MASSIVE SIMULATIONS USING MAPREDUCE MODEL

MASSIVE SIMULATIONS USING MAPREDUCE MODEL

In the last few years cloud computing is growing as a dominant solution for large scale numerical problems. It is based on MapReduce programming model, which provides high scalability and flexibility, but also optimizes costs of computing infrastructure. This paper studies feasibility of MapReduce...

Full description

Bibliographic Details
Main Authors: Artur Krupa, Bartosz Sawicki
Format: Article
Language:English
Published: Lublin University of Technology 2015-10-01
Series:Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
Subjects:
mapreduce
cloud computing
platform performance
hadoop
Online Access:https://ph.pollub.pl/index.php/iapgos/article/view/1100
id doaj-6ac9f83f4fbe47eea598cb56f90409e9
record_format Article
spelling doaj-6ac9f83f4fbe47eea598cb56f90409e92020-11-25T03:14:04ZengLublin University of TechnologyInformatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska 2083-01572391-67612015-10-015410.5604/20830157.1176574MASSIVE SIMULATIONS USING MAPREDUCE MODELArtur Krupa0Bartosz Sawicki1Politechnika Warszawska, Instytut Elektrotechniki Teoretycznej i Systemów Informacyjno-PomiarowychPolitechnika Warszawska, Instytut Elektrotechniki Teoretycznej i Systemów Informacyjno-Pomiarowych In the last few years cloud computing is growing as a dominant solution for large scale numerical problems. It is based on MapReduce programming model, which provides high scalability and flexibility, but also optimizes costs of computing infrastructure. This paper studies feasibility of MapReduce model for scientific problems consisting of many independent simulations. Experiment based on variability analysis for simple electro­magnetic problem with over 10,000 scenarios proves that platform has nearly linear scalability with over 80% of theoretical maximum performance. https://ph.pollub.pl/index.php/iapgos/article/view/1100mapreducecloud computingplatform performancehadoop
collection DOAJ
language English
format Article
sources DOAJ
author Artur Krupa
Bartosz Sawicki
spellingShingle Artur Krupa
Bartosz Sawicki
MASSIVE SIMULATIONS USING MAPREDUCE MODEL
Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
mapreduce
cloud computing
platform performance
hadoop
author_facet Artur Krupa
Bartosz Sawicki
author_sort Artur Krupa
title MASSIVE SIMULATIONS USING MAPREDUCE MODEL
title_short MASSIVE SIMULATIONS USING MAPREDUCE MODEL
title_full MASSIVE SIMULATIONS USING MAPREDUCE MODEL
title_fullStr MASSIVE SIMULATIONS USING MAPREDUCE MODEL
title_full_unstemmed MASSIVE SIMULATIONS USING MAPREDUCE MODEL
title_sort massive simulations using mapreduce model
publisher Lublin University of Technology
series Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
issn 2083-0157
2391-6761
publishDate 2015-10-01
description In the last few years cloud computing is growing as a dominant solution for large scale numerical problems. It is based on MapReduce programming model, which provides high scalability and flexibility, but also optimizes costs of computing infrastructure. This paper studies feasibility of MapReduce model for scientific problems consisting of many independent simulations. Experiment based on variability analysis for simple electro­magnetic problem with over 10,000 scenarios proves that platform has nearly linear scalability with over 80% of theoretical maximum performance.
topic mapreduce
cloud computing
platform performance
hadoop
url https://ph.pollub.pl/index.php/iapgos/article/view/1100
work_keys_str_mv AT arturkrupa massivesimulationsusingmapreducemodel
AT bartoszsawicki massivesimulationsusingmapreducemodel
_version_ 1724644647941177344

Similar Items