An improved evolutlonary approach for the cluster allocation problem

In a distributed system, consisting of a set of interconnected local area networks, users migrate to different machines, users invoke different programs and users and programs need distinct data files to satisfy their expectations. Consequently optimal allocation of parallel program tasks can increa...

Descripción completa

Detalles Bibliográficos
Autores principales: Apolloni, Rubén, Molina, Silvia, Gallard, Raúl Hector
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 1999
Materias:
Ciencias Informáticas
ARTIFICIAL INTELLIGENCE
cluster allocation problem
Clustering
improved evolutlonary
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/22226
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-22226
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
ARTIFICIAL INTELLIGENCE
cluster allocation problem
Clustering
improved evolutlonary
spellingShingle Ciencias Informáticas
ARTIFICIAL INTELLIGENCE
cluster allocation problem
Clustering
improved evolutlonary
Apolloni, Rubén
Molina, Silvia
Gallard, Raúl Hector
An improved evolutlonary approach for the cluster allocation problem
topic_facet Ciencias Informáticas
ARTIFICIAL INTELLIGENCE
cluster allocation problem
Clustering
improved evolutlonary
description In a distributed system, consisting of a set of interconnected local area networks, users migrate to different machines, users invoke different programs and users and programs need distinct data files to satisfy their expectations. Consequently optimal allocation of parallel program tasks can increase system performance as results of traffic cost reducti9n between clusters2• The problem of allocating a program in a particular system node can be divided into two subproblems: i) allocate the program in a cluster such that traffic costs are minimized and ii) within a particular cluster choose the node following sorne load balancing criteria [5]. To solve subproblem i), in 1992 U. M. Borghoff [2] proposed the Individual Program Execution Location Algorithm IPELA, where essentially giving a distribution of data files the best allocation for program execution, minimizing the expected intercluster traffic, is searched. The algorithm uses diverse input data such us the cost for starting a program at sorne node [10], thedependencies between program and data files [1], separated read and write access costs [9], the impact of l/O activities on the communication costs [8] and the allocation of program and data files [3]. . As the number of possible allocations induce high complexity and the model could not be solved too optimality Borghoff reduced the number of combinations by limiting the number of data file replicas and looking for those combinations where the relevant file sets's allocation is varied. This approach reduced complexity. Nevertheless running ¡PELA implied evaluation of each solution in a large problem space.
format Objeto de conferencia
Objeto de conferencia
author Apolloni, Rubén
Molina, Silvia
Gallard, Raúl Hector
author_facet Apolloni, Rubén
Molina, Silvia
Gallard, Raúl Hector
author_sort Apolloni, Rubén
title An improved evolutlonary approach for the cluster allocation problem
title_short An improved evolutlonary approach for the cluster allocation problem
title_full An improved evolutlonary approach for the cluster allocation problem
title_fullStr An improved evolutlonary approach for the cluster allocation problem
title_full_unstemmed An improved evolutlonary approach for the cluster allocation problem
title_sort improved evolutlonary approach for the cluster allocation problem
publishDate 1999
url http://sedici.unlp.edu.ar/handle/10915/22226
work_keys_str_mv AT apolloniruben animprovedevolutlonaryapproachfortheclusterallocationproblem
AT molinasilvia animprovedevolutlonaryapproachfortheclusterallocationproblem
AT gallardraulhector animprovedevolutlonaryapproachfortheclusterallocationproblem
AT apolloniruben improvedevolutlonaryapproachfortheclusterallocationproblem
AT molinasilvia improvedevolutlonaryapproachfortheclusterallocationproblem
AT gallardraulhector improvedevolutlonaryapproachfortheclusterallocationproblem
bdutipo_str Repositorios
_version_ 1764820465377869825

Ejemplares similares