Analysis of Interconnection Networks in Heterogeneous Multi-Cluster Systems

Size: px
Start display at page:

Download "Analysis of Interconnection Networks in Heterogeneous Multi-Cluster Systems"

Transcription

1 Analyss of Interconnecton Networks n Heterogeneous Mult-Cluster Systems Bahman Javad, Jemal H. Abawajy, Mohammad K. Akbar, Saed Nahavand Computer Engneerng and IT Department Amrkabr Unversty of Technology 44 Hafez Ave., Tehran, Iran {javad,akbar}@ce.aut.ac.r School of Eng. and Informaton Technology Deakn Unversty VIC. 37, Australa {jemal,nahavand}@deakn.edu.au Abstract The study of nterconnecton networks s mportant because the overall performance of a dstrbuted system s often crtcally hnged on the effectveness of ts nterconnecton network. In the mean tme, the heterogenety s one of the most mportant factors of such systems. Ths paper addresses the problem of nterconnecton networks performance modelng of large-scale dstrbuted systems wth emphases on heterogeneous mult-cluster computng systems. So, we present an analytcal model to predct message latency n mult-cluster systems n the presence of cluster sze heterogenety. The model s valdated through comprehensve smulaton, whch demonstrates that the proposed model exhbts a good degree of accuracy for varous system organzatons and under dfferent workng condtons.. Introducton An ncreasng trend n the hgh performance computng (HC development s towards the networked dstrbuted systems such as commodtybased cluster computng [] and grd computng [] systems. Due to advances n computatonal and communcaton technologes, t s economcally feasble to conglomerate multple clusters to development of large-scale dstrbuted systems known as mult-cluster systems. These systems are ganng momentum both n academc and commercal sectors and a wde varety of parallel applcatons are beng hosted on such systems as well [3-5]. In ths paper, we focus on the nterconnecton networks for mult-cluster computng systems. The study of nterconnecton networks s mportant because the overall performance of a dstrbuted system s often crtcally hnged on the effectveness of ts nterconnecton network. Also, the nterconnecton network desgn plays a central role n the desgn and development of mult-cluster computng systems. Smulaton has been used to nvestgate the performance of varous components of mult-cluster computng systems [3]. Instead, we focus on analytc model. Several analytcal performance models of multcomputer systems have been proposed n the lterature for dfferent nterconnecton networks and routng algorthms (e.g., [6-9]. Unfortunately, lttle attenton has been gven to the cluster computng systems. Most of the exstng researches are based on homogenous cluster systems and the evaluatons are confned to a sngle cluster [0-]. A general model based on queung networks was proposed for a sngle cluster computng n [0]. The model assumes that the processors are homogenous. Also, extensve numercal calculaton of the model renders t too complcated. Furthermore, the model cannot be used for multcluster computng systems n the presence of heterogenety. Also, a performance model for Network of Workstatons wth processor heterogenety s dscussed n [3]. The authors recently proposed an analytcal model for mult-cluster systems n the presence of processor heterogenety n [4, 5]. To ths end, we present an analytcal performance model of nterconnecton networks for mult-cluster computng systems. The model takes nto account stochastc quanttes as well as cluster szes heterogenety. The model s valdated through comprehensve smulaton, whch demonstrated that the proposed model exhbts a good degree of accuracy for varous system szes and under dfferent operatng condtons. The rest of the paper s organzed as follows. In Secton, a bref background s dscussed. In Secton 3, we gve detaled descrpton of the proposed analytcal model. We present the model valdaton experments n Secton 4. We summarze our fndngs and conclude the paper n Secton 5.

2 . Background The system under study n ths paper s a multcluster computng systems whch s made up of C clusters, each cluster s composed of N computng nodes, {0,,..., C }, each comprsng a processor wth processng power τ and ts assocated memory module as s depcted n Fg.. Also, each cluster has two communcaton networks, an Intra- Communcaton Network (ICN, whch s used for the purpose of message passng between processors, and an nter-communcaton Network (ECN, whch s used to transmt messages between clusters, management of the system, and also for the scalablty of the system. ICN ECN Cluster # (N Computng Nodes Intra-Communcaton Network (ICN Cluster #(C- (N C- Computng Nodes Fg.. Heterogeneous mult-cluster system It should be noted that, ECN can be accessed drectly by the processors of each cluster wthout gong through the ICN (see Fg.. To nterconnect ECN and ICN, a set of Concentrators/Dspatchers [0] are used, whch combne message traffc from/to one cluster to/from other cluster. As mentoned before, the nterconnecton networks n such systems are crucal n ganng a desrable speedup. However, havng a rapd network does not necessarly guarantee to obtan a good performance, due to contenton problems. The contenton problems whch adversely affect the overall performance would happen n host nodes, network lnks, and network swtches [4]. Node contenton happens when multple data packets compete to contan a receve channel of a node, but lnk contenton occurs when two or more packets share a communcaton lnk. The swtch contenton s due to unbalanced traffc flow through the swtch, whch would result n overflow of the swtch buffer. The man factors whch have mpact on contenton of an nterconnecton network and determne ts performance are Topology, Routng algorthm and Flow control mechansm. Topology defnes how the network s physcally connected together. Hgh performance computng clusters typcally utlze Clos networks, more commonly knows as Fat-Tree or Constant Bsectonal Bandwdth networks to construct large node count non-blockng swtch confguratons [, ]. In ths paper we adopted m-port n-tree [5] as a fxed arty swtches to construct the topology for each cluster system. An m-port n-tree topology conssts of N processng nodes and N sw network swtches whch can be calculated as follows: m N n n ( m Nsw (n ( In addton, each network swtch tself has m 0,,,..., m that are communcaton ports { } attached to other swtches or processng nodes. Every swtch except root swtches uses ports n the range of { 0,,,..., ( m / } to have connecton wth ts descendants or processng node, and usng ports n the range of {( m/,( m/ +,..., m } for connecton wth ts ancestors. It can be shown that the m-port n- tree s a full bsecton bandwdth topology [8], so the lnk contenton doesn t occur n such network. Routng algorthms establsh the path between the source and the destnaton of a message. The most commercal cluster networks (e.g. Myrnet, InfnBand and QsNet adopt determnstc routngs [6]. The smplest determnstc routng used n such networks s Up*/Down* routng [7] whch can be used n networks wth both source and dstrbuted routng. Of ths, we used a determnstc routng based on Up*/Down* routng whch s proposed n [8]. In ths algorthm, each message experences two phases, an ascendng phase to get to a Nearest Common Ancestor (NCA, followed by a descendng phase. Furthermore, snce ths algorthm performs a balanced traffc dstrbuton, so the swtch contenton problem wll be extngushed. Flow control manages the allocaton of resource to messages as they progress along ther route. Two most famous flow control mechansms are store-andforward and wormhole flow control whch are wdely used n the commercal swtches. Snce the most dedcated cluster network technologes are usng wormhole flow control, we adopt ths mechansm to outlne the analytcal model. In regards of exstng heterogenety n such systems and based on the dscussons of [3], we categorzed possble heterogenety n mult-cluster systems as follows: Communcaton networks rocessors computatonal power System organzatons (e.g., cluster sze It s obvous that develop an analytcal model to cover all types of heterogenety would be qute complcated.

3 Hence, n ths paper we consder the last category (.e., system organzaton as t s llustrated n the followng sectons. 3. The Analytcal Model In ths secton, we develop an analytc model for the above mentoned mult-cluster system. The proposed model s bult on the bass of the followng assumptons whch are wdely used n smlar studes [6-0]:. Nodes generate traffc ndependently of each other, and whch follows a osson process wth a mean rate of g messages per tme unt. Moreover, the arrval process at a gven channel of each network s approxmated by an ndependent osson process.. The destnaton of each request would be any node n the system wth unform dstrbuton. 3. The number of processors n each cluster s dfferent ( N and the processng power of cluster s nodes are homogenous wth the same processng power ( τ 0 τ... τc. 4. The network swtches are nput buffered and each channel s assocated wth a sngle flt buffer. 5. Message length s fxed (M flts. 6. The source queue at the njecton channel n the source node has nfnte capacty. Moreover, messages are transferred to the node once they arrve at ther destnatons. 3.. Mean Network Latency In what follows, we fnd the mean latency of each communcaton network from cluster pont of vew, S. Snce each message may cross dfferent number of lnks to reach ts destnaton, we consder the network latency of an j-lnk message as S, and j averagng over all the possble nodes destned made by a message yelds the mean network latency as: ( jn, j n (3 j S S Where j, n s the probablty of a message whch s orgnated from cluster crossng j-lnk (j-lnk n the ascendng and j-lnk n the descendng phase to reach ts destnaton n a m-port n -tree topology. As t s mentoned n assumpton, we take nto account the unform traffc pattern so, based on the m-port n -tree topology, we can defne ths probablty as follows: j m m j,,..., n N m ( m j n N jn, j 3... Channel Message Rate (4 The message flow model of the system s shown n Fg., where the path of a flt through varous communcaton networks s llustrated. As shown n the model, the processor requests wll be drected to ICN and ECN by probabltes o and o respectvely, where {0,,..., C }. The external message of cluster leaves the ECN at the end of ascendng phase and crosses through the ICN and then start the descendng phase n the ECN of the cluster v to reach ts destnaton node. Hence, t s lke that a complete journey n the ECN. Therefore, the message rate receved n each networks can be obtaned as follows: ( ( I N ( o g (5 N + N (6 ( v E o g v o g (( ( ( v N N + N N (, o v o v v g I (7 N + Nv Gven that a newly generated message n cluster makes j-lnk to reach ts destnaton wth probablty j, n, the average number of lnks that a message makes to reach ts destnaton s gven by: avg ( j, n n (8 j d j Wth substtutng of Eq.(4 n Eq.(8, the average message dstance s obtaned as, d avg m ( mn n + n m m n (9

4 - o ( ICN (m-port n-tree g o ( ECN (m-port n-tree Con./Ds. ICN (m-port n c-tree ECN (m-port nv-tree Con./Ds. Fg.. Message flow model n the system Consequently, we could derve the rate of receved messages n each channel, whch can be wrtten as: η η η I E I ( I d avg( I (0 4nN E davg( E ( 4nN I davg( I ( 4n c where n c, the number of trees n the ICN compute n such that C ( m/ c. As t s depcted n Fg., ( the probablty o has been used as the probablty of outgong requests wthn cluster. Accordng to assumpton, ths parameter s computed by the followng equaton: o C j 0, j N N j 3... Mean Channel Servce Tme g (3 In ths topology we have two types of connectons, node to swtch (or swtch to node and swtch to swtch. In the frst and the last stage, we have node to swtch and swtch to node connecton respectvely. In the mddle stages, the swtch to swtch connecton s employed. Each type of connecton has a servce tme whch s approxmated as follows: t t α + L β (4 cn net m net α + L β (5 cs sw m net where t cn and t cs represent tmes to transmt from node to swtch (or swtch to node and swtch to swtch connecton, respectvely. α net and α sw are the network and swtch latency, β net s the transmsson tme of one byte (nverse of bandwdth and Lm s the length of each flt n bytes. Our analyss begns at the last stage and contnues backward to the frst stage. The number of stage for a message wth j-lnk journey s K j. The destnaton, stage K, s always able to receve a message, so the servce tme gven to a message at the fnal stage s t cn. The servce tme at nternal stages mght be more because a channel would be dled when the channel of subsequent stage s busy. The mean amount of tme that a message wats to acqure a channel at stage k for cluster, W k, j, s gven by the product of the channel blockng probablty n stage k, B, and the mean servce tme of a channel at k, j stage k, S k, j / [5]: W S (6 k, j k, j Bk, j The value of B s determned usng a brthdeath Markov chan [5]. Solvng ths chan for the k, j steady state probabltes gves: η S (7 B k k, j k, j The mean servce tme of a channel at stage k s equal to the message transfer tme and watng tme at subsequent stages to acqure a channel, so: S k, j K ( Ws, j + Mt otherwse (8 cs s k+ Mtcn k K Accordng to ths equaton, the mean network latency S S. s equal to 0, j ( j 3.. Mean Message Latency A message orgnatng from a gven source node n cluster sees a network latency of S (gven by Eq.(3. Due to blockng stuaton that takes place n the network, the dstrbuton functon of message latency becomes general. Therefore, a channel at source node s modeled as an M/G/ queue. The mean watng tme for an M/G/ queue s gven by [9]:

5 W ρ ρ x ( + Cx ( ρ ( (9 x (0 ( σ ( x C x ( ( x where s the mean arrval rate on the network, ( x s the mean servce tme, and σ s the varance x of the servce tme dstrbuton. Snce the mnmum servce tme of a message at the frst stage s equal to Mt cn, the varance of the servce tme dstrbuton s approxmated based on a method proposed by Draper and Ghosh [8] as follows: ( σ ( x S Mt cn As a result, the mean watng tme n source queue becomes, W ( S Mtcn ( S + ( S ( S (3 At last, the mean tme for the tal flt to reach the destnaton can be wrtten by the followng equaton: n K R t + t jn, cs cn j k (4 The mean latency seen by the message, T, crossng from source node from cluster to destnaton, conssts of three parts; the mean watng tme at the source queue ( W, the mean servce tme at the frst stage ( S, and the mean tme for the tal flt to reach the destnaton ( R. Hence, T W + S + R (5 The mean message latency n the ICN from cluster pont of vew, T I, would be found by the above equaton wth substtuton of ηk ηi and ( I Mean Message Latency for Inter-Cluster Networks As mentoned before, external messages cross through both networks, ECN and ICN, to get to the destnaton n other cluster. Snce the flow control mechansm s wormhole, the latency of these networks should be calculated as a merge one. Therefore based on the Eq.(3, we can wrte, n nv nc E& I ( jl, h ( jl, h j l h ( + + S S (6 It means each external message cross (j+l-lnk through the ECN (j-lnk n the source cluster and l- lnk n the destnaton cluster v and h-lnk n the ICN to reach ts destnaton. It can be shown that the + would be, ( j, l h + (7 ( j, l h j, n l, nv h, nc In the nter-cluster networks, the number of stages for each message journey s K j+ h+ l. Based on Eqs.(6 and (7, the mean amount of tme that a message wats to acqure a channel at stage k, n the nter-cluster networks s as follows: W η ( S (8 k,( j, l + h k k,( j, l + h Where the channel rate s drven by the followng equaton: η k ηi j k < j+ h η E otherwse (9 Smlar to the ntra-cluster network, the network latency for an nter-cluster message equals to the mean servce tme of a channel at stage 0 and can be found by Eq.(8. As before, the source queue s modeled as an M/G/ queue and the same method s used to approxmate the varance of servce tme. Thus, the mean watng tme of the source queue n the ntercluster networks can be calculated as: W E& I ( ( E & I S Mtcn S E& I + ( S E & I ( E S E& I E (30 Fnally, the arthmetc average s used to compute the mean message latency n the nter-cluster networks from cluster pont of vew, as follows:

6 T C v 0, v E& I ( W E& I + SE& I + RE & I C (3 Where the mean tme for the tal flt to reach the destnaton can be obtaned as follows: R t t n nv nc K E& I ( jl, + h cs+ cn j l h k (3 The concentrator/dspatcher s workng as smple b-drectonal buffers to nterface two external networks (.e., ECN and ICN. The mean watng tme at the concentrator/dspatcher s calculated n a smlar manner to that for the source queue (Eq.(9. The servce tme of the queue would be Mt cs and there s no varance n the servce tme, snce the messages length s fxed. So, the mean watng tme are gven by followng equatons: W s I ( Mt cs ( I Mtcs (33 Also, we model the dspatch buffers n the concentrator/dspatcher as an M/G/ queue, wth the same rate of concentrate buffers. So the mean watng tme s gven smlarly by Eq.(33. The arthmetc average of sum of the two above mentoned watng tmes gves mean watng tme at the concentrator/dspatcher as follows: C (, v W d ( W s (34 C v 0, v uttng all together, we could fnd the mean message latency from cluster pont of vew (based on Fg. wth the followng equaton: ( ( ( o ( T I o ( T E& I W d + + (35 To calculate the total mean of message latency, we use a weghted arthmetc average as follows: C N 0 N (36 4. Valdaton of the Model In order to valdate the proposed model and justfy the appled approxmatons, the model was smulated. The smulator uses the same assumptons as the analyss. Messages are generated at each node accordng to osson process wth the mean nterarrval rate of g. The destnaton node s determned by usng a unform random number generator. For each smulaton experment, statstcs were gathered for a total number of 00,000 messages. Statstc gatherng was dscarded for the frst 0,000 messages to avod dstortons due to the warm-up phase. Also, there s a dran phase at the end of smulaton n whch 0,000 generated messages were not n the statstc gatherng to provde enough tme for all packets to reach ther destnaton. Extensve valdaton experments have been performed for several combnatons of clusters szes, network szes, network technologes, and message length. The general conclusons have been found to be consstent across all the cases consdered. After all, to llustrate the result of some specfc cases to show the valdty of our model, the tems whch were examned carefully are presented n Table. Moreover, the two dfferent message lengths, M3 and 64 flts wth dfferent szes, L m 56 and 5 bytes are used. The network bandwdth s 500/tme unt and network latency and swtch latency are 0.0 and 0.0 tme unt, respectvely. Table. System organzatons for valdaton N C m Node Organzatons n n n 3 [0,] [,7] [8,3] n 3 n 4 n 5 [0,7] [8,0] [,5] The results of smulaton and analyss for a system wth above mentoned parameters are depcted n Fg. 3 and Fg. 4 n whch the mean message latences are plotted aganst the offered traffc for two dfferent system organzatons. The fgures reveal that the analytcal model predcts the mean message latency wth a good degree of accuracy when the system s n the steady state regon, that s, when t has not reached the saturaton pont. However, there are dscrepances n the results provded by the model and the smulaton when the system s under heavy traffc and approaches the saturaton pont. Ths s due to the approxmatons that have been made n the analyss to ease the model development. For nstance, n ths regon the traffc on the lnks s not completely ndependent, as we assume n our analytcal model. Also, one of the most sgnfcant term n the model under heavly loaded system, s the average watng tme at the source queue and concentrators/dspatchers. The approxmaton whch s made to compute the varance of the servce tme receved by a message at a gven channel (Eq.( s a factor of the model naccuracy. Snce, the most evaluaton studes focus on network performance n the steady state regons, so we can conclude that the proposed model can be a practcal

7 evaluaton tool that can help system desgner to explore the desgn space and examne varous desgn parameters. N0, m8, M3 N0, m8, M64 Mean Message Latency A nalyss (Lm56 Smulato n A nalyss (Lm5 Smulato n Mean Message Latency Analyss (Lm56 Smulaton Analyss (Lm5 Smulaton Offered Traffc Offered Traffc Fg. 3. Mean message latency n a system wth N0, M3 and 64 N544, m4, M3 N544, m4, M64 Mean Message Latency Analyss (Lm56 Smulaton Analyss (Lm5 Smulaton Mean Message Latency Analyss (Lm56 Smulaton Analyss (Lm5 Smulaton Offered Traffc Offered Traffc Fg. 4. Mean message latency n a system wth N544, M3 and Conclusons Analytcal models play a crucal role n evaluaton of a system under varous desgn ssues. In ths paper, an analytcal model of nterconnecton networks for mult-cluster computng systems n the presence of cluster szes heterogenety s dscussed. The proposed model has been valdated wth versatle confguratons and desgn parameters. Smulaton experments have proved that the model predcts message latency wth a reasonable accuracy. For future work, we ntent to develop and extend the model to cover other categores of heterogenety and non-unform traffc pattern as well. Acknowledgments Specal thanks to Mr. D. Sgro and R. Ruge regardng the system setup for the smulatons. The help of Dr. A. Khonsar from Tehran Unversty for hs worthwhle comments s apprecated. Fnancal support from Intellgent System Research Laboratory s also greatly apprecated. 6. References [] M.Q. Xu, Effectve Meta-Computng usng LSF Mult-Cluster, In roceedngs of the IEEE Internatonal Conference on Cluster and Grd, Brsbane, Australa, May 00, pp

8 [] I. Foster, The Grd: A New Infrastructure for st Century Scence, hyscs Today, Vol.55, No., Feb. 00, pp [3] J. H. Abawajy, and S.. Dandamud. arallel Job Schedulng on Mult-Cluster Computng Systems, In roceedngs of the IEEE Internatonal Conference on Cluster Computng, Hong Kong, Dec. 003, pp [4] DAS- 00, The DAS- Supercomputer. [5] B. Boas, Storage on the Lunatc Frnge. Lawrence Lvermore Natonal Laboratory, anel at Supercomputng Conference 003, hoenx, AZ, Nov [6] H. Sarbaz-Azad, A. Khonsar, and M. Ould-Khaoua, erformance Analyss of Determnstc Routng n Wormhole k-ary n-cubes wth Vrtual Channels, Journal of Interconnecton Networks, Vol. 3, Nos.&, 00, pp [7] M. Ould-Khaoua A erformance Model for Duato's Fully-adaptve Routng Algorthm n k-ary n-cubes, IEEE Transacton on Computers, Vol.4, No., 999, pp. -8. [8] J.T. Draper and J. Ghosh, A Comprehensve Analytcal Model for Wormhole Routng n Multcomputer Systems, Journal of arallel and Dstrbuted Computng, Vol. 3, No., 994, pp [9] Y.M. Boura and C.R. Das, erformance Analyss of Bufferng Schemes n Wormhole Routers, IEEE Transactons on Computers, Vol. 46, No. 6, Jun. 997, pp [0].C. Hu and L. Klenrock, A Queung Model for Wormhole Routng wth Tmeout, In roceedngs of the 4 th Internatonal Conference on Computer Communcatons and Networks, Nevada, LV, Sep. 995, pp [] X. Du, X. Zhang, and Z. Zhu, Memory Herarchy Consderaton for Cost-Effectve Cluster Computng, IEEE Transacton on Computers, Vol.49, No.5, Sep. 000, pp [] B. Javad, S. Khorsand, and M. K. Akbar, Study of Cluster-based arallel Systems usng Analytcal Modelng and Smulaton, Lecture Notes n Computer Scence, Vol. 9, Sprnger-Verlag, 005, pp [3] A. Clemats and A. Corana, Modelng erformance of Heterogeneous arallel Computng Systems, Journal of arallel Computng, Vol.5, No.9, Sep. 999, pp [4] A.T.T. Chun and C.L. Wang. Contenton-free Complete Exchange Algorthm on Clusters, In roceedngs of the IEEE Internatonal Conference on Cluster Computng, Saxony, Germany, Nov. 000, pp [5] X. Ln, An Effcent Communcaton Scheme for Fat- Tree Topology on Infnband Networks, M.Sc Thess, Department of Informaton Engneerng and Computer Scence, Feng Cha Unversty, Tawan [6] M. Kobuch, K. Watanae, K. Kono, A. Jouraku, and H. Amano. erformance Evaluaton of Routng Algorthm n RHNET- Cluster, In roceedngs of the IEEE Internatonal Conference on Cluster Computng, Hong Kong, Dec. 003, pp [7] M. D. Schroeder et. al. Autonet: A Hgh-Speed, Self Confgurng Local Area Network Usng ont-to- ont Lnks. SRC research report 59, Dgtal Equpment Corporaton, Apr [8] B. Javad, J. H. Abawajy, and M. K. Akbar, Modelng and Analyss of Heterogeneous Loosely- Coupled Dstrbuted Systems, Techncal Report TR C06/, School of Informaton Technology, Deakn Unversty, Australa, Jan 006. [9] L. Klenrock, Queung System: Computer Applcatons, Vol., John Wly ublsher, New York [0] W. Dally and B. Towles, rncples and ractces of Interconnecton Networks, Morgan Kaufmann ublsher, San Francsco, 004. [] InfnBand Clusterng, Delverng Better rce/erformance than Ethernet, Whte aper, Mellanox Technologes Inc., Santa Clara, CA, 005. [] Buldng Scalable, Hgh erformance Cluster/Grd Networks: The Role of Ethernet, Whte aper, Force0 Networks Inc., Mlptas, CA, 004. [3] J. Dongarra and A. Lastovetsky, An Overvew of Heterogeneous Hgh erformance and Grd Computng, In Engneerng the Grd: Status and erspectve, Eds B. DMartno, J. Dongarra, A. Hose, L. Yang, and H. Zma, Amercan Scentfc ublshers, Feb [4] B. Javad, M. K. Akbar, and J. H. Abawajy, Analyss of Mult-Cluster Computng Systems wth rocessor Heterogenety, In roceedngs of the th Internatonal Computer Socety of Iran Computer Conference, Tehran, Iran, Jan. 006, pp [5] B. Javad, J. H. Abawajy, and M. K. Akabr, Analytcal Interconnecton Networks Model for Mult-Cluster Computng Systems, In 3th Internatonal Conference on Analytcal and Stochastc Modelng Technques and Applcatons, Bonn, Germany, to be appeared.

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

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

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

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

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

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

On the Exact Analysis of Bluetooth Scheduling Algorithms

On the Exact Analysis of Bluetooth Scheduling Algorithms On the Exact Analyss of Bluetooth Schedulng Algorth Gl Zussman Dept. of Electrcal Engneerng Technon IIT Hafa 3000, Israel glz@tx.technon.ac.l Ur Yechal Dept. of Statstcs and Operatons Research School of

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

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

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

Advanced Computer Networks

Advanced Computer Networks Char of Network Archtectures and Servces Department of Informatcs Techncal Unversty of Munch Note: Durng the attendance check a stcker contanng a unque QR code wll be put on ths exam. Ths QR code contans

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

Network Coding as a Dynamical System

Network Coding as a Dynamical System Network Codng as a Dynamcal System Narayan B. Mandayam IEEE Dstngushed Lecture (jont work wth Dan Zhang and a Su) Department of Electrcal and Computer Engneerng Rutgers Unversty Outlne. Introducton 2.

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

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

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

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices Internatonal Mathematcal Forum, Vol 7, 2012, no 52, 2549-2554 An Applcaton of the Dulmage-Mendelsohn Decomposton to Sparse Null Space Bases of Full Row Rank Matrces Mostafa Khorramzadeh Department of Mathematcal

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

X- Chart Using ANOM Approach

X- Chart Using ANOM Approach ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are

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

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

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z.

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z. TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS Muradalyev AZ Azerbajan Scentfc-Research and Desgn-Prospectng Insttute of Energetc AZ1012, Ave HZardab-94 E-mal:aydn_murad@yahoocom Importance of

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

A New Approach For the Ranking of Fuzzy Sets With Different Heights

A New Approach For the Ranking of Fuzzy Sets With Different Heights New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays

More information

Maximum Weight Matching Dispatching Scheme in Buffered Clos-Network Packet Switches

Maximum Weight Matching Dispatching Scheme in Buffered Clos-Network Packet Switches Maxmum Weght Matchng Dspatchng Scheme n Buffered Clos-Network Packet Swtches Roberto Roas-Cessa, Member, IEEE, E Ok, Member, IEEE, and H. Jonathan Chao, Fellow, IEEE Abstract The scalablty of Clos-network

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

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

Constructing Minimum Connected Dominating Set: Algorithmic approach

Constructing Minimum Connected Dominating Set: Algorithmic approach Constructng Mnmum Connected Domnatng Set: Algorthmc approach G.N. Puroht and Usha Sharma Centre for Mathematcal Scences, Banasthal Unversty, Rajasthan 304022 usha.sharma94@yahoo.com Abstract: Connected

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

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data Malaysan Journal of Mathematcal Scences 11(S) Aprl : 35 46 (2017) Specal Issue: The 2nd Internatonal Conference and Workshop on Mathematcal Analyss (ICWOMA 2016) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES

More information

ANALYTICAL MODEL AND PERFORMANCE ANALYSIS OF A NETWORK INTERFACE CARD. Abstract

ANALYTICAL MODEL AND PERFORMANCE ANALYSIS OF A NETWORK INTERFACE CARD. Abstract ANALYTICAL MODEL AND PERFORMANCE ANALYSIS OF A NETWORK INTERFACE CARD Naveen Cherukur 1, Gokul B. Kandraju 2, Natarajan Gautam 3, and Anand Svasubramanam 4 Abstract One of the key concerns for practtoners

More information

CS 268: Lecture 8 Router Support for Congestion Control

CS 268: Lecture 8 Router Support for Congestion Control CS 268: Lecture 8 Router Support for Congeston Control Ion Stoca Computer Scence Dvson Department of Electrcal Engneerng and Computer Scences Unversty of Calforna, Berkeley Berkeley, CA 9472-1776 Router

More information

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 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 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

More information

Using Memory and Random Sampling for Load Balancing in High-radix Switches

Using Memory and Random Sampling for Load Balancing in High-radix Switches Unversty of Toronto SNL Techncal Report TR-SN-UT-7--2. c Soudeh Ghorban Khaled et al. Usng Memory and Random Samplng for Load Balancng n Hgh-radx Swtches Soudeh Ghorban Khaled, Yashar Ganjal Department

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

A Topology-aware Random Walk

A Topology-aware Random Walk A Topology-aware Random Walk Inkwan Yu, Rchard Newman Dept. of CISE, Unversty of Florda, Ganesvlle, Florda, USA Abstract When a graph can be decomposed nto clusters of well connected subgraphs, t s 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

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

Sample Solution. Advanced Computer Networks P 1 P 2 P 3 P 4 P 5. Module: IN2097 Date: Examiner: Prof. Dr.-Ing. Georg Carle Exam: Final exam

Sample Solution. Advanced Computer Networks P 1 P 2 P 3 P 4 P 5. Module: IN2097 Date: Examiner: Prof. Dr.-Ing. Georg Carle Exam: Final exam Char of Network Archtectures and Servces Department of Informatcs Techncal Unversty of Munch Note: Durng the attendance check a stcker contanng a unque QR code wll be put on ths exam. Ths QR code contans

More information

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour 6.854 Advanced Algorthms Petar Maymounkov Problem Set 11 (November 23, 2005) Wth: Benjamn Rossman, Oren Wemann, and Pouya Kheradpour Problem 1. We reduce vertex cover to MAX-SAT wth weghts, such that the

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

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

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

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

Positive Semi-definite Programming Localization in Wireless Sensor Networks

Positive Semi-definite Programming Localization in Wireless Sensor Networks Postve Sem-defnte Programmng Localzaton n Wreless Sensor etworks Shengdong Xe 1,, Jn Wang, Aqun Hu 1, Yunl Gu, Jang Xu, 1 School of Informaton Scence and Engneerng, Southeast Unversty, 10096, anjng Computer

More information

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc.

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 97-735 Volume Issue 9 BoTechnology An Indan Journal FULL PAPER BTAIJ, (9), [333-3] Matlab mult-dmensonal model-based - 3 Chnese football assocaton super league

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

Intra-Parametric Analysis of a Fuzzy MOLP

Intra-Parametric Analysis of a Fuzzy MOLP Intra-Parametrc Analyss of a Fuzzy MOLP a MIAO-LING WANG a Department of Industral Engneerng and Management a Mnghsn Insttute of Technology and Hsnchu Tawan, ROC b HSIAO-FAN WANG b Insttute of Industral

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

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

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

Computer Communications

Computer Communications Computer Communcatons 3 (22) 3 48 Contents lsts avalable at ScVerse ScenceDrect Computer Communcatons journal homepage: www.elsever.com/locate/comcom On the queueng behavor of nter-flow asynchronous network

More information

Comparisons of Packet Scheduling Algorithms for Fair Service among Connections on the Internet

Comparisons of Packet Scheduling Algorithms for Fair Service among Connections on the Internet Comparsons of Packet Schedulng Algorthms for Far Servce among Connectons on the Internet Go Hasegawa, Takahro Matsuo, Masayuk Murata and Hdeo Myahara Department of Infomatcs and Mathematcal Scence Graduate

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

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 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

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications Effcent Loa-Balance IP Routng Scheme Base on Shortest Paths n Hose Moel E Ok May 28, 2009 The Unversty of Electro-Communcatons Ok Lab. Semnar, May 28, 2009 1 Outlne Backgroun on IP routng IP routng strategy

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

Analysis of QoS in WLAN

Analysis of QoS in WLAN Analyss of QoS n WLAN PAAL E. ENGELSTAD AND OLAV N. ØSTERBØ Paal E. Engelstad s Research Scentst n Telenor R&D An analytcal model s proposed to descrbe the prorty schemes of the EDCA mechansm of the IEEE

More information

Performance Evaluation of IEEE e based on ON-OFF Traffic Model I. Papapanagiotou PhD. Student

Performance Evaluation of IEEE e based on ON-OFF Traffic Model I. Papapanagiotou PhD. Student erformance Evaluaton of IEEE 82.e based on ON-OFF Traffc Model I. apapanagotou hd. Student Wreless Telecommuncaton Laboratory Unversty of atras 265 4 atras Greece papapanag@upnet.gr J.S. Vardakas hd. Student

More information

Security Enhanced Dynamic ID based Remote User Authentication Scheme for Multi-Server Environments

Security Enhanced Dynamic ID based Remote User Authentication Scheme for Multi-Server Environments Internatonal Journal of u- and e- ervce, cence and Technology Vol8, o 7 0), pp7-6 http://dxdoorg/07/unesst087 ecurty Enhanced Dynamc ID based Remote ser Authentcaton cheme for ult-erver Envronments Jun-ub

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

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

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

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

F Geometric Mean Graphs

F Geometric Mean Graphs Avalable at http://pvamu.edu/aam Appl. Appl. Math. ISSN: 1932-9466 Vol. 10, Issue 2 (December 2015), pp. 937-952 Applcatons and Appled Mathematcs: An Internatonal Journal (AAM) F Geometrc Mean Graphs A.

More information

A MapReduce-supported Data Center Networking Topology

A MapReduce-supported Data Center Networking Topology A MapReduce-supported Data Center Networkng Topology Zelu Dng*,, Xue Lu, Deke Guo*, Honghu Chen*, Xueshan Luo* * Natonal Unversty of Defense Technology, Chna McGll Unversty, Canada Abstract Several novel

More information

Analytic Evaluation of Quality of Service for On-Demand Data Delivery

Analytic Evaluation of Quality of Service for On-Demand Data Delivery Analytc Evaluaton of Qualty of Servce for On-Demand Data Delvery Hongfe Guo Haonan Tan ( guo@cs.wsc.edu) (haonan@cs.wsc.edu) Abstract Qualty of servce (QoS) measured as balkng probablty and average watng

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

Availability and QoS Performance Evaluation of Public IP Networks Tivadar Jakab 1, Gábor Horváth 1, Rozália Konkoly 2, Éva Csákány 2 1

Availability and QoS Performance Evaluation of Public IP Networks Tivadar Jakab 1, Gábor Horváth 1, Rozália Konkoly 2, Éva Csákány 2 1 Avalablty and QoS Performance Evaluaton of Publc IP Networks Tvadar Jakab, Gábor Horváth, Rozála Konkoly, Éva Csákány Department of Telecommuncatons, Budapest Unversty of Technology and Economcs Magyar

More information

New Exploration of Packet-Pair Probing for Available Bandwidth Estimation and Traffic Characterization

New Exploration of Packet-Pair Probing for Available Bandwidth Estimation and Traffic Characterization New Exploraton of Packet-Par Probng for Avalable Bandwdth Estmaton and Traffc Characterzaton Yu Cheng, Vkram Ravndran, Alberto Leon-Garca, Hsao-Hwa Chen Department of Electrcal and Computer Engneerng,

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

Efficient Backoff Algorithm in Wireless Multihop Ad Hoc Networks

Efficient Backoff Algorithm in Wireless Multihop Ad Hoc Networks 1 Chen-Mn Wu, 2 Hu-Ka Su, 3 Wang-Has Yang *1,Correspondng Author Nanhua Unversty, cmwu@mal.nhu.edu.tw 2 Natonal Formosa Unversty, hksu@nfu.edu.tw 3 Hsupng Insttute of Technology, yangwh@mal.ht.edu.tw do:10.4156/jact.vol3.

More information

UBICC Publishers 2008 Ubiquitous Computing and Communication Journal

UBICC Publishers 2008 Ubiquitous Computing and Communication Journal UBICC Journal Ubqutous Computng and Communcaton Journal 008 Volume 3. 008-04-30. ISSN 99-844 Specal Issue on Moble Adhoc Networks UBICC ublshers 008 Ubqutous Computng and Communcaton Journal Edted by Usman

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

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

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

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

Quantifying Performance Models

Quantifying Performance Models Quantfyng Performance Models Prof. Danel A. Menascé Department of Computer Scence George Mason Unversty www.cs.gmu.edu/faculty/menasce.html 1 Copyrght Notce Most of the fgures n ths set of sldes come from

More information

Available online at ScienceDirect. Procedia Computer Science 103 (2017 )

Available online at  ScienceDirect. Procedia Computer Science 103 (2017 ) Avalable onlne at www.scencedrect.com ScenceDrect Proceda Computer Scence 03 (207 ) 562 568 XIIth Internatonal Symposum «Intellgent Systems», INTELS 6, 5-7 October 206, Moscow, Russa Retral queueng systems

More information

Reliability and Performance Models for Grid Computing

Reliability and Performance Models for Grid Computing Relablty and Performance Models for Grd Computng Yuan-Shun Da,2, Jack Dongarra,3,4 Department of Electrcal Engneerng and Computer Scence, Unversty of Tennessee, Knoxvlle 2 Department of Industral and Informaton

More information

Faster Network Design with Scenario Pre-filtering

Faster Network Design with Scenario Pre-filtering Faster Network Desgn wth Scenaro Pre-flterng Debojyot Dutta, Ashsh Goel, John Hedemann ddutta@s.edu, agoel@usc.edu, johnh@s.edu Informaton Scences Insttute School of Engneerng Unversty of Southern Calforna

More information

Cell Count Method on a Network with SANET

Cell Count Method on a Network with SANET CSIS Dscusson Paper No.59 Cell Count Method on a Network wth SANET Atsuyuk Okabe* and Shno Shode** Center for Spatal Informaton Scence, Unversty of Tokyo 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

More information

OPTIMAL CONFIGURATION FOR NODES IN MIXED CELLULAR AND MOBILE AD HOC NETWORK FOR INET

OPTIMAL CONFIGURATION FOR NODES IN MIXED CELLULAR AND MOBILE AD HOC NETWORK FOR INET OPTIMAL CONFIGURATION FOR NODE IN MIED CELLULAR AND MOBILE AD HOC NETWORK FOR INET Olusola Babalola D.E. Department of Electrcal and Computer Engneerng Morgan tate Unversty Dr. Rchard Dean Faculty Advsor

More information

Derivation of Three Queue Nodes Discrete-Time Analytical Model Based on DRED Algorithm

Derivation of Three Queue Nodes Discrete-Time Analytical Model Based on DRED Algorithm Seventh Internatonal Conference on Informaton Technology Dervaton of Three Queue Nodes Dscrete-Tme Analytcal Model Based on DRED Algorthm Jafar Ababneh, Hussen Abdel-Jaber, 3 Fad Thabtah, 3 Wael Had, EmranBadarneh

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

Lecture 5: Multilayer Perceptrons

Lecture 5: Multilayer Perceptrons Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented

More information

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method Internatonal Journal of Computatonal and Appled Mathematcs. ISSN 89-4966 Volume, Number (07), pp. 33-4 Research Inda Publcatons http://www.rpublcaton.com An Accurate Evaluaton of Integrals n Convex and

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

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

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network S. Sudha and N. Ammasagounden Natonal Insttute of Technology, Truchrappall,

More information

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis Internatonal Mathematcal Forum, Vol. 6,, no. 7, 8 Soltary and Travelng Wave Solutons to a Model of Long Range ffuson Involvng Flux wth Stablty Analyss Manar A. Al-Qudah Math epartment, Rabgh Faculty of

More information

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010 Smulaton: Solvng Dynamc Models ABE 5646 Week Chapter 2, Sprng 200 Week Descrpton Readng Materal Mar 5- Mar 9 Evaluatng [Crop] Models Comparng a model wth data - Graphcal, errors - Measures of agreement

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

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

Obstacle-Aware Routing Problem in. a Rectangular Mesh Network

Obstacle-Aware Routing Problem in. a Rectangular Mesh Network Appled Mathematcal Scences, Vol. 9, 015, no. 14, 653-663 HIKARI Ltd, www.m-hkar.com http://dx.do.org/10.1988/ams.015.411911 Obstacle-Aware Routng Problem n a Rectangular Mesh Network Norazah Adzhar Department

More information

The Shortest Path of Touring Lines given in the Plane

The Shortest Path of Touring Lines given in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 262 The Open Cybernetcs & Systemcs Journal, 2015, 9, 262-267 The Shortest Path of Tourng Lnes gven n the Plane Open Access Ljuan Wang 1,2, Dandan He

More information