cloud computng, In Proceedngs of the 2012 Internatonal Conference of Modern Computer Scence and Applcatons. Berln, Sprnger, 2013, pp [18] H. F. Huang, P. Wang, K. Cao, J. Y. Dong, H. Tang, L. Chen, C. Ren and Y.Huang, Cloud computng load balancng evaluaton system and evaluaton method, C. N. Patent CN , August 22, Receved: September 22, 2014 Revsed: November 30, 2014 Accepted: December 02, 2014 Deng et al.; Lcensee Bentham Open. Ths s an open access artcle lcensed under the terms of the Creatve Commons Attrbuton Non-Commercal Lcense ( lcenses/by-nc/3.0/) whch permts unrestrcted, non-commercal use, dstrbuton and reproducton n any medum, provded the work s properly cted.

Communication Networks II Contents

Communication Networks II Contents 8 / 1 -- Communcaton Networs II (Görg) -- www.comnets.un-bremen.de Communcaton Networs II Contents 1 Fundamentals of probablty theory 2 Traffc n communcaton networs 3 Stochastc & Marovan Processes (SP

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

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

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

Load Balancing By Max-Min Algorithm in Private Cloud Environment

Load Balancing By Max-Min Algorithm in Private Cloud Environment Internatonal Journal of Scence and Research (IJSR ISSN (Onlne: 2319-7064 Index Coperncus Value (2013: 6.14 Impact Factor (2013: 4.438 Load Balancng By Max-Mn Algorthm n Prvate Cloud Envronment S M S Suntharam

More information

A heuristic task deployment approach for load balancing

A heuristic task deployment approach for load balancing Xu Gaochao, Dong Yunmeng, Fu Xaodog, Dng Yan, Lu Peng, Zhao Ja Abstract A heurstc task deployment approach for load balancng Gaochao Xu, Yunmeng Dong, Xaodong Fu, Yan Dng, Peng Lu, Ja Zhao * College of

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

A Dynamic Load Balancing for Massive Multiplayer Online Game Server

A Dynamic Load Balancing for Massive Multiplayer Online Game Server A Dynamc Load Balancng for Massve Multplayer Onlne Game Server Jungyoul Lm, Jaeyong Chung, Jnryong Km and Kwanghyun Shm Dgtal Content Research Dvson Electroncs and Telecommuncatons Research Insttute Daejeon,

More information

Survey on Virtual Machine Placement Techniques in Cloud Computing Environment

Survey on Virtual Machine Placement Techniques in Cloud Computing Environment Survey on Vrtual Machne Placement Technques n Cloud Computng Envronment Rajeev Kumar Gupta and R. K. Paterya Department of Computer Scence & Engneerng, MANIT, Bhopal, Inda ABSTRACT In tradtonal data center

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

Dynamic Fleet Management for Cybercars

Dynamic Fleet Management for Cybercars Proceedngs of the IEEE ITSC 2006 2006 IEEE Intellgent Transportaton Systems Conference Toronto, Canada, September 17-20, 2006 TC7.5 Dynamc Fleet Management for Cybercars Fenghu. Wang, Mng. Yang, Ruqng.

More information

Heuristic Scheduling Algorithms for Allocation of Virtualized Network and Computing Resources

Heuristic Scheduling Algorithms for Allocation of Virtualized Network and Computing Resources Journal of Software Engneerng and Applcatons, 203, 6, -3 http://dx.do.org/0.4236/sea.203.600 Publshed Onlne January 203 (http://www.scrp.org/ournal/sea) Heurstc Schedulng Algorthms for Allocaton of Vrtualzed

More information

Resource Scheduling in Desktop Grid by Grid-JQA

Resource Scheduling in Desktop Grid by Grid-JQA The 3rd Internatonal Conference on Grd and Pervasve Computng - Worshops esource Schedulng n Destop Grd by Grd-JQA L. Mohammad Khanl M. Analou Assstant professor Assstant professor C.S. Dept.Tabrz Unversty

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

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

A Dynamic Energy-Efficiency Mechanism for Data Center Networks

A Dynamic Energy-Efficiency Mechanism for Data Center Networks A Dynamc Energy-Effcency Mechansm for Data Center Networks Sun Lang, Zhang Jnfang, Huang Daochao, Yang Dong, Qn Yajuan A Dynamc Energy-Effcency Mechansm for Data Center Networks 1 Sun Lang, 1 Zhang Jnfang,

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

A Load-Balancing Algorithm for Cluster-based Multi-core Web Servers

A Load-Balancing Algorithm for Cluster-based Multi-core Web Servers Journal of Computatonal Informaton Systems 7: 13 (2011) 4740-4747 Avalable at http://www.jofcs.com A Load-Balancng Algorthm for Cluster-based Mult-core Web Servers Guohua YOU, Yng ZHAO College of Informaton

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

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

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

"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

Rate Monotonic (RM) Disadvantages of cyclic. TDDB47 Real Time Systems. Lecture 2: RM & EDF. Priority-based scheduling. States of a process

Rate Monotonic (RM) Disadvantages of cyclic. TDDB47 Real Time Systems. Lecture 2: RM & EDF. Priority-based scheduling. States of a process Dsadvantages of cyclc TDDB47 Real Tme Systems Manual scheduler constructon Cannot deal wth any runtme changes What happens f we add a task to the set? Real-Tme Systems Laboratory Department of Computer

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

An Energy-Efficient Data Placement Algorithm and Node Scheduling Strategies in Cloud Computing Systems

An Energy-Efficient Data Placement Algorithm and Node Scheduling Strategies in Cloud Computing Systems 2nd Internatonal Conference on Advances n Computer Scence and Engneerng (CSE 2013) An Energy-Effcent Data Placement Algorthm and Node Schedulng Strateges n Cloud Computng Systems Yanwen Xao Massve Data

More information

Study on CET4 Marks in China s Graded English Teaching

Study on CET4 Marks in China s Graded English Teaching Study on CET4 Marks n Chna s Graded Englsh Teachng CHE We College of Foregn Studes, Shandong Insttute of Busness and Technology, P.R.Chna, 264005 Abstract: Ths paper deploys Logt model, and decomposes

More information

Frequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters

Frequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters Frequency Selectve IQ Phase and IQ Ampltude Imbalance Adjustments for OFDM Drect Converson ransmtters Edmund Coersmeer, Ernst Zelnsk Noka, Meesmannstrasse 103, 44807 Bochum, Germany edmund.coersmeer@noka.com,

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

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

IWFMS: An Internal Workflow Management System/Optimizer for Hadoop

IWFMS: An Internal Workflow Management System/Optimizer for Hadoop IWFMS: An Internal Workflow Management System/Optmzer for Hadoop Lan Lu, Yao Shen Department of Computer Scence and Engneerng Shangha JaoTong Unversty Shangha, Chna lustrve@gmal.com, yshen@cs.sjtu.edu.cn

More information

Efficient Project Portfolio as a tool for Enterprise Risk Management

Efficient Project Portfolio as a tool for Enterprise Risk Management Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse

More information

An Integrated Scheduling Mechanism for Fault-Tolerant Modular Avionics Systems

An Integrated Scheduling Mechanism for Fault-Tolerant Modular Avionics Systems An Integrated Schedulng Mechansm for Fault-Tolerant Modular Avoncs Systems Yann-Hang Lee Mohamed Youns Jeff Zhou CISE Department Unversty of Florda Ganesvlle, FL 326 yhlee@cse.ufl.edu Advanced System Technology

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

A hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm

A hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm Avalable onlne www.ocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(7):1884-1889 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 A hybrd global optmzaton algorthm based on parallel

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

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

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

Cost-based Scheduling of Scientific Workflow Applications on Utility Grids

Cost-based Scheduling of Scientific Workflow Applications on Utility Grids Cost-based Schedulng of Scentfc Workflow Applcatons on Utlty Grds Ja Yu, Rakumar Buyya and Chen Khong Tham Grd Computng and Dstrbuted Systems Laboratory Dept. of Computer Scence and Software Engneerng

More information

LITERATURE REVIEW: VARIOUS PRIORITY BASED TASK SCHEDULING ALGORITHMS IN CLOUD COMPUTING

LITERATURE REVIEW: VARIOUS PRIORITY BASED TASK SCHEDULING ALGORITHMS IN CLOUD COMPUTING LITERATURE REVIEW: VARIOUS PRIORITY BASED TASK SCHEDULING ALGORITHMS IN CLOUD COMPUTING 1 MS. POOJA.P.VASANI, 2 MR. NISHANT.S. SANGHANI 1 M.Tech. [Software Systems] Student, Patel College of Scence and

More information

Resource Scheduling Based on Dynamic Dependence Injection in Virtualization-based Simulation Grid

Resource Scheduling Based on Dynamic Dependence Injection in Virtualization-based Simulation Grid Proceedngs of the 200 4th Internatonal Conference on Computer Supported Cooperatve Work n Desgn Resource Schedulng Based on Dynamc Dependence Injecton n Vrtualzaton-based Smulaton Grd Hanbng Lu,Hongy Su,

More information

QoS-based Scheduling of Workflow Applications on Service Grids

QoS-based Scheduling of Workflow Applications on Service Grids QoS-based Schedulng of Workflow Applcatons on Servce Grds Ja Yu, Rakumar Buyya and Chen Khong Tham Grd Computng and Dstrbuted System Laboratory Dept. of Computer Scence and Software Engneerng The Unversty

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

IMPACT ANALYSIS OF A CELLULAR PHONE

IMPACT ANALYSIS OF A CELLULAR PHONE 4 th ASA & μeta Internatonal Conference IMPACT AALYSIS OF A CELLULAR PHOE We Lu, 2 Hongy L Bejng FEAonlne Engneerng Co.,Ltd. Bejng, Chna ABSTRACT Drop test smulaton plays an mportant role n nvestgatng

More information

An Integrated Dynamic Resource Scheduling Framework in On-Demand Clouds *

An Integrated Dynamic Resource Scheduling Framework in On-Demand Clouds * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 30, 1537-1552 (2014) An Integrated Dynamc Resource Schedulng Framework n On-Demand Clouds * College of Computer Scence and Technology Zhejang Unversty Hangzhou,

More information

An Optimal Model for Priority based Service Scheduling Policy for Cloud Computing Environment

An Optimal Model for Priority based Service Scheduling Policy for Cloud Computing Environment An Optmal Model for Prorty based Servce Schedulng Polcy for Cloud Computng Envronment Dr. M. Dakshayn Dept. of ISE, BMS College of Engneerng, Bangalore, Inda. Dr. H. S. Guruprasad Dept. of ISE, BMS College

More information

The Greedy Method. Introduction. 0/1 Knapsack Problem

The Greedy Method. Introduction. 0/1 Knapsack Problem The Greedy Method Introducton We have completed data structures. We now are gong to look at algorthm desgn methods. Often we are lookng at optmzaton problems whose performance s exponental. For an optmzaton

More information

An ILP Formulation for Task Mapping and Scheduling on Multi-core Architectures

An ILP Formulation for Task Mapping and Scheduling on Multi-core Architectures An ILP Formulaton for Task Mappng and Schedulng on Mult-core Archtectures Yng Y, We Han, Xn Zhao, Ahmet T. Erdogan and Tughrul Arslan Unversty of Ednburgh, The Kng's Buldngs, Mayfeld Road, Ednburgh, EH9

More information

Resource Sharing Models and Heuristic Load Balancing Methods for

Resource Sharing Models and Heuristic Load Balancing Methods for Resource Sharng Models and Heurstc Load Balancng Methods for Grd Schedulng Problems Wanneng Shu 1,2, Lxn Dng 2,3,*, Shenwen Wang 2,3 1 College of Computer Scence, South-Central Unversty for Natonaltes,

More information

Traffic-light a stress test for life insurance provisions

Traffic-light a stress test for life insurance provisions MEMORANDUM Date 006-09-7 Authors Bengt von Bahr, Göran Ronge Traffc-lght a stress test for lfe nsurance provsons Fnansnspetonen P.O. Box 6750 SE-113 85 Stocholm [Sveavägen 167] Tel +46 8 787 80 00 Fax

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

Research on Evaluation of Customer Experience of B2C Ecommerce Logistics Enterprises

Research on Evaluation of Customer Experience of B2C Ecommerce Logistics Enterprises 3rd Internatonal Conference on Educaton, Management, Arts, Economcs and Socal Scence (ICEMAESS 2015) Research on Evaluaton of Customer Experence of B2C Ecommerce Logstcs Enterprses Yle Pe1, a, Wanxn Xue1,

More information

Profit-Aware DVFS Enabled Resource Management of IaaS Cloud

Profit-Aware DVFS Enabled Resource Management of IaaS Cloud IJCSI Internatonal Journal of Computer Scence Issues, Vol. 0, Issue, No, March 03 ISSN (Prnt): 694-084 ISSN (Onlne): 694-0784 www.ijcsi.org 37 Proft-Aware DVFS Enabled Resource Management of IaaS Cloud

More information

On the Optimal Control of a Cascade of Hydro-Electric Power Stations

On the Optimal Control of a Cascade of Hydro-Electric Power Stations On the Optmal Control of a Cascade of Hydro-Electrc Power Statons M.C.M. Guedes a, A.F. Rbero a, G.V. Smrnov b and S. Vlela c a Department of Mathematcs, School of Scences, Unversty of Porto, Portugal;

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

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

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

FORMAL ANALYSIS FOR REAL-TIME SCHEDULING

FORMAL ANALYSIS FOR REAL-TIME SCHEDULING FORMAL ANALYSIS FOR REAL-TIME SCHEDULING Bruno Dutertre and Vctora Stavrdou, SRI Internatonal, Menlo Park, CA Introducton In modern avoncs archtectures, applcaton software ncreasngly reles on servces provded

More information

1 Approximation Algorithms

1 Approximation Algorithms CME 305: Dscrete Mathematcs and Algorthms 1 Approxmaton Algorthms In lght of the apparent ntractablty of the problems we beleve not to le n P, t makes sense to pursue deas other than complete solutons

More information

A Performance Analysis of View Maintenance Techniques for Data Warehouses

A Performance Analysis of View Maintenance Techniques for Data Warehouses A Performance Analyss of Vew Mantenance Technques for Data Warehouses Xng Wang Dell Computer Corporaton Round Roc, Texas Le Gruenwald The nversty of Olahoma School of Computer Scence orman, OK 739 Guangtao

More information

Improved SVM in Cloud Computing Information Mining

Improved SVM in Cloud Computing Information Mining Internatonal Journal of Grd Dstrbuton Computng Vol.8, No.1 (015), pp.33-40 http://dx.do.org/10.1457/jgdc.015.8.1.04 Improved n Cloud Computng Informaton Mnng Lvshuhong (ZhengDe polytechnc college JangSu

More information

Research of concurrency control protocol based on the main memory database

Research of concurrency control protocol based on the main memory database Research of concurrency control protocol based on the man memory database Abstract Yonghua Zhang * Shjazhuang Unversty of economcs, Shjazhuang, Shjazhuang, Chna Receved 1 October 2014, www.cmnt.lv The

More information

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network 700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School

More information

Distributed Optimal Contention Window Control for Elastic Traffic in Wireless LANs

Distributed Optimal Contention Window Control for Elastic Traffic in Wireless LANs Dstrbuted Optmal Contenton Wndow Control for Elastc Traffc n Wreless LANs Yalng Yang, Jun Wang and Robn Kravets Unversty of Illnos at Urbana-Champagn { yyang8, junwang3, rhk@cs.uuc.edu} Abstract Ths paper

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

Real-Time Process Scheduling

Real-Time Process Scheduling Real-Tme Process Schedulng ktw@cse.ntu.edu.tw (Real-Tme and Embedded Systems Laboratory) Independent Process Schedulng Processes share nothng but CPU Papers for dscussons: C.L. Lu and James. W. Layland,

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

Case Study: Load Balancing

Case Study: Load Balancing Case Study: Load Balancng Thursday, 01 June 2006 Bertol Marco A.A. 2005/2006 Dmensonamento degl mpant Informatc LoadBal - 1 Introducton Optmze the utlzaton of resources to reduce the user response tme

More information

Joint Dynamic Radio Resource Allocation and Mobility Load Balancing in 3GPP LTE Multi-Cell Network

Joint Dynamic Radio Resource Allocation and Mobility Load Balancing in 3GPP LTE Multi-Cell Network 288 FENG LI, LINA GENG, SHIHUA ZHU, JOINT DYNAMIC RADIO RESOURCE ALLOCATION AND MOBILITY LOAD BALANCING Jont Dynamc Rado Resource Allocaton and Moblty Load Balancng n 3GPP LTE Mult-Cell Networ Feng LI,

More information

Modeling and Analysis of 2D Service Differentiation on e-commerce Servers

Modeling and Analysis of 2D Service Differentiation on e-commerce Servers Modelng and Analyss of D Servce Dfferentaton on e-commerce Servers Xaobo Zhou, Unversty of Colorado, Colorado Sprng, CO zbo@cs.uccs.edu Janbn We and Cheng-Zhong Xu Wayne State Unversty, Detrot, Mchgan

More information

A Novel Auction Mechanism for Selling Time-Sensitive E-Services

A Novel Auction Mechanism for Selling Time-Sensitive E-Services A ovel Aucton Mechansm for Sellng Tme-Senstve E-Servces Juong-Sk Lee and Boleslaw K. Szymansk Optmaret Inc. and Department of Computer Scence Rensselaer Polytechnc Insttute 110 8 th Street, Troy, Y 12180,

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

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING Matthew J. Lberatore, Department of Management and Operatons, Vllanova Unversty, Vllanova, PA 19085, 610-519-4390,

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

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ). REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or

More information

Self-Adaptive SLA-Driven Capacity Management for Internet Services

Self-Adaptive SLA-Driven Capacity Management for Internet Services Self-Adaptve SLA-Drven Capacty Management for Internet Servces Bruno Abrahao, Vrglo Almeda and Jussara Almeda Computer Scence Department Federal Unversty of Mnas Geras, Brazl Alex Zhang, Drk Beyer and

More information

Politecnico di Torino. Porto Institutional Repository

Politecnico di Torino. Porto Institutional Repository Poltecnco d Torno Porto Insttutonal Repostory [Artcle] A cost-effectve cloud computng framework for acceleratng multmeda communcaton smulatons Orgnal Ctaton: D. Angel, E. Masala (2012). A cost-effectve

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

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

A GENERIC HANDOVER DECISION MANAGEMENT FRAMEWORK FOR NEXT GENERATION NETWORKS

A GENERIC HANDOVER DECISION MANAGEMENT FRAMEWORK FOR NEXT GENERATION NETWORKS A GENERIC HANDOVER DECISION MANAGEMENT FRAMEWORK FOR NEXT GENERATION NETWORKS Shanthy Menezes 1 and S. Venkatesan 2 1 Department of Computer Scence, Unversty of Texas at Dallas, Rchardson, TX, USA 1 shanthy.menezes@student.utdallas.edu

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

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

Power Consumption Optimization Strategy of Cloud Workflow. Scheduling Based on SLA

Power Consumption Optimization Strategy of Cloud Workflow. Scheduling Based on SLA Power Consumpton Optmzaton Strategy of Cloud Workflow Schedulng Based on SLA YONGHONG LUO, SHUREN ZHOU School of Computer and Communcaton Engneerng Changsha Unversty of Scence and Technology 960, 2nd Secton,

More information

Cloud Auto-Scaling with Deadline and Budget Constraints

Cloud Auto-Scaling with Deadline and Budget Constraints Prelmnary verson. Fnal verson appears In Proceedngs of 11th ACM/IEEE Internatonal Conference on Grd Computng (Grd 21). Oct 25-28, 21. Brussels, Belgum. Cloud Auto-Scalng wth Deadlne and Budget Constrants

More information

VoIP Playout Buffer Adjustment using Adaptive Estimation of Network Delays

VoIP Playout Buffer Adjustment using Adaptive Estimation of Network Delays VoIP Playout Buffer Adjustment usng Adaptve Estmaton of Network Delays Mroslaw Narbutt and Lam Murphy* Department of Computer Scence Unversty College Dubln, Belfeld, Dubln, IRELAND Abstract The poor qualty

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

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

Load Balancing Algorithm of Switched Dynamic Iteration

Load Balancing Algorithm of Switched Dynamic Iteration Send Orders for Reprnts to reprnts@benthamscence.ae 236 The Open Cybernetcs Systemcs Journal, 2015, 9, 236-242 Load Balancng Algorthm of Swtched Dynamc Iteraton Open Access Chen Yansheng 1,3,* Wu Zhongkun

More information

Computer Networks 55 (2011) 3503 3516. Contents lists available at ScienceDirect. Computer Networks. journal homepage: www.elsevier.

Computer Networks 55 (2011) 3503 3516. Contents lists available at ScienceDirect. Computer Networks. journal homepage: www.elsevier. Computer Networks 55 (2011) 3503 3516 Contents lsts avalable at ScenceDrect Computer Networks journal homepage: www.elsever.com/locate/comnet Bonded defct round robn schedulng for mult-channel networks

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

RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL. Yaoqi FENG 1, Hanping QIU 1. China Academy of Space Technology (CAST) yaoqi.feng@yahoo.

RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL. Yaoqi FENG 1, Hanping QIU 1. China Academy of Space Technology (CAST) yaoqi.feng@yahoo. ICSV4 Carns Australa 9- July, 007 RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL Yaoq FENG, Hanpng QIU Dynamc Test Laboratory, BISEE Chna Academy of Space Technology (CAST) yaoq.feng@yahoo.com Abstract

More information

A Cluster Based Replication Architecture for Load Balancing in Peer-to-Peer Content Distribution

A Cluster Based Replication Architecture for Load Balancing in Peer-to-Peer Content Distribution A Cluster Based Replcaton Archtecture for Load Balancng n Peer-to-Peer Content Dstrbuton S.Ayyasamy 1 and S.N. Svanandam 2 1 Asst. Professor, Department of Informaton Technology, Tamlnadu College of Engneerng

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

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

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

Auditing Cloud Service Level Agreement on VM CPU Speed

Auditing Cloud Service Level Agreement on VM CPU Speed Audtng Cloud Servce Level Agreement on VM CPU Speed Ryan Houlhan, aojang Du, Chu C. Tan, Je Wu Department of Computer and Informaton Scences Temple Unversty Phladelpha, PA 19122, USA Emal: {ryan.houlhan,

More information

A Programming Model for the Cloud Platform

A Programming Model for the Cloud Platform Internatonal Journal of Advanced Scence and Technology A Programmng Model for the Cloud Platform Xaodong Lu School of Computer Engneerng and Scence Shangha Unversty, Shangha 200072, Chna luxaodongxht@qq.com

More information

Study on Model of Risks Assessment of Standard Operation in Rural Power Network

Study on Model of Risks Assessment of Standard Operation in Rural Power Network Study on Model of Rsks Assessment of Standard Operaton n Rural Power Network Qngj L 1, Tao Yang 2 1 Qngj L, College of Informaton and Electrcal Engneerng, Shenyang Agrculture Unversty, Shenyang 110866,

More information

Chapter 4 ECONOMIC DISPATCH AND UNIT COMMITMENT

Chapter 4 ECONOMIC DISPATCH AND UNIT COMMITMENT Chapter 4 ECOOMIC DISATCH AD UIT COMMITMET ITRODUCTIO A power system has several power plants. Each power plant has several generatng unts. At any pont of tme, the total load n the system s met by the

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

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