Energy-Efficient Workload Placement in Enterprise Datacenters

Size: px
Start display at page:

Download "Energy-Efficient Workload Placement in Enterprise Datacenters"

Transcription

1 COVER FEATURE CLOUD COMPUTING Energy-Effcent Workload Placement n Enterprse Datacenters Quan Zhang and Wesong Sh, Wayne State Unversty Power loss from an unnterruptble power supply can account for 15 percent of a datacenter s energy. A rack-level power model that relates IT workload and ts power dsspaton allows optmzed workload placement that can save a datacenter roughly $1.4 mllon n annual energy costs. R sng electrcty costs are makng energy effcency a crtcal concern for datacenters, whch devour massve amounts of energy annually. Accordng to the Natural Resources Defense Councl, US datacenters expended 91 bllon kwh of electrcty n 2013, wth a proected ncrease to 140 bllon kwh annually by 2020 ( At these consumpton rates, energy costs wll contnue to be a maor contrbutor to a datacenter s total cost of ownershp (TCO). To mprove datacenters energy effcency, researchers and practtoners have focused on reducng IT equpment power consumpton, whch s typcally 30 percent of a datacenter s energy cost. The most popular approaches apply dynamc voltage/frequency scalng (DVFS) to reduce power dsspaton from the CPU and memory subsystem;1,2 consoldate servers by assgnng tasks to fewer servers and shuttng down dle ones;3,4 or evenly allocate workloads among servers through load balancng.5,6 Other approaches are based on hardware-resource 46 CO M PUTE R P U B LISH ED BY TH E I EEE COMP UTER SOCI E T Y use, such as subsystem power models for specfc computer components,7 9 and system power models for nonvrtualzed and vrtualzed envronments Reducng IT equpment power consumpton certanly has mert, but these strateges gnore another large contrbutor to energy cost: power losses from an unnterruptble power supply (UPS), whch account for an addtonal 15 percent of overall energy cost.13 To address ths area, we created a rack-level power model that maps workload drectly to ts power dsspaton and formulated a mathematcal soluton that chooses an optmal workload allocaton to mnmze IT equpment power consumpton and power loss from UPSs. Usng a TCO model, we then analy zed potental electrcty cost savngs. Our expermental results show that the rack-level power model precsely matches measured power, wth an error rate of ±2.5 percent or less. For a datacenter that hosts 50 racks (1,000 servers) wth 10 applcatons, our smulaton showed a potental power savngs of up to 5.2 percent relatve to that wth a unform workload allocaton. Ths percentage translates to $1.4 mllon n annual /16/$ IEEE

2 Electrcty grd ATS UPSs PDUs Racks TABLE 1. Unnterruptble power supply (UPS) power loss wth two workload dstrbutons. Workload dstrbuton 1 Workload dstrbuton 2 Backup power generator UPS confguraton Loaded capacty (%) Power loss (W) Total loss (W) Loaded capacty (%) Power loss (W) Total loss (W) FIGURE 1. Smplfed power flow n a typcal datacenter. At the hghest layer, the utlty power and backup power, such as a desel generator, pass through unnterruptble power supples (UPSs) through an automatc transform swtch (ATS) and go through power dstrbuton unts (PDUs) to dfferent racks. energy cost savngs for a 76-MW datacenter wth a power- usage effectveness (PUE) of 1.7. UPS AND ENERGY USE Fgure 1 shows a smplfed power flow n a typcal datacenter. From the racks, power s dstrbuted through strps to ndvdual servers, all of whch have ther own power supples. Because a UPS represents a sngle falure pont, datacenters often use redundant UPSs n both centralzed and dstrbuted topologes to ensure that hosted servces are always avalable. A redundant confguraton can be a sngle N system, comprsng one UPS module, or multple N systems, comprsng parallel modules whose capactes are matched to the crtcal-load proecton. A centralzed topology typcally deploys UPSs at the faclty level; a dstrbuted topology deploys them at the rack or server level. 14 The choce of confguraton depends on a datacenter s falure frequency. Two popular redundant confguratons are parallel, or N+1, and system-plus-system, or. An N+1 redundant confguraton conssts of parallel, same-sze UPS modules, and the spare power s at least equal to the crtcal- load capacty. A redundant confguraton the most relable and expensve desgn can tolerate every concevable sngle falure pont. N+1 Rack , ,026 2,047 Rack ,053 Rack , ,723 3,432 Rack , ,684 Each confguraton has a unque power-loss behavor. In an N+1 confguraton, power loss decreases when the IT power load ncreases; n a confguraton, power loss ncreases as IT power load ncreases. Thus, for a rack-level UPS confguraton, nether fewer servers runnng at full speed nor more servers runnng slower wth unform workload dstrbuton wll always save power because lowerng UPS output load leads to lower converson effcency. Ths observaton about power-loss behavor was foundatonal to our work. Enterprse datacenters generally run fewer applcatons sometmes only one across the entre datacenter. Google s datacenters, for example, run Web 2.0 and software as a servce (SaaS). In these cases, a sngle datacenter has a large workload, no vrtualzaton, and tens of thousands of physcal servers. Thus, workload placement s crtcal n separatng the often mllons of user requests across racks. ANALYZING UPS POWER LOSS In a double-converson UPS, power loss occurs when power transforms from AC to DC for battery storage and agan from DC to AC for delvery to racks and servers. Power loss s also ted to UPS topology. Our focus s on power loss n a racklevel dstrbuted UPS topology, where power loss depends on UPS effcency and redundant confguraton choce, and loaded capacty (real-tme power 2,079 3,407 load) depends on IT workload. For an N+1 confguraton, loaded capacty vares from 0 to 100 percent; for a confguraton, maxmum loaded capacty s only 50 percent, as the total power load s evenly allocated to two UPSs. UPS effcency depends on the technology used. To gather evdence that optmal workload dstrbutons for varous UPS confguratons dffer, we looked at data from two racks n the Wayne State Unversty datacenter; one rack had 20 fully loaded servers and the other had 20 dle servers. We then collected data from two workload dstrbutons: dstrbuton 1 had 20 fully loaded servers on the same rack and all dle servers on the other rack; and dstrbuton 2 had 12 fully loaded servers and 8 dle servers on one rack and the remanng mx of 8 loaded and 12 dle servers on the other rack. Table 1 shows the UPS power losses of dfferent UPS confguratons and workload dstrbutons. For the N+1 confguraton, dstrbuton type 1 has lower power losses; for the confguraton, dstrbuton 2 has lower power losses. Fgure 2 shows a UPS effcency curve based on data we collected from our two workload dstrbutons. Typcally, lower UPS effcency leads to hgher UPS power losses, but n datacenters, IT equpment dctates loaded capacty and thus UPS power loss. FEBRUARY

3 CLOUD COMPUTING Effcency (%) Gven the UPS effcency curve n Fgure 2, we used a natural logarthmc functon to ft the curve and Mathematca to calculate the UPS power loss. Fgure 3 shows the power loss of UPSs wth N+1 and UPS confguratons. MODELING ENERGY- EFFICIENT PLACEMENT On the bass of the data n Table 1, we formulated an optmzaton problem to mnmze the total power of IT equpment and UPS power loss through the UPS load (% of full power ratng) FIGURE 2. UPS effcency curve based on data collected from Wayne State Unversty s datacenter. To fnd the relatonshp between IT equpment power and UPS power loss, we used a UPS wth a power ratng of 8 kw for a rack wth 20 servers. All servers had the same measured peak power of 350 W. The dle power of 20 servers was 4,366 W. Power loss (W) 2,500 2,000 1,500 1, N + 1 UPS loaded capacty FIGURE 3. UPS power loss of a sngle rack wth N+1 and confguratons. For the N+1 confguraton, power loss ncreases when loaded capacty s less than 50 percent and decreases when t s hgher than 50 percent. For the confguraton, power loss contnuously ncreases wth loaded capacty. use of a rack-level power model that drectly maps the rack s work load to ts power dsspaton. We used the model along wth our workload-placement calculatons to solve the optmzaton problem. Rack-level power modelng Our rack-level power model uses workload nformaton, such as throughput and nstructons per second (IPC), as drect nputs. The model s target applcaton s an enterprse data center wth nonvrtualzed servers, each of whch hosts only one applcaton. We assume that the CPU s runnng at a fxed speed wthout dynamc tunng. We express the rack-level power model as IDLE P ( w)= P + α w, (1) where P IDLE s the rack s dle power and the summaton of α w s the total power ntroduced by all workloads on ths rack. α s the coeffcent that represents watts per performance of workload on the th rack. α has dfferent unts for dfferent applcatons and hardware. For CPU-ntensve applcatons, α could be watts per nstructon; for memory-ntensve applcatons, t could be watts per byte; and for Web servces, watts per request mght be a sold ndcator of system effcency. Workload proflng provdes hstorc knowledge that can be used to choose the approprate α metrc. In our experments, we profled an applcaton n four steps. We frst measured the dle power of the th rack as P IDLE. We then fully loaded the rack to get a performance upper bound for ths applcaton. As a thrd step, we gradually ncreased the workload, makng the rack run at dfferent power levels, and recorded the rack power. Fnally, we calculated the average value (performance per watts) of all sample ponts, whch we used as α. We repeated ths process for dfferent types of applcatons to get the correspondng α value for the th rack. Optmzaton problem Our optmzaton problem was for a datacenter that hosts multple applcatons 48 COMPUTER

4 smultaneously, wth each server hostng only one applcaton at a tme, and a workload that can be dynamcally assgned to a dfferent server subset. In addton, we assumed that one UPS s connected to only one rack deployed n ether an N+1 or a redundant confguraton. Because UPS power loss vares sgnfcantly wth IT power load, clearly any workload change or revsed dstrbuton wll affect IT equpment power loss. Our goal was to mnmze both the total IT equpment power and wasted rack-level UPS power. We chose the optmal workload allocaton gven the equalty and nequalty constrants of where P s the power of the th rack and η(p ) s the converson effcency when the UPS has the IT power load of η(p ). Equaton 3 ensures that the performance requrement s satsfed for workload. In Equaton 4, C s the mark), whch smulates Web servce requests to read and wrte to a database. We ran the two applcatons separately to get α as descrbed n Equaton 1 and then estmated real-tme UPS POWER LOSS VARIES SIGNIFICANTLY WITH IT POWER LOAD, SO ANY WORK LOAD CHANGE OR REDISTRIBUTION WILL AFFECT IT EQUIPMENT POWER LOSS. performance, whch means the summaton of all racks workload should be equal to the total workload from all users; capacty, whch means the hardware resource requrement should be less than each rack s maxmum hardware capacty; and power, whch means the total rack power satsfes the specfed power-cappng requrement (by operator or hardware). Gven these constrants, the mathematcal formulaton of the optmzaton problem s Mnmze as long as w = w, P η ( P ) (2) (3) w C, and (4) C IDLE CAP P + α w P, (5) capacty lmtaton for workload on rack, and C s the hardware lmtaton for rack. In Equaton 5, P CAP s the cappng power for the th rack. The functon f[η(p )] denotes the relatonshp between the UPS output power load and ts correspondng converson effcency. η(p ) can be expressed as P η( P )= α ln + b, (6) P UPS where P UPS s the UPS nput power, and α and b are fxed to match the converson effcency curve for dfferent UPSs. In our evaluaton, we chose a value of for α and for b. EVALUATION RESULTS To verfy the power model, we conducted an experment wth 10 servers and two applcatons. The servers were eght Intel CPU servers and two AMD CPU servers; the applcatons were Y-Cruncher ( -cruncher), a CPU-ntensve applcaton, and Yahoo Cloud Servng Benchmark (YCSB; /news/yahoo-cloud-servng-bench power by runnng the two applcatons on all 10 machnes smultaneously whle randomly changng each applcaton s workload durng the test. The sample frequency s 1 Hz, whch s suffcent for tasks that must execute over many hours or even days. We conducted the test on Intel and AMD machnes separately and used lnear regresson to ft the dataponts. The P IDLE of 10 machnes was 2,183 W. The workload of Y-Cruncher and YCSB are represented n dgts per second and operatons per second. The coeffcents α of Y-Cruncher on Intel and AMD servers were W/dgts/s and W/dgts/s. The coeffcents α of YCSB on Intel and AMD servers were W/operatons/s and W /operatons/s. Fgure 4 shows the measured power by a power meter and the estmated power usng our rack-level power model. Error rates were wthn ±2.5 percent a correspondng powerestmaton error of less than 83 W. Moreover, our rack-level power model overestmated power consumpton 82 percent of the tme (246 out of 300 sample ponts). For under estmated cases, FEBRUARY

5 CLOUD COMPUTING 3,550 3,500 Measured power Estmated power Error rate , , Power (W) 3,350 3, % 3, , , , Tme (s) 3.00 FIGURE 4. Real-tme power estmaton and error rate. Error rate s represented as (estmated power measured power)/measured power. In some cases, the gap between measured power and estmated power s less than 47 W wth an error rate of 1.4 percent. the gap between measured power and estmated power was less than 47 W wth an error rate of 1.4 percent. These results are sgnfcant n lght of the optmzaton problem s power constrant. Hgh underestmaton pro b ablty and error rate can lead to a volaton of the rack-level powercappng requrement. Smulaton results We compared the total IT equpment power and wasted power from UPSs n both our optmal workload allocaton and a baselne case that evenly allocates workload among racks. We assumed that each rack hosts 20 servers, and that each rack s power s suppled by one or two UPSs wth an N+1 or a UPS confguraton. Our smulaton was for 50 racks runnng 10 applcatons smultaneously. We used Mathematca to perform the smulaton, whch ended when ether the teratons exceeded a predefned threshold or the results converged to the requested precson. Power-reducton comparson. Fgure 5 shows the power reducton wth our optmal workload allocaton relatve to the baselne allocaton (evenly dstrbuted workloads). For both the N+1 and UPS confguratons, the optmal workload allocaton reduces power consumpton by 1.23 percent to 5.20 percent. The N+1 confguraton has a slghtly hgher power-reducton rate, but overall the rate gap between confguratons s small for all loads. Optmal workload allocaton acheves the hghest power reducton at the datacenter utlzaton of 50 percent, whch s also the average level for most datacenters. 15 The degree of power reducton depends on the UPS effcency curve and the alpha coeffcent value (α ) n Equaton 1. As an extreme example, f UPS effcency s constant, power reducton wll be zero for all datacenter-utlzaton levels. That s, regardless of workload dstrbuton, UPS effcency (total UPS output power) s constant for a partcular workload sze. Because UPS effcency s constant, UPS nput power and power loss are also constant. Because the alpha coeffcent de cdes the power-ncrease rate for a specfc applcaton, t affects the datacenter s power consumpton (UPS output power), whch s why a dfferent workload allocaton mght have a dfferent power consumpton for the same workload sze. Workload-type effects. To better un - der stand how workload type affects power reducton, we changed the applcaton mx whle keepng total datacenter utlzaton at 50 percent. In ths smulaton, we dvded the 10 applcatons nto two categores CPU-ntensve and Web servce and then mxed the types wth dfferent proportons. As Fgure 6 shows, a greater proporton of CPU-ntensve applcatons translates to hgher power reducton, wth the maxmum reducton at 85 percent CPU-ntensve applcatons and 15 percent Web servce applcatons. These results are predctable: the more CPU-ntensve applcatons there are, the more power goes to the rack. The hgher rack power ncreases the UPS s loaded capacty, whch could result n lower power loss. Translaton to energycost reducton Datacenter power capacty vares consderably. As of 2011, t was estmated to be anywhere from 2 to 100 MW ( 50 COMPUTER

6 N + 1 /nternatonal/publcatons/clmate /2011/Cool%20IT/drty-data-facltes -table-greenpeace.pdf), wth half the datacenters surveyed fallng between 20 and 76 MW. Accordng to a 2014 Uptme Insttute report ( ournal.uptmensttute.com/2014 -data-center-ndustry-survey), the average data center PUE s 1.7. For a datacenter wth a 76-MW capacty, IT equpment power consumpton would be 44.7 MW. Wth the 5.2 maxmum power- consumpton reducton demonstrated n our smulaton, the datacenter could reduce ts annual energy cost by 44.7 MW per day, whch s roughly $1.4 mllon ( days 24 h 0.07 $/kwh 0.052). Our experments wth the racklevel power model show that UPS confguratons sgnfcantly affect a datacenter s energy effcency and that UPS power loss s dfferent when IT workload changes. Along wth our workload-placement calculatons, the model mnmzes IT equp ment power consumpton and UPS power loss wth up to a 5.2 percent power reducton relatve to an even workload-allocaton strategy. In future work, we wll focus on how DVFS and swtchng servers on and off can enhance UPS effcency. ACKNOWLEDGMENTS Ths work s supported n part by Natonal Scence Foundaton (NSF) grant CNS We thank Wayne State Unversty s Computng and Informaton Technology Department for ts sgnfcant asss tance and NextEnergy for collectng data and runnng experments. The research reported n ths artcle s based on work done by Power reducton (%) Wesong Sh whle he was at NSF. REFERENCES 1. A. Gandh et al., Optmal Power Allocaton n Server Farms, Proc. ACM Int l Conf. Measurement and Modelng of Computer Systems (SIGMET- RICS 09), 2009, pp Q. Deng et al., Coscale: Coordnatng CPU and Memory System DVFS n Server Systems, Proc. 45th IEEE/ ACM Int l Symp. Mcroarchtecture (MICRO 12), 2012, pp Datacenter utlzaton (%) FIGURE 5. Power reducton wth our optmal workload allocaton (optmal power) relatve to an evenly allocated workload (baselne) for an N+1 and a UPS confguraton. Power reducton s represented as (baselne power optmal power)/baselne power. Power reducton s hghest for both confguratons when datacenter utlzaton s 50 percent. Power reducton (%) :1.0 N : : : : : : :0.3 Workload dstrbuton (CPU:Web) 0.8: :0.15 FIGURE 6. Power reducton wth dfferent proportons of CPU-ntensve (CPU) and Web servce (Web) applcatons when datacenter utlzaton s 50 percent. Power reducton s (baselne power optmal power)/baselne power. 0.9: J.S. Chase et al., Managng Energy and Server Resources n Hostng Centers, ACM SIGOPS Operatng Systems Rev., vol. 35, no. 5, 2001, pp R. Nathu and K. Schwan, Vrtual Power: Coordnated Power Management n Vrtualzed Enterprse Systems, ACM SIGOPS Operatng Systems Rev., vol. 41, no. 6, 2007, pp Q. Tang et al., Energy-Effcent Thermal-Aware Task Schedulng 1.0:0 FEBRUARY

7 CLOUD COMPUTING ABOUT THE AUTHORS QUAN ZHANG s a doctoral researcher n computer scence at Wayne State Unversty. Hs research nterests nclude dstrbuted systems, cloud computng, and energy-effcent computng. Zhang receved a BS n computer scence from Tong Unversty. He s a student member of IEEE. Contact hm at quan.zhang@ wayne.edu. WEISONG SHI s a professor of computer scence at Wayne State Unversty. Hs research nterests nclude energy-effcent computer systems and software, Internet computng, and moble health. Sh receved a PhD n computer engneerng from the Chnese Academy of Scences. He s an IEEE Fellow and a Senor Member of ACM. Contact hm at wesong@wayne.edu. for Homogeneous Hgh-Performance Int l Symp. Low Power Electroncs and Computng Data Centers: Desgn (ISLPED 01), 2001, pp A Cyber-Physcal Approach, IEEE 8. H. Davd et al., Rapl: Memory Power Trans. Parallel and Dstrbuted Systems, Estmaton and Cappng, Proc. 15th vol. 19, no. 11, 2008, pp ACM/IEEE Int l Symp. Low-Power 6. A. Verma, P. Ahua, and A. Neog, Electroncs and Desgn (ISLPED 10), Pmapper: Power and Mgraton Cost 2010, pp Aware Applcaton Placement n Vrtualzed Systems, Proc. 9th ACM Dsk Power Consumpton, Proc. 2nd 9. J. Zedlewsk et al., Modelng Hard- /IFIP/USENIX Int l Conf. Mddleware USENIX Conf. Fle and Storage Technologes (FAST 03), 2003, pp (Mddleware 08), 2008, pp R. Joseph and M. Martonos, Runtme 10. C. Lefurgy, X. Wang, and M. Ware, Power Estmaton n Hgh- Performance Server-Level Power Control, Mcroprocessors, Proc. 6th ACM/IEEE Proc. 4th IEEE Int l Conf. Autonomc Computng (ICAC 07), 2007, pp D. Mesner, B.T. Gold, and T.F. Wen sch, The Powernap Server Archtecture, ACM Trans. Computer Systems, vol. 29, no. 1, 2011, pp A. Kansal et al., Vrtual Machne Power Meterng and Provsonng, Proc. 1st ACM Symp. Cloud Computng (SOCC 10), 2010, pp E. Pakbazna and M. Pedram, Mnmzng Data Center Coolng and Server Power Costs, Proc. 14th ACM /IEEE Int l Symp. Low-Power Electroncs and Desgn (ISLPED 01), 2009, pp V. Kontorns et al., Managng Dstrbuted UPS Energy for Effectve Power Cappng n Datacenters, Proc. 39th Ann. IEEE/ACM Int l Symp. Computer Archtecture (ISCA 12), 2012, pp L.A. Barroso and U. Hölzle, The Data Center as a Computer: An Introducton to the Desgn of Warehouse-Scale Machnes, Morgan and Claypool, Selected CS artcles and columns are also avalable for free at Engneerng and Applyng the Internet IEEE Internet Computng reports emergng tools, technologes, and applcatons mplemented through the Internet to support a worldwde computng envronment. For submsson nformaton and author gudelnes, please vst 52 COMPUTER

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

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

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

More information

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

Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier

Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier Some materal adapted from Mohamed Youns, UMBC CMSC 611 Spr 2003 course sldes Some materal adapted from Hennessy & Patterson / 2003 Elsever Scence Performance = 1 Executon tme Speedup = Performance (B)

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

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

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

More information

Mathematics 256 a course in differential equations for engineering students

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

More information

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling

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

More information

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

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

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

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

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

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

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

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

More information

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

Solution Brief: Creating a Secure Base in a Virtual World

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

More information

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

Achieving Energy Proportionality In Server Clusters

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

More information

Resource and Virtual Function Status Monitoring in Network Function Virtualization Environment

Resource and Virtual Function Status Monitoring in Network Function Virtualization Environment Journal of Physcs: Conference Seres PAPER OPEN ACCESS Resource and Vrtual Functon Status Montorng n Network Functon Vrtualzaton Envronment To cte ths artcle: MS Ha et al 2018 J. Phys.: Conf. Ser. 1087

More information

Optimizing Document Scoring for Query Retrieval

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

More information

ELEC 377 Operating Systems. Week 6 Class 3

ELEC 377 Operating Systems. Week 6 Class 3 ELEC 377 Operatng Systems Week 6 Class 3 Last Class Memory Management Memory Pagng Pagng Structure ELEC 377 Operatng Systems Today Pagng Szes Vrtual Memory Concept Demand Pagng ELEC 377 Operatng Systems

More information

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION

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

More information

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

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

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

More information

Distributed Middlebox Placement Based on Potential Game

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

More information

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

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

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

More information

CACHE MEMORY DESIGN FOR INTERNET PROCESSORS

CACHE MEMORY DESIGN FOR INTERNET PROCESSORS CACHE MEMORY DESIGN FOR INTERNET PROCESSORS WE EVALUATE A SERIES OF THREE PROGRESSIVELY MORE AGGRESSIVE ROUTING-TABLE CACHE DESIGNS AND DEMONSTRATE THAT THE INCORPORATION OF HARDWARE CACHES INTO INTERNET

More information

Game Based Virtual Bandwidth Allocation for Virtual Networks in Data Centers

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

More information

Dynamic Voltage Scaling of Supply and Body Bias Exploiting Software Runtime Distribution

Dynamic Voltage Scaling of Supply and Body Bias Exploiting Software Runtime Distribution Dynamc Voltage Scalng of Supply and Body Bas Explotng Software Runtme Dstrbuton Sungpack Hong EE Department Stanford Unversty Sungjoo Yoo, Byeong Bn, Kyu-Myung Cho, Soo-Kwan Eo Samsung Electroncs Taehwan

More information

The Codesign Challenge

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

More information

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

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

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

Two-Stage Data Distribution for Distributed Surveillance Video Processing with Hybrid Storage Architecture

Two-Stage Data Distribution for Distributed Surveillance Video Processing with Hybrid Storage Architecture Two-Stage Data Dstrbuton for Dstrbuted Survellance Vdeo Processng wth Hybrd Storage Archtecture Yangyang Gao, Hatao Zhang, Bngchang Tang, Yanpe Zhu, Huadong Ma Bejng Key Lab of Intellgent Telecomm. Software

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

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

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

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

Fast Computation of Shortest Path for Visiting Segments in the Plane

Fast Computation of Shortest Path for Visiting Segments in the Plane Send Orders for Reprnts to reprnts@benthamscence.ae 4 The Open Cybernetcs & Systemcs Journal, 04, 8, 4-9 Open Access Fast Computaton of Shortest Path for Vstng Segments n the Plane Ljuan Wang,, Bo Jang

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

Towards High Fidelity Network Emulation

Towards High Fidelity Network Emulation Towards Hgh Fdelty Network Emulaton Lanje Cao, Xangyu Bu, Sona Fahmy, Syuan Cao Department of Computer Scence, Purdue nversty, West Lafayette, IN, SA E-mal: {cao62, xb, fahmy, cao208}@purdue.edu Abstract

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

A Dynamic Feedback-based Load Balancing Methodology

A Dynamic Feedback-based Load Balancing Methodology .J. Modern Educaton and Computer Scence, 2017, 12, 57-65 Publshed Onlne December 2017 n MECS (http://www.mecs-press.org/) DO: 10.5815/jmecs.2017.12.07 A Dynamc Feedback-based Load Balancng Methodology

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

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

THere are increasing interests and use of mobile ad hoc

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

More information

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

Assembler. Building a Modern Computer From First Principles.

Assembler. Building a Modern Computer From First Principles. Assembler Buldng a Modern Computer From Frst Prncples www.nand2tetrs.org Elements of Computng Systems, Nsan & Schocken, MIT Press, www.nand2tetrs.org, Chapter 6: Assembler slde Where we are at: Human Thought

More information

Energy Aware Virtual Machine Migration Techniques for Cloud Environment

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

More information

AADL : about scheduling analysis

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

More information

A QoS-aware Scheduling Scheme for Software-Defined Storage Oriented iscsi Target

A QoS-aware Scheduling Scheme for Software-Defined Storage Oriented iscsi Target A QoS-aware Schedulng Scheme for Software-Defned Storage Orented SCSI Target Xanghu Meng 1,2, Xuewen Zeng 1, Xao Chen 1, Xaozhou Ye 1,* 1 Natonal Network New Meda Engneerng Research Center, Insttute of

More information

A Semi-Distributed Load Balancing Architecture and Algorithm for Heterogeneous Wireless Networks

A Semi-Distributed Load Balancing Architecture and Algorithm for Heterogeneous Wireless Networks A Sem-Dstrbuted oad Balancng Archtecture and Algorthm for Heterogeneous reless Networks Md. Golam Rabul Ala Choong Seon Hong * Kyung Hee Unversty, Korea rob@networkng.khu.ac.kr, cshong@khu.ac.kr Abstract

More information

Configuration Management in Multi-Context Reconfigurable Systems for Simultaneous Performance and Power Optimizations*

Configuration Management in Multi-Context Reconfigurable Systems for Simultaneous Performance and Power Optimizations* Confguraton Management n Mult-Context Reconfgurable Systems for Smultaneous Performance and Power Optmzatons* Rafael Maestre, Mlagros Fernandez Departamento de Arqutectura de Computadores y Automátca Unversdad

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

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

Joint Energy Scheduling and Water Saving in Geo-Distributed Mixed-Use Buildings

Joint Energy Scheduling and Water Saving in Geo-Distributed Mixed-Use Buildings Ths artcle has been accepted for publcaton n a future ssue of ths journal, but has not been fully edted. Content may change pror to fnal publcaton. Ctaton nformaton: DOI 1.119/TSG.218.288654, IEEE Transactons

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

Channel 0. Channel 1 Channel 2. Channel 3 Channel 4. Channel 5 Channel 6 Channel 7

Channel 0. Channel 1 Channel 2. Channel 3 Channel 4. Channel 5 Channel 6 Channel 7 Optmzed Regonal Cachng for On-Demand Data Delvery Derek L. Eager Mchael C. Ferrs Mary K. Vernon Unversty of Saskatchewan Unversty of Wsconsn Madson Saskatoon, SK Canada S7N 5A9 Madson, WI 5376 eager@cs.usask.ca

More information

Wavefront Reconstructor

Wavefront Reconstructor A Dstrbuted Smplex B-Splne Based Wavefront Reconstructor Coen de Vsser and Mchel Verhaegen 14-12-201212 2012 Delft Unversty of Technology Contents Introducton Wavefront reconstructon usng Smplex B-Splnes

More information

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation Intellgent Informaton Management, 013, 5, 191-195 Publshed Onlne November 013 (http://www.scrp.org/journal/m) http://dx.do.org/10.36/m.013.5601 Qualty Improvement Algorthm for Tetrahedral Mesh Based on

More information

Multi-objective Virtual Machine Placement for Load Balancing

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

More information

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

More information

Self-Tuning, Bandwidth-Aware Monitoring for Dynamic Data Streams

Self-Tuning, Bandwidth-Aware Monitoring for Dynamic Data Streams Self-Tunng, Bandwdth-Aware Montorng for Dynamc Data Streams Navendu Jan, Praveen Yalagandula, Mke Dahln, Yn Zhang Mcrosoft Research HP Labs The Unversty of Texas at Austn Abstract We present, a self-tunng,

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

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

DiBA: Distributed Power Budget Allocation for Large-Scale Computing Clusters

DiBA: Distributed Power Budget Allocation for Large-Scale Computing Clusters 26 6th IEEE/ACM Internatonal Symposum on Cluster, Cloud, and Grd Computng DBA: Dstrbuted Power Budget Allocaton for Large-Scale Computng Clusters Masoud Bade SEAS Harvard Unversty mbadek@seas.harvard.edu

More information

Optimized caching in systems with heterogeneous client populations

Optimized caching in systems with heterogeneous client populations Performance Evaluaton 42 (2000) 163 185 Optmzed cachng n systems wth heterogeneous clent populatons Derek L. Eager a,, Mchael C. Ferrs b, Mary K. Vernon b a Department of Computer Scence, Unversty of Saskatchewan,

More information

Outline. Digital Systems. C.2: Gates, Truth Tables and Logic Equations. Truth Tables. Logic Gates 9/8/2011

Outline. Digital Systems. C.2: Gates, Truth Tables and Logic Equations. Truth Tables. Logic Gates 9/8/2011 9/8/2 2 Outlne Appendx C: The Bascs of Logc Desgn TDT4255 Computer Desgn Case Study: TDT4255 Communcaton Module Lecture 2 Magnus Jahre 3 4 Dgtal Systems C.2: Gates, Truth Tables and Logc Equatons All sgnals

More information

Real-time Fault-tolerant Scheduling Algorithm for Distributed Computing Systems

Real-time Fault-tolerant Scheduling Algorithm for Distributed Computing Systems Real-tme Fault-tolerant Schedulng Algorthm for Dstrbuted Computng Systems Yun Lng, Y Ouyang College of Computer Scence and Informaton Engneerng Zheang Gongshang Unversty Postal code: 310018 P.R.CHINA {ylng,

More information

Cost-efficient deployment of distributed software services

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

More information

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

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

Virtual Machine Placement Based on the VM Performance Models in Cloud

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

More information

A 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

An Efficient Garbage Collection for Flash Memory-Based Virtual Memory Systems

An Efficient Garbage Collection for Flash Memory-Based Virtual Memory Systems S. J and D. Shn: An Effcent Garbage Collecton for Flash Memory-Based Vrtual Memory Systems 2355 An Effcent Garbage Collecton for Flash Memory-Based Vrtual Memory Systems Seunggu J and Dongkun Shn, Member,

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Maintaining temporal validity of real-time data on non-continuously executing resources

Maintaining temporal validity of real-time data on non-continuously executing resources Mantanng temporal valdty of real-tme data on non-contnuously executng resources Tan Ba, Hong Lu and Juan Yang Hunan Insttute of Scence and Technology, College of Computer Scence, 44, Yueyang, Chna Wuhan

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

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

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

Application of VCG in Replica Placement Strategy of Cloud Storage

Application of VCG in Replica Placement Strategy of Cloud Storage Internatonal Journal of Grd and Dstrbuted Computng, pp.27-40 http://dx.do.org/10.14257/jgdc.2016.9.4.03 Applcaton of VCG n Replca Placement Strategy of Cloud Storage Wang Hongxa Computer Department, Bejng

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract

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

TripS: Automated Multi-tiered Data Placement in a Geo-distributed Cloud Environment

TripS: Automated Multi-tiered Data Placement in a Geo-distributed Cloud Environment TrpS: Automated Mult-tered Data Placement n a Geo-dstrbuted Cloud Envronment Kwangsung Oh, Abhshek Chandra, and Jon Wessman Department of Computer Scence and Engneerng Unversty of Mnnesota Twn Ctes Mnneapols,

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

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

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

More information

Decision Support for the Dynamic Reconfiguration of Machine Layout and Part Routing in Cellular Manufacturing

Decision Support for the Dynamic Reconfiguration of Machine Layout and Part Routing in Cellular Manufacturing Decson Support for the Dynamc Reconfguraton of Machne Layout and Part Routng n Cellular Manufacturng Hao W. Ln and Tomohro Murata Abstract A mathematcal based approach s presented to evaluate the dynamc

More information

Self-Tuning, Bandwidth-Aware Monitoring for Dynamic Data Streams

Self-Tuning, Bandwidth-Aware Monitoring for Dynamic Data Streams Self-Tunng, Bandwdth-Aware Montorng for Dynamc Data Streams Navendu Jan #, Praveen Yalagandula, Mke Dahln #, Yn Zhang # # Unversty of Texas at Austn HP Labs Abstract We present, a self-tunng, bandwdth-aware

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 Genetic Algorithm Based Dynamic Load Balancing Scheme for Heterogeneous Distributed Systems

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

More information

If you miss a key. Chapter 6: Demand Paging Source:

If you miss a key. Chapter 6: Demand Paging Source: ADRIAN PERRIG & TORSTEN HOEFLER ( -6- ) Networks and Operatng Systems Chapter 6: Demand Pagng Source: http://redmne.replcant.us/projects/replcant/wk/samsunggalaxybackdoor If you mss a key after yesterday

More information

Sequential search. Building Java Programs Chapter 13. Sequential search. Sequential search

Sequential search. Building Java Programs Chapter 13. Sequential search. Sequential search Sequental search Buldng Java Programs Chapter 13 Searchng and Sortng sequental search: Locates a target value n an array/lst by examnng each element from start to fnsh. How many elements wll t need to

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

Parallelization of a Series of Extreme Learning Machine Algorithms Based on Spark

Parallelization of a Series of Extreme Learning Machine Algorithms Based on Spark Parallelzaton of a Seres of Extreme Machne Algorthms Based on Spark Tantan Lu, Zhy Fang, Chen Zhao, Yngmn Zhou College of Computer Scence and Technology Jln Unversty, JLU Changchun, Chna e-mal: lutt1992x@sna.com

More information

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

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

More information

RAP. Speed/RAP/CODA. Real-time Systems. Modeling the sensor networks. Real-time Systems. Modeling the sensor networks. Real-time systems:

RAP. Speed/RAP/CODA. Real-time Systems. Modeling the sensor networks. Real-time Systems. Modeling the sensor networks. Real-time systems: Speed/RAP/CODA Presented by Octav Chpara Real-tme Systems Many wreless sensor network applcatons requre real-tme support Survellance and trackng Border patrol Fre fghtng Real-tme systems: Hard real-tme:

More information

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples

More information