An Adaptive Batched Patch Caching Scheme for Multimedia Streaming *

Size: px
Start display at page:

Download "An Adaptive Batched Patch Caching Scheme for Multimedia Streaming *"

Transcription

1 An Adatve Batched Patch achng Schee for Multeda Streang * Shaohua Qn, Wehong He, Zu L, and Janng Hu School of outer Scence, Beng Unversty of Aeronautcs & Astronautcs, Beng 8,hna {shqn,annghu}@buaa.edu.cn Hengyang Branch of Hunan Unversty, Hengyang 4, hna hwh@hnbc.edu.cn etwork Research enter of Tsnghua Unversty, Beng 84,hna zl@cernet.edu.cn Abstract. Large-scale steang eda alcatons usually consue a sgnfcant aount of server and network resources due to the hgh bandwdth requreents and the long-lved nature of the streang eda obects. In ths aer, we address the roble of effcently streang eda obect to the clents over a dstrbuted nfrastructure consstng of vdeo server and roy caches. We buld on the earler work and roose an adatve batched atch cachng schee, whch tghtly cobne the transsson schedulng wth roy cachng. Ths schee adatvely caches the net segent data at roy fro the ongong entre strea, whch deends on the current batchng nterval that has non-zero requests. We deonstrate the benefts of our schee coare to the classcal streang strateges. Our evaluatons show that ths schee can reduce sgnfcantly the consuton of aggregate bandwdth on backbone lnk wthn uch wder range of request arrval rate. Keywords: Streang eda, Batched atch, Proy cache, Multcast, Server schedulng. Introducton The eergence of the Internet as a ervasve councaton edu, and a ature dgtal vdeo technology have led to a rse of varous networked streang eda alcatons such as vdeo-on-deand, dstance learnng, vdeo gae and vdeo conferencng. As access rovders are rollng out faster last-le connectons, the bottleneck s shftng ustrea to the rovder s backbone, eerng lnks and best-effort Internet. Due to the large sze, long-lved nature of the streang obects, they need to consue uch ore network bandwdth and server syste resource n dstrbuton and delvery. At the sae te, the I/O caacty of the vdeo server and network bandwdth are ossble to be unrestraned enhanceent because of hardware costs ltaton. So, n the rocess of dstrbutng streang eda over the Internet, how to reduce the backbone bandwdth consuton and effcently utlze the vdeo server syste resource have becoe the research hotsot n the area of streang eda alcatons n recent years. Estng research has focused on develong transsson schees that use ultcast or broadcast connectons n nnovatve ways to reduce server and network loads, * Ths work s suorted by the SF of hna under grant 65. J. Vcente and D. Hutchson Eds.: MMS 4, LS 7,. 6 7, 4. IFIP Internatonal Federaton for Inforaton Processng 4

2 64 Shaohua Qn et al. for servng a oular vdeo to ultle asynchronous clents. Batchng [], Patch [], [4], HMSM[] and Otzed Batch Patchng [] are reactve n that the server transts vdeo data only on deand, n resonse to arrvng clent requests. These schees have an underlyng requreent that the ultcast or broadcast connectvty between the server and the clents s avalable. However, IP ultcast deloyent n the Internet has been slow and even today reans severely lted n scoe and reach. Therefore, transsson schees that can suort effcent delvery n such redonantly uncast settngs need to be develoed.. Another attractve soluton for reducng server loads, backbone network traffc and access latences s the use of roy caches. Ths technque has roven to be qute effectve for delverng tradtonal Web obects. However, streang eda obect can be very large, and tradtonal technques for cachng entre obects are not arorate for such eda. achng strateges that have been roosed n recent years [7],[],[],[4] cache a orton of streang eda obect at the roy. These ref and segentaton-based cachng ethods have a nuber of advantages ncludng reducng startu latency and tter on the server-roy ath, whle savng bandwdth usage along that ath. However, they do not take the ssue of the transsson schedulng nto consderaton. Recent work [] cobnes ref cachng wth royasssted reactve transsson schees for reducng the transsson cost of ultle heterogeneous vdeos. Another work [5],[6],[8],[9] cobnes ultcast-based server schedulng wth roy cachng to nze the aggregate bandwdth usage. In artcular, the Batched Patch achng BP roosed n [5] whch caches the atch data at cachng roy n order to ake ore clents to share t, and as thus acheve better erforance. However, when the request arrval rate s very hgh, these schees entoned above are stll consue qute a few syste resources. In ths aer, we buld on early work and roose an adatve batched atch cachng schee knows as ABP whch cobnes dynac cachng at the roy wth scalable transsson schee at the orgn server. In ths schee, the server-roy network connectons only rovde uncast servce, and on the roy-clent ath offers ultcast caablty. By adatve re-cachng the atch data for the ucong request n the net batchng nterval, t acheves lower bandwdth consuton than the BP schee over a wder range of request arrval rate. The rest of ths aer s organzed as follows. In secton, soe revous works n the ultcast and streang eda cachng areas are revewed. In secton, we resent and forulate our schee n detal. Secton 4 shows results that coare the erforance of new schee and BP. Fnally we resent our conclusons and ongong work n secton 5. Prevous Work Streang eda obects over ultcast consues less network bandwdth and oses less of a load on the server than does streang eda obects over ultle uncast channels. Batchng s a sle schedulng strategy based on ultcast. It delays the earler arrval request to wat for uch ore clents, and serves the over a sngle channel. Patchng s certanly one of the ost effcent technques. The server streas the entre vdeo sequentally to the very frst clent. A later clent receves ts future layback data by lstenng to an estng ongong ultcast of the sae vdeo, and the server only transts afresh only the ssng orton atch data.

3 An Adatve Batched Patch achng Schee for Multeda Streang 65 The concet of otzed batch atchng OBP n lterature [] has recently been roosed, whch aed at nzng the average backbone rate. Bascally, clent requests are batched together on an nterval bass before requestng ether a atch or a regular ultcast fro the server. There s an otal atchng wndow after whch t s ore bandwdth effcent to start a new entre strea rather than send atches. Ths schee outerfors other ultcast-based technques such as otal atchng [4] n ters of average backbone rate over a large range of request rates []. The Batched Patch achng BP was bult on the Otzed Batch Patchng dea. Uon receton of a atch, the roy stores t n the buffer for a erod of the atchng wndow sze, so that t s avalable for the last requests of the sae atchng wndow and consequently reduces the bandwdth usage of the etra channel. By cachng the atch data n the roy, ths schee deands the average backbone rate saller than that of OBP schee. But, t needs to retranst all of the atch data. We dffer fro all the above works n that we develo a new echans to refetch the atch data fro the ongong entre strea along the uncast connecton of the server and the roy. At the sae te, the re-fetchng data s cached dynacally at the roy. They can serve the requests of the sae atchng wndow. Moreover, by varyng the sze of the atchng wndow accordng to oularty of the streang eda obect, the nu consuton of the backbone bandwdth can acheve, and lted storage sace of roy can utlze effcently. SERVER Pr oy Pr oy lent l ent lent lent Fg.. Illustraton of roy cache for streang eda. Adatve Batched Patch achng Schee In ths secton, we consder a delverng archtecture of streang eda obect, whch coosed of an orgn server, a set of roes, and a fnte set of eda obects. Each roy s resonsble for a grou of clents as shown n Fg.. We assue relable transssons over the server-roy ath, and the access network roy-clent s lossless and ultcast enabled. We further assue that the clents are always request lay back fro the begnnng of the eda obect. Moreover we ose the roy to lay the role of a clent for server. That s, all the streang eda obect data streaed out of the server are requested by the roy and are thereby forwarded through t. A roy streas the ref drectly to ts clents f a ref of the eda obect s resent locally, and contacts the server for the reander suff of the strea. Otherwse, the roy sends the server a request to start a full strea uncast and ultcasts t to a set of clents. In order to sheld the clent-erceved startu latency, the roy edately sends clent the frst segent data by uncast channel once a request arrves n each batchng nterval. Ths uncast strea wll ternate at

4 66 Shaohua Qn et al. the boundary of the batchng nterval. At ths te, the clent wll on the full strea and the atch data strea that started by the roy va ultcast channel. We net ntroduce the notatons used n ths aer, as resented n Table. We consder a server wth a reostory of M onstant-bt-rate BR eda obects. Let eda obect M s characterzed by ts layback rate r, duraton L, and average access rate λ. Table. Paraeters used n ths aer. Para. Defnton M uber of the eda obects L Length of eda obect sec. r Playback rate of eda obect bs S The cache sze of roy Ω oralzed transsson rate λ Average request arrval rate for obect W Patchng wndow sze for obect µ Total atch data for obect b The batchng nterval. Schee Descrton The basc dea of the adatve batched atch cachng s that whenever a full strea s started, the roes that receve the data fro ths strea allocate a buffer sze of b unts to cache the ucong data. And at the end of each batch n the sae atchng wndow, these roes check to see whether or not there are requests. If there are requests, these roes searately add b unts to the buffer and cache the ongong strea contnuously. Otherwse they sto cachng. Snce we do not cache the data segents at the end of each batch of zero requests, the roy wll need to start an etra channel to afresh the f there are requests n the subsequent batchng ntervals. Full strea Full strea L L W b -b b b b t t - t t b t t Server te A B D E F Proy te Fg.. Tng Dagra for adatve batched atch cachng. Our scenaro s llustrated n Fg., The roy dvdes unforly the te as nto ntervals [t -, t ] of duraton b, Assue a request arrves at the roy at te t [t -, t ], and the ost recent full strea was started at te t. If t s such that t < t W, the roy need to transt atch data of duraton t t b to the clent at te t, also the roy ons the full strea at te t, and ultcasts t to the clents. However,

5 An Adatve Batched Patch achng Schee for Multeda Streang 67 f t > t W, a new full strea wll be started at te t. Snce the frst segent data [, b ] of the streang eda obect has been stored at the roy at te t after the full strea s started, whether the subsequent segent data need to be cached deends on the current batchng ntervals that have no-zero requests before te t. Ths s better elaned wth the followng eale. Suose there are eght batchng ntervals n the atchng wndow, that s W 8b. The full strea was started at te t. Also at te t the roy began to buffer the frst segent data fro ths stea. Suose [t, t ] had requests, then at te t the roy adds b unts to the buffer and caches the ongong strea contnuously. Ths akes the roy can serve the requests arrve at te ntervals [t, t ] and [t, t ], and does not request server for any atch bytes. Suose the net two ntervals do not have any requests, and the roy does not cache the corresondng data segent [b,b ],[ b,4b ]contnuously. If the fourth nterval [t, t 4 ] has requests, at te t 4, the buffer of the roy has only contaned two segent data [, b ] and [b, b ]. The requests arrve n the fourth nterval requres the atches to be 4b -long, and so the roy eands the buffer fro havng b unts to havng 5b unts, and then fetches the ssng atch data [b,b ] and [b,4b ] fro the server by the etra channel whle storng the segent data [4b,5b ] fro the ongong full strea. The rocessng ethod for subsequence ntervals s slar to that for the revew ntervals. At last, whether the eghth nterval [t 7, t 8 ], has requests or not, the roy wll not store the net segent data fro the full strea at te t 8. Our schee has a rearkable characterstc. That s, the ore robablty of the request arrval each batchng nterval has That eans the request arrval rate s very hgh, the lttle atch data need to be transtted afresh becoe. When each batched nterval of atchng wndow has no-zero requests, the re-fetchng echans can assure that the deanded atchng data ust obtanng fro full strea can satsfy all the request arrved n the sae atchng wndow. On the other hand, f only the last batchng nterval has requests, the roy wll need to fetch the atch data u to b va the etra channel.. Schee Analyses and Proble Forulaton For slcty of eoston, we gnore network roagaton latency. In order to derve analytc eressons n evaluatng the erforance of our schee, we frst ake an abstract of our schee as follows: Assue the access rate of eda obect are odeled by Posson rocess wth araeter λ such that - λ e b s the robablty to have an ety batch zero request of duraton b. The roy stores the atch data n the buffer at least for a erod of W b, so that t s avalable for the all requests arrved n the sae atchng wndow. Suose denotes the requests that arrve n the th batchng nterval [t -, t ]. Let,,, be a sequence of ndeendent rando varables wth coon robablty dstrbuton.

6 68 Shaohua Qn et al. Whether the roy need to fetch the atch data by etra channel at te t deends on the values of,,, - and. In artcular f or, the roy does not request server for any atch bytes. Assue the roy request server for the atches sze s ψ n the atchng wndow. It s obvously ψ wll lkely take one aong the values,b,b,, b, we ght as well let denotes the robablty of ψb, that s ψb,,,,,. Wth the above assuton, we can acheve the ean value of η, naely b b Eψ ow we need to deterne. Obvously,,,, ψ b ψ b - - k ψ b ψ

7 An Adatve Batched Patch achng Schee for Multeda Streang 69 Thus the eresson of can be wrtten as:,,,,,. Substtutng equaton. nto equaton, by coutng all the dfferent ossbltes of batchng nterval along the atchng wndow, we get the average nuber of atched data segents, µ at roy. It s gven by µ Eψ b The aggregate transsson rate on the backbone lnk, R, ncludes the transsson of atches µ and the full strea of duraton L fro the server. Its noralzed transsson rate Ω s thus obtaned fro: R L µ Ω 4 r I Where I reresents the nterval duraton between two adacent full streas: I b / λ 5 The average buffer caacty S needed for cachng at roy s then gven by S µ µ r 6 Where µ' denotes the segent data receved fro the full strea. Accordng to the buffer allocatng echans n our schee, µ' s gven by µ b b 7 We now coute the roy network bandwdth. Recall that the roy delver the frst segent data to clents va uncast channel, and forwards the full strea and the other atchng data va ultcast channel. Thus ts noralzed bandwdth B roy s gven by: B λ b b r - ory I 4 uercal Results and oarsons In ths secton, we evaluate the erforance of our roosed schee ABP and contrast t aganst BP n three asects usng nuercal result. Suose the duraton of the streang eda obect s nutes, and ts average lay back rate s.5 Mbs MPEG-. Frst, we eane the transsson quanttes of atchng data that needed to get by the etra channel wth resect to the request arrval rate and the atchng wndow sze. As shown n Fg., adotng the ABP schee, the average nuber of transtted atches decreases radly as the request arrval rate ncreases, and that close to zero. r Ω 8

8 7 Shaohua Qn et al. Ths ndcates that ABP schee only needs to fetch few atch data through the etra channel whle the request arrval rate reaches relatve hgh. But the BP schee needs to fetch all the atch data through the etra channel, and that close to the atchng wndow sze. In other words, whatever the request arrval rate and the atchng wndow change, under the sae condtons, the ABP schee can save uch ore bandwdth of etra channel than the BP schee. Average nuber of transtted atches [n] BP AB P Request arrval rate [req/ n] Fg.. Average nuber of transtted atches through etra channel versus the request arrval rate, b [n]. Secondly, we coare the noralzed backbone rate deanded n the case of transttng one eda obect for both schees ABP and BP by showng n Fg. 4a ~ d. Fro these dagras we see that the noralzed backbone rate requred n the ABP schee s always saller than that n the BP schee at dfferent values of the atchng wndow as well as request arrval rate. Also, as the atchng wndow sze ncreases, the noralzed backbone rate decreases oralzed backbone rate Ω BP ABP oralzed backbone rate Ω BP ABP Request arrval rate [req/n] 4. a Request arrval rate[req/n]. b oralzed backbone rate Ω BP ABP Request arrval rate[req/n] c oralzed backbone rate Ω BP ABP Request arrval rate [req/n] Fg. 4. oralzed backbone rate versus request arrval rate at dfferent values of atchng wndow, b [n]. d

9 An Adatve Batched Patch achng Schee for Multeda Streang 7 Thrdly, we show n Fg.5 a ~ d the buffer requreent at roy to deal wth one eda obect for both schees ABP and BP wth resect to the atchng wndow sze and the request arrval rate. As the atchng wndow sze ncreases, the buffer requreent also ncreases. Moreover, under the sae condtons, both of these schees consue alost the sae buffers at roy, esecally n the hgh request arrval rate. Ths evdence ndcates that ABP schee archves the lower bandwdth savng than the BP schee, whle t does not consue uch ore buffer sze. Average buffer occuancy [MB] 9 8 BP APB Average buffer occuancy [MB] 9 BP ABP Average buffer occuancy [MB] Request arrval rate [req/n] 4 a BP ABP Request arrval rate [req/n] c Average buffer occuancy [MB] Request arrval rate [req/n] b BP ABP Request Arrval rate [req/n] Fg. 5. Average buffer occuancy at roy versus request arrval rate at dfferent values of atchng wndow, b [n]. d oralzed backbone rate Ω 6 ABP schee 5 λ 8 req/ n, b n 4 λ.5 req/n, b n λ 8 req/ n, b n Patchng wndow sze [n] Fg. 6. oralzed backbone rate versus atchng wndows sze. Fnally, Fg.6 shows the evoluton of the noralzed backbone rate Ω versus the duraton of the atchng wndows under dfferent request arrval rate and the batchng nterval by adotng ABP schee. We clearly fnd that the noralzed backbone

10 7 Shaohua Qn et al. rate ay no longer ehbt a nu value for the atchng wndow duraton wthn T. Moreover, the longer the duraton of atchng wndow, the hgher buffer sze requred at the roy. Accordngly, n ractce the ntal value of the atchng wndow can be deterned usng the eresson n lterature [], afterwards, we let the atchng wndow sze to adatvely eand or shorten n ters of request arrval rate. Intutvely, f all batches durng the duraton of the strea have no-zero requests, ths eda obect s really very oular and we ought to eand the atchng wndow n order to uch cache ths entre obect at roy and not have to request fro the server. Wth such a dynacal control of atchng wndow, t nstructs the roy to leent an otal cache for each eda obect, thereby achevng the better tradeoff between backbone bandwdth and storage requreents. 5 onclusons and Ongong Work In ths aer, we roosed an adatve batched atch cachng schee that onts server schedulng and roy cachng aed at reducng the bandwdth streaed fro the server. We forulate the on-deanded nubers of noralzed backbone transsson rate for consderng a artcular streang eda obect. oared wth the tradtonal batched atch-cachng schee, the roosed schee acheves uch ore savngs of backbone bandwdth by adatve re-cachng the atch data fro full strea. In addton, the adatablty of the roosed schee kees on very well wthn wde range of request arrval rate. The nuercal results show that the adatve batched atch cachng s a hghly effcent ethod that allevates bottlenecks for the delvery of streang eda obects. For slcty of eoston, we gnore network roagaton latency throughout the aer. ote that our schee can be easly adated to the scenaro when the network roagaton latency along server-roy ath s not gnorable. In order to hde the transsson delay for a streang eda obect fro the server, the roy cache has to be allocated to accoodate a ref for each eda obect. We are currently nvestgatng the trade-offs between bandwdth reducton and buffer occuancy at roy. We are also elorng the scenaros based on ABP where the roes can cooerate. References. A. Dan, D. Stara, P. Shahabuddn: Schedulng olces for an on-deand vdeo server wth batchng. In Proc. AM Multeda, San Francsco, alforna, K. A. Hua,Y. a, S. Sheu: Patchng: A ultcast technque for true vdeo-on-deand servces, n Proc. AM Multeda, Brtstol UK, P. P. Whte, J. rowcroft: Otzed batch atchng wth classes of servce, AM ouncatons Revew, Vol., o.4, 4. Y.a, K. Hua, K.Vu: Otzng Patchng Perforance. In roc. of AM/SPIE Multeda outng and etworkng, O.Verscheure,.Verkatraan, P. Froassard, L. An: Jont server schedulng and roy cachng for vdeo delvery. outer ouncatons, Vol.5, o. 4, Venkatraan, O. Verscheure, P. Frossard, K. W. Lee: Otal roy anageent for ulteda streang n content dstrbuton networks. In roc. of AM OSSDAV, Ma Beach, FL, USA, May 47 54

11 An Adatve Batched Patch achng Schee for Multeda Streang 7 7. S. Sen, J. Reford, D. Towsley: Proy ref cachng for ulteda steas. In roc. of IEEE IFOOM 99, ew York, USA, Pascal Frossard, Olver Verscheure: Batched atch cachng for streang eda. IEEE ouncatons Letters, Vol.6, o.4,, S.-H. Gary han, Fouad Tobag: Dstrbuted servers archtecture for networked vdeo servces. IEEE/AM Trans. on etworkng, Vol.9, o., 5 6. B. Wang, S. Sen, M. Adler, D. Towsley: Otal roy cache allocaton for effcent streang eda dstrbuton. IEEE Trans. on Multeda, Vol.6, o., D. Eager, M. Vernon, J. Zahoran: Mnzng Bandwdth Requreents for On-Deand Data Delvery. IEEE Trans. on Knowledge and Data Engneerng, Vol., o. 5, K. Wu, P. S. Yu, J. Wolf: Segent-based roy cachng of ulteda streas. In Proc. of WWW, Hong Kong, ay S. hen, B. Shen, S. Wee, X. Zhang: Adatve and lazy segentaton based roy cachng for steang eda delvery. In roc. of AM OSSDAV, Monterey, A, 4. S. hen, B. Shen, S. Wee, X. Zhang: Investgatng erforance nsghts of segent-based roy cachng of streang eda strateges. In roc. of MM 4, San, A,

IEEE Distributed Coordination Function(DCF): Analysis and Enhancement *

IEEE Distributed Coordination Function(DCF): Analysis and Enhancement * IEEE 802. Dstrbuted Coordnaton Functon(DCF): Analyss and Enhanceent * Hatao Wu, Shduan Cheng, Yong Peng, Keng Long, Jan Ma 2 Natonal Key Lab of Swtchng Technology and Telecouncaton Networks, P.O.Box 206,

More information

Delay Analysis of Different Backoff Algorithms in IEEE

Delay Analysis of Different Backoff Algorithms in IEEE Delay Analyss of Dfferent Backoff Algorths n IEEE 82. Ivan N. Vukovc otorola Inc., 44 W. Sure Dr., Arlngton Heghts, IL, 64 USA, Ivan.Vukovc@otorola.co, (847) 632-5963, fax (847) 435-997 Abstract - In ths

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

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

Introduction. Leslie Lamports Time, Clocks & the Ordering of Events in a Distributed System. Overview. Introduction Concepts: Time

Introduction. Leslie Lamports Time, Clocks & the Ordering of Events in a Distributed System. Overview. Introduction Concepts: Time Lesle Laports e, locks & the Orderng of Events n a Dstrbuted Syste Joseph Sprng Departent of oputer Scence Dstrbuted Systes and Securty Overvew Introducton he artal Orderng Logcal locks Orderng the Events

More information

Access Delay Analysis of IEEE DCF in the Presence of Hidden Stations

Access Delay Analysis of IEEE DCF in the Presence of Hidden Stations Access Delay Analyss of IEEE 82. DCF n the Presence of Hdden tatons Fu-Y Hung and Ivan Marsc CAIP Center, ECE Deartent, Rutgers Unversty Pscataway, NJ 8854-888 {fuyhung, arsc}@ca.rutgers.edu Abstract In

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

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

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

More information

Performance Evaluation of Multicast Video Streaming via P2P Networking

Performance Evaluation of Multicast Video Streaming via P2P Networking Secal Issue of Internatonal Journal of Comuter Alcatons (0975 8887) on Electroncs, Informaton and Communcaton Engneerng - ICEICE o.4, Dec 20 erformance Evaluaton of Multcast Vdeo Streamng va 2 etworkng

More information

ALM-FastReplica: Optimizing the Reliable Distribution of Large Files within CDNs

ALM-FastReplica: Optimizing the Reliable Distribution of Large Files within CDNs ALM-FastReplca: Optzng the Relable Dstrbuton of Large Fles wthn CDNs Ludla Cherkasova Internet Systes and Storage Laboratory HP Laboratores Palo Alto HPL-005-64 Aprl 4, 005* E-al: cherkasova@hpl.hp.co

More information

On-line Scheduling Algorithm with Precedence Constraint in Embeded Real-time System

On-line Scheduling Algorithm with Precedence Constraint in Embeded Real-time System 00 rd Internatonal Conference on Coputer and Electrcal Engneerng (ICCEE 00 IPCSIT vol (0 (0 IACSIT Press, Sngapore DOI: 077/IPCSIT0VNo80 On-lne Schedulng Algorth wth Precedence Constrant n Ebeded Real-te

More information

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation College of Engneerng and Coputer Scence Mechancal Engneerng Departent Mechancal Engneerng 309 Nuercal Analyss of Engneerng Systes Sprng 04 Nuber: 537 Instructor: Larry Caretto Solutons to Prograng Assgnent

More information

Optimization Methods: Integer Programming Integer Linear Programming 1. Module 7 Lecture Notes 1. Integer Linear Programming

Optimization Methods: Integer Programming Integer Linear Programming 1. Module 7 Lecture Notes 1. Integer Linear Programming Optzaton Methods: Integer Prograng Integer Lnear Prograng Module Lecture Notes Integer Lnear Prograng Introducton In all the prevous lectures n lnear prograng dscussed so far, the desgn varables consdered

More information

Keywords: Cloud Computing, Resource Allocation, Queueing Theory, Performance Measures.

Keywords: Cloud Computing, Resource Allocation, Queueing Theory, Performance Measures. Volume, Issue 9, Setember ISSN: 77 8X Internatonal Journal of Advanced Research n Comuter Scence and Software Engneerng Research Paer Avalable onlne at: wwwjarcssecom Resource Allocaton n Cloud Comutng

More information

Shared Running Buffer Based Proxy Caching of Streaming Sessions

Shared Running Buffer Based Proxy Caching of Streaming Sessions Shared Runnng Buffer Based Proxy Cachng of Streamng Sessons Songqng Chen, Bo Shen, Yong Yan, Sujoy Basu Moble and Meda Systems Laboratory HP Laboratores Palo Alto HPL-23-47 March th, 23* E-mal: sqchen@cs.wm.edu,

More information

THE CONDENSED FUZZY K-NEAREST NEIGHBOR RULE BASED ON SAMPLE FUZZY ENTROPY

THE CONDENSED FUZZY K-NEAREST NEIGHBOR RULE BASED ON SAMPLE FUZZY ENTROPY Proceedngs of the 20 Internatonal Conference on Machne Learnng and Cybernetcs, Guln, 0-3 July, 20 THE CONDENSED FUZZY K-NEAREST NEIGHBOR RULE BASED ON SAMPLE FUZZY ENTROPY JUN-HAI ZHAI, NA LI, MENG-YAO

More information

Equation Based Rate Control and Multiple Connections for Adaptive Video Streaming in Cellular Networks

Equation Based Rate Control and Multiple Connections for Adaptive Video Streaming in Cellular Networks Equaton Based Rate Control and Multple Connectons for Adaptve Vdeo Streang n Cellular Networks A. Mardanan Dehkord and V. Tabataba Vakl Abstract Rate control s an portant ssue for vdeo streang n cellular

More information

Handover Delay Estimation Method for IMS-Based Systems with Heterogeneous Access Networks

Handover Delay Estimation Method for IMS-Based Systems with Heterogeneous Access Networks Councatons 07; (): -7 http://www.scencepublshnggroup.co/j/co do: 0.8/j.co.0700. ISSN: 8-9 (Prnt); ISSN: 8-9 (Onlne) Handover Delay Estaton Method for IMS-Based Systes wth Heterogeneous Access Networks

More information

An Energy-Aware QoS Routing Protocol for Wireless Sensor Networks

An Energy-Aware QoS Routing Protocol for Wireless Sensor Networks An Energy-Aware QoS Routng Protocol for Wreless Sensor Networks Abstract Recent advances n wreless sensor networks have led to any new routng rotocols secfcally desgned for sensor networks. Alost all of

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

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

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

2016 International Conference on Sustainable Energy, Environment and Information Engineering (SEEIE 2016) ISBN:

2016 International Conference on Sustainable Energy, Environment and Information Engineering (SEEIE 2016) ISBN: 06 Internatonal Conference on Sustanable Energy, Envronent and Inforaton Engneerng (SEEIE 06) ISBN: 978--60595-337-3 A Study on IEEE 80. MAC Layer Msbehavor under Dfferent Back-off Algorths Trong Mnh HOANG,,

More information

A Scheduling Algorithm of Periodic Messages for Hard Real-time Communications on a Switched Ethernet

A Scheduling Algorithm of Periodic Messages for Hard Real-time Communications on a Switched Ethernet IJCSNS Internatonal Journal of Comuter Scence and Networ Securty VOL.6 No.5B May 26 A Schedulng Algorthm of Perodc Messages for Hard eal-tme Communcatons on a Swtched Ethernet Hee Chan Lee and Myung Kyun

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

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements Module 3: Element Propertes Lecture : Lagrange and Serendpty Elements 5 In last lecture note, the nterpolaton functons are derved on the bass of assumed polynomal from Pascal s trangle for the fled varable.

More information

Load Balancing Algorithm for Web Server Based on Weighted Minimal Connections

Load Balancing Algorithm for Web Server Based on Weighted Minimal Connections Journal of Web ystes and Applcatons (2017) Vol. 1, Nuuber 1 Clausus centfc Press, Canada Load Balancng Algorth for Web erver Based on Weghted Mnal Connectons Pan Zhu1, a, Jangxng Zhang 2,b College of Inforaton

More information

Multicast Tree Rearrangement to Recover Node Failures. in Overlay Multicast Networks

Multicast Tree Rearrangement to Recover Node Failures. in Overlay Multicast Networks Multcast Tree Rearrangeent to Recover Node Falures n Overlay Multcast Networks Hee K. Cho and Chae Y. Lee Dept. of Industral Engneerng, KAIST, 373-1 Kusung Dong, Taejon, Korea Abstract Overlay ultcast

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

An Adaptive Sleep Strategy for Energy Conservation in Wireless Sensor Networks

An Adaptive Sleep Strategy for Energy Conservation in Wireless Sensor Networks An Adaptve Sleep Strategy for Energy Conservaton n Wreless Sensor Networks Guseppe Anastas, Marco Cont, Maro D Francesco Abstract - In recent years, wreless sensor network deployents for real lfe applcatons

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

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 Unified Approach to Survivability of Connection-Oriented Networks

A Unified Approach to Survivability of Connection-Oriented Networks A Unfed Approach to Survvablty of Connecton-Orented Networs Krzysztof Walowa Char of Systes and Coputer Networs, Faculty of Electroncs, Wroclaw Unversty of Technology, Wybrzeze Wyspansego 27, 50-370 Wroclaw,

More information

An Efficient Fault-Tolerant Multi-Bus Data Scheduling Algorithm Based on Replication and Deallocation

An Efficient Fault-Tolerant Multi-Bus Data Scheduling Algorithm Based on Replication and Deallocation BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volue 16, No Sofa 016 Prnt ISSN: 1311-970; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-016-001 An Effcent Fault-Tolerant Mult-Bus Data

More information

Merging Results by Using Predicted Retrieval Effectiveness

Merging Results by Using Predicted Retrieval Effectiveness Mergng Results by Usng Predcted Retreval Effectveness Introducton Wen-Cheng Ln and Hsn-Hs Chen Departent of Coputer Scence and Inforaton Engneerng Natonal Tawan Unversty Tape, TAIWAN densln@nlg.cse.ntu.edu.tw;

More information

Generating Fuzzy Term Sets for Software Project Attributes using and Real Coded Genetic Algorithms

Generating Fuzzy Term Sets for Software Project Attributes using and Real Coded Genetic Algorithms Generatng Fuzzy Ter Sets for Software Proect Attrbutes usng Fuzzy C-Means C and Real Coded Genetc Algorths Al Idr, Ph.D., ENSIAS, Rabat Alan Abran, Ph.D., ETS, Montreal Azeddne Zah, FST, Fes Internatonal

More information

Zooming in Surrogate Optimization Using Convolute RBF. Masao Arakawa 1

Zooming in Surrogate Optimization Using Convolute RBF. Masao Arakawa 1 t World Congress on Structural and ultdsclnary Otsaton 7 t - t, June 5, Sydney Australa Zoong n Surrogate Otzaton Usng Convolute RBF asao Arakawa Kagawa Unversty, Takaatsu, JAPAN, arakawa@eng.kagawa-u.ac.j.

More information

Sums of exponential functions and their new fundamental properties

Sums of exponential functions and their new fundamental properties Sus of exonental functons and ther new fundaental roertes Yur K. Shestoaloff Abstract hs aer dscovers and roves the fundaental roertes of sus of exonental functon n the for of а heore that s stated as

More information

A New Scheduling Algorithm for Servers

A New Scheduling Algorithm for Servers A New Schedulng Algorth for Servers Nann Yao, Wenbn Yao, Shaobn Ca, and Jun N College of Coputer Scence and Technology, Harbn Engneerng Unversty, Harbn, Chna {yaonann, yaowenbn, cashaobn, nun}@hrbeu.edu.cn

More information

Algorithm for Computer Aided Design Curve Shape Form Generation of Knitting Patterns

Algorithm for Computer Aided Design Curve Shape Form Generation of Knitting Patterns Algorth for Couter Aded Desgn Curve Shae For Generaton of Knttng Patterns Elena Zahareva-Stoyanova Techncal Unversty of Gabrovo 4 H. Drat str. 500 Gabrovo, ulgara, hone +59 59 Abstract - The knttng ndustry

More information

Concurrent Apriori Data Mining Algorithms

Concurrent Apriori Data Mining Algorithms Concurrent Apror Data Mnng Algorthms Vassl Halatchev Department of Electrcal Engneerng and Computer Scence York Unversty, Toronto October 8, 2015 Outlne Why t s mportant Introducton to Assocaton Rule Mnng

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

1 Calculation and Analysis of Buffer

1 Calculation and Analysis of Buffer Sep. 5 Journal of Electronc Scence and Technology of Chna Vol.3 No.3 ` Calculaton and Analyss of Destnaton Buffer for ulteda Servce n ole Ad Hoc Network ZHOU Zhong, AO Yu-ng, JIANG Zh-qong. School of Councaton

More information

The ray density estimation of a CT system by a supervised learning algorithm

The ray density estimation of a CT system by a supervised learning algorithm Te ray densty estaton of a CT syste by a suervsed learnng algort Nae : Jongduk Baek Student ID : 5459 Toc y toc s to fnd te ray densty of a new CT syste by usng te learnng algort Background Snce te develoent

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

Learning-Based Top-N Selection Query Evaluation over Relational Databases

Learning-Based Top-N Selection Query Evaluation over Relational Databases Learnng-Based Top-N Selecton Query Evaluaton over Relatonal Databases Lang Zhu *, Wey Meng ** * School of Mathematcs and Computer Scence, Hebe Unversty, Baodng, Hebe 071002, Chna, zhu@mal.hbu.edu.cn **

More information

A FUZZY-LOGIC APPROACH FOR DEVELOPING VARIABLES CONTROL CHARTS AND PROCESS CAPABILITY INDICES UNDER LINGUISTIC MEASUREMENTS

A FUZZY-LOGIC APPROACH FOR DEVELOPING VARIABLES CONTROL CHARTS AND PROCESS CAPABILITY INDICES UNDER LINGUISTIC MEASUREMENTS A FUZZY-LOGIC APPROACH FOR DEVELOPING VARIABLES CONTROL CHARTS AND PROCESS CAPABILITY INDICES UNDER LINGUISTIC MEASUREMENTS Abbas Al-Refae, Areen Obadat 1, Ra H. Fouad 1, and Bassel Hanayneh 1 Deartent

More information

Support Vector Machines

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

More information

Efficient Caching of Video Content to an Architecture of Proxies according to a Frequency-Based Cache Management Policy

Efficient Caching of Video Content to an Architecture of Proxies according to a Frequency-Based Cache Management Policy Effcent Cachng of Vdeo Content to an Archtecture of Proxes accordng to a Frequency-Based Cache Management Polcy Anna Satsou, Mchael Pateraks Laboratory of Informaton and Comuter Networks Deartment of Electronc

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

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

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

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

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

Monte Carlo inference

Monte Carlo inference CS 3750 achne Learnng Lecture 0 onte Carlo nerence los Hauskrecht los@cs.ptt.edu 539 Sennott Square Iportance Saplng an approach or estatng the epectaton o a uncton relatve to soe dstrbuton target dstrbuton

More information

Scalable Download Protocols

Scalable Download Protocols Scalable Download Protocols A Thess Submtted to the College of Graduate Studes and Research In Partal Fulfllment of the Requrements For the Degree of Doctor of Phlosophy In the Department of Computer Scence

More information

Multi-Constraint Multi-Processor Resource Allocation

Multi-Constraint Multi-Processor Resource Allocation Mult-Constrant Mult-Processor Resource Allocaton Ar R. B. Behrouzan 1, Dp Goswa 1, Twan Basten 1,2, Marc Gelen 1, Had Alzadeh Ara 1 1 Endhoven Unversty of Technology, Endhoven, The Netherlands 2 TNO Ebedded

More information

Bayesian Networks: Independencies and Inference. What Independencies does a Bayes Net Model?

Bayesian Networks: Independencies and Inference. What Independencies does a Bayes Net Model? Bayesan Networks: Indeendences and Inference Scott Daves and Andrew Moore Note to other teachers and users of these sldes. Andrew and Scott would be delghted f you found ths source materal useful n gvng

More information

Pattern Classification of Back-Propagation Algorithm Using Exclusive Connecting Network

Pattern Classification of Back-Propagation Algorithm Using Exclusive Connecting Network World Acade of Scence, Engneerng and Technolog 36 7 Pattern Classfcaton of Bac-Propagaton Algorth Usng Eclusve Connectng Networ Insung Jung, and G-Na Wang Abstract The obectve of ths paper s to a desgn

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

A Base Station-Coordinated Contention Resolution for IEEE PMP Networks

A Base Station-Coordinated Contention Resolution for IEEE PMP Networks A Base Staton-Coordnated Contenton Resoluton for IEEE 802.6 PMP Networks Wenyan Lu, Weja Ja,2, Wenfeng Du, and Ldong Ln 2 School of Informaton Scence & Engneerng, Central South Unversty, Changsha, 40083,

More information

Scheduling Workflow Applications on the Heterogeneous Cloud Resources

Scheduling Workflow Applications on the Heterogeneous Cloud Resources Indan Journal of Scence and Technology, Vol 8(2, DOI: 0.7485/jst/205/v82/57984, June 205 ISSN (rnt : 0974-6846 ISSN (Onlne : 0974-5645 Schedulng Workflow Applcatons on the Heterogeneous Cloud Resources

More information

Hermite Splines in Lie Groups as Products of Geodesics

Hermite Splines in Lie Groups as Products of Geodesics Hermte Splnes n Le Groups as Products of Geodescs Ethan Eade Updated May 28, 2017 1 Introducton 1.1 Goal Ths document defnes a curve n the Le group G parametrzed by tme and by structural parameters n the

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

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

Color Image Segmentation Based on Adaptive Local Thresholds

Color Image Segmentation Based on Adaptive Local Thresholds Color Iage Segentaton Based on Adaptve Local Thresholds ETY NAVON, OFE MILLE *, AMI AVEBUCH School of Coputer Scence Tel-Avv Unversty, Tel-Avv, 69978, Israel E-Mal * : llero@post.tau.ac.l Fax nuber: 97-3-916084

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

Broadcast Time Synchronization Algorithm for Wireless Sensor Networks Chaonong Xu 1)2)3), Lei Zhao 1)2), Yongjun Xu 1)2) and Xiaowei Li 1)2)

Broadcast Time Synchronization Algorithm for Wireless Sensor Networks Chaonong Xu 1)2)3), Lei Zhao 1)2), Yongjun Xu 1)2) and Xiaowei Li 1)2) Broadcast Tme Synchronzaton Algorthm for Wreless Sensor Networs Chaonong Xu )2)3), Le Zhao )2), Yongun Xu )2) and Xaowe L )2) ) Key Laboratory of Comuter Archtecture, Insttute of Comutng Technology Chnese

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

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

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

ARTICLE IN PRESS. Signal Processing: Image Communication

ARTICLE IN PRESS. Signal Processing: Image Communication Sgnal Processng: Image Communcaton 23 (2008) 754 768 Contents lsts avalable at ScenceDrect Sgnal Processng: Image Communcaton journal homepage: www.elsever.com/locate/mage Dstrbuted meda rate allocaton

More information

A Network Bandwidth Computation Technique for IP Storage with QoS Guarantees

A Network Bandwidth Computation Technique for IP Storage with QoS Guarantees A Network Bandwdth Computaton Technque for IP Storage wth QoS Guarantees Young Jn Nam 1, Junkl Ryu 1, Chank Park 1, and Jong Suk Ahn 2 1 Department of Computer Scence and Engneerng Pohang Unversty of Scence

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

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 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

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

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

126 Int. J. Ad Hoc and Ubiquitous Computing, Vol. 1, No. 3, Djamel Djenouri*

126 Int. J. Ad Hoc and Ubiquitous Computing, Vol. 1, No. 3, Djamel Djenouri* 126 Int. J. Ad Hoc and Ubqutous Coputng, Vol. 1, No. 3, 2006 New power-aware routng protocol for oble ad hoc networks Djael Djenour* Basc Software Laboratory, CERIST Center of Research, Algers, Algera

More information

Energy-aware Delay-Constrained Routing in Wireless Sensor Networks

Energy-aware Delay-Constrained Routing in Wireless Sensor Networks Energy-aware Delay-Constraned Routng n Wreless Sensor Networks Keal Akkaya and Mohaed Youns Departent of Coputer Scence and Electrcal Engneerng Unversty of Maryland Baltore County, Baltore, MD 21250 {keal1,

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

Harfoush, Bestavros, and Byers, Robust Identfcaton of Shared Losses Usng End-to-End Uncast Probes 2 Introducton One of the defnng prncples of the netw

Harfoush, Bestavros, and Byers, Robust Identfcaton of Shared Losses Usng End-to-End Uncast Probes 2 Introducton One of the defnng prncples of the netw Robust Identfcaton of Shared Losses Usng End-to-End Uncast Probes Λ Khaled Harfoush Azer Bestavros John Byers harfoush@cs.bu.edu best@cs.bu.edu byers@cs.bu.edu Computer Scence Department Boston Unversty

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

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

A study of Adaptive Replication Technique in routing time-constrained messages (VoIP) in MANET

A study of Adaptive Replication Technique in routing time-constrained messages (VoIP) in MANET A study of Adaptve Replcaton Technque n routng te-constraned essages (VoIP) n MANET SWATI SAXENA Research Scholar AIM & ACT Banasthal Vdyapth Banasthal, (Ra.) Dr. MADHAVI SINHA Asst. Prof. (HOD) Dept.

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

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

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

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

More information

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

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1)

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1) Secton 1.2 Subsets and the Boolean operatons on sets If every element of the set A s an element of the set B, we say that A s a subset of B, or that A s contaned n B, or that B contans A, and we wrte A

More information

Efficient QoS Provisioning at the MAC Layer in Heterogeneous Wireless Sensor Networks

Efficient QoS Provisioning at the MAC Layer in Heterogeneous Wireless Sensor Networks Effcent QoS Provsonng at the MAC Layer n Heterogeneous Wreless Sensor Networks M.Soul a,, A.Bouabdallah a, A.E.Kamal b a UMR CNRS 7253 HeuDaSyC, Unversté de Technologe de Compègne, Compègne Cedex F-625,

More information

Routing Time-Constrained Traffic in Wireless Sensor Networks

Routing Time-Constrained Traffic in Wireless Sensor Networks Routng Te-Constraned Traffc n Wreless Sensor Networks Keal Akkaya and Mohaed Youns Departent of Coputer Scence and Electrcal Engneerng Unversty of Maryland, Baltore County Baltore, MD 2250 keal youns@cs.ubc.edu

More information

Internet Traffic Managers

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

More information

Journal of Engineering Science and Technology Review 10 (5) (2017) Research Article

Journal of Engineering Science and Technology Review 10 (5) (2017) Research Article Jestr Journal of Engneerng Scence and Technology Revew 0 (5) (07) 4-49 Research Artcle Study on Fault Tolerance Method n Cloud Platfor based on Worload Consoldaton Model of Vrtual Machne Zhxn L,,*, Le

More information

Gateway Algorithm for Fair Bandwidth Sharing

Gateway Algorithm for Fair Bandwidth Sharing Algorm for Far Bandwd Sharng We Y, Rupnder Makkar, Ioanns Lambadars Department of System and Computer Engneerng Carleton Unversty 5 Colonel By Dr., Ottawa, ON KS 5B6, Canada {wy, rup, oanns}@sce.carleton.ca

More information

User Behavior Recognition based on Clustering for the Smart Home

User Behavior Recognition based on Clustering for the Smart Home 3rd WSEAS Internatonal Conference on REMOTE SENSING, Vence, Italy, Noveber 2-23, 2007 52 User Behavor Recognton based on Clusterng for the Sart Hoe WOOYONG CHUNG, JAEHUN LEE, SUKHYUN YUN, SOOHAN KIM* AND

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

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

Advanced LEACH: A Static Clustering-based Heteroneous Routing Protocol for WSNs

Advanced LEACH: A Static Clustering-based Heteroneous Routing Protocol for WSNs Advanced LEACH: A Statc Clusterng-based Heteroneous Routng Protocol for WSNs A. Iqbal 1, M. Akbar 1, N. Javad 1, S. H. Bouk 1, M. Ilah 1, R. D. Khan 2 1 COMSATS Insttute of Informaton Technology, Islamabad,

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge Detection in Noisy Images Using the Support Vector Machines Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona

More information