Ítem
Acceso Abierto

Beyond the mean in fork-join queues: efficient approximation for response-time tails

Mostrar el registro sencillo de la publicación
dc.creatorQiu, Zhanspa
dc.creatorPérez, Juan F.spa
dc.creatorHarrison, Peter G.spa
dc.date.accessioned2020-08-19T14:41:37Z
dc.date.available2020-08-19T14:41:37Z
dc.date.created2015-09spa
dc.description.abstractFork-join queues are natural models for various computer and communications systems that involve parallel multitasking and the splitting and resynchronizing of data, such as parallel computing, query processing in distributed databases, and parallel disk access. Job response time in a fork-join queue is a critical performance indicator but its exact analysis is challenging. We introduce a stochastic model for -node homogeneous fork-join queues () that focuses on the difference in length between any node-queue and the shortest one, truncating the state space such that the maximum difference is at most a constant . Whilst most previous methods focus on the mean response time, our model is also able to evaluate the response time distribution, as well as accommodating phase-type processing times and Markovian arrival processes. In order to tackle scenarios with high loads, which require a large value of to provide sufficient accuracy, we develop an efficient algorithm using matrix-analytic methods. Tests against simulation show that the proposed model yields accurate results for 2-node fork-join queues. As the model becomes numerically intractable for large values of , we further propose an approximate approach, based on properties of order statistics and extreme values. The approximation gives a high degree of accuracy on response time tails, and has the advantage of being efficient and scalable, requiring only the analytical results for a single-node and 2-node fork-join queues, which we obtain with the aforementioned matrix-analytic model. Comparison with simulation results shows that our approximation yields good fits for the tails, even in very large cases with general processing and inter-arrival times.eng
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.1016/j.peva.2015.06.007
dc.identifier.issnISSN: 0166-5316
dc.identifier.issnEISSN: 1872-745X
dc.identifier.urihttps://repository.urosario.edu.co/handle/10336/27286
dc.language.isoengspa
dc.publisherElsevierspa
dc.relation.citationEndPage116
dc.relation.citationStartPage99
dc.relation.citationTitlePerformance Evaluation
dc.relation.citationVolumeVol. 91
dc.relation.ispartofPerformance Evaluation, ISSN: 0166-5316;EISSN: 1872-745X, Vol.91 (2015); pp. 99-116spa
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S0166531615000553spa
dc.rights.accesRightsinfo:eu-repo/semantics/openAccess
dc.rights.accesoAbierto (Texto Completo)spa
dc.sourcePerformance Evaluationspa
dc.source.instnameinstname:Universidad del Rosario
dc.source.reponamereponame:Repositorio Institucional EdocUR
dc.subject.keywordFork-join queuesspa
dc.subject.keywordResponse-time distributionspa
dc.subject.keywordMatrix-analytic methodsspa
dc.subject.keywordOrder statisticsspa
dc.titleBeyond the mean in fork-join queues: efficient approximation for response-time tailsspa
dc.title.TranslatedTitleMás allá de la media en colas de unión en bifurcación: aproximación eficiente para colas de tiempo de respuestaspa
dc.typearticleeng
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersion
dc.type.spaArtículospa
Archivos
Bloque original
Mostrando1 - 1 de 1
Miniatura
Nombre:
1-s2-0-S0166531615000553-main.pdf
Tamaño:
710.51 KB
Formato:
Adobe Portable Document Format
Descripción:
Descargar
Colecciones
Artículos