Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements
Main Author: | |
---|---|
Publication Date: | 2019 |
Other Authors: | , , , , |
Format: | Article |
Language: | eng |
Source: | Repositório Institucional da Udesc |
dARK ID: | ark:/33523/0013000006f50 |
Download full: | https://repositorio.udesc.br/handle/UDESC/5762 |
Summary: | Copyright © 2019 Inderscience Enterprises Ltd.The diversity of services, prices, and geographical footprints has turned the clouds into a complex and heterogeneous environment. Moreover, the survivability and reliability aspects are often disregarded by tenants, eventually resulting in heavy losses due to unavailability of services that are hosted on Virtual Infrastructures (VIs). We present an alternative to improve Vis’ survivability and reliability, which considers the use of replicas and the spreading of virtual resources atop providers, regions, and zones. We formulate the VI allocation with survivability and reliability requirements as a mixed integer program, and three strategies to solve the formulation are proposed. First, the binary constraints are relaxed to obtain a Linear Program (LP), and the LP solution is given as input for the simulated annealing technique. Then, two GPU-accelerated algorithms are proposed to speed up the allocation of large-scale scenarios. Simulation with different reliability requests indicate an increasing in survivability without inflating costs. |
id |
UDESC-2_49a43c680abb1b539e95e1e82dfe070b |
---|---|
oai_identifier_str |
oai:repositorio.udesc.br:UDESC/5762 |
network_acronym_str |
UDESC-2 |
network_name_str |
Repositório Institucional da Udesc |
repository_id_str |
6391 |
spelling |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirementsCopyright © 2019 Inderscience Enterprises Ltd.The diversity of services, prices, and geographical footprints has turned the clouds into a complex and heterogeneous environment. Moreover, the survivability and reliability aspects are often disregarded by tenants, eventually resulting in heavy losses due to unavailability of services that are hosted on Virtual Infrastructures (VIs). We present an alternative to improve Vis’ survivability and reliability, which considers the use of replicas and the spreading of virtual resources atop providers, regions, and zones. We formulate the VI allocation with survivability and reliability requirements as a mixed integer program, and three strategies to solve the formulation are proposed. First, the binary constraints are relaxed to obtain a Linear Program (LP), and the LP solution is given as input for the simulated annealing technique. Then, two GPU-accelerated algorithms are proposed to speed up the allocation of large-scale scenarios. Simulation with different reliability requests indicate an increasing in survivability without inflating costs.2024-12-06T12:40:38Z2019info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlep. 708 - 7231741-848810.1504/IJGUC.2019.102752https://repositorio.udesc.br/handle/UDESC/5762ark:/33523/0013000006f50International Journal of Grid and Utility Computing106Raugust A.S.*Loch W.J.*Rodrigo De Souza F.Pillon, Mauricio AronneMiers, Charles ChristianKoslovski, Guilherme Piegasengreponame:Repositório Institucional da Udescinstname:Universidade do Estado de Santa Catarina (UDESC)instacron:UDESCinfo:eu-repo/semantics/openAccess2024-12-07T20:48:43Zoai:repositorio.udesc.br:UDESC/5762Biblioteca Digital de Teses e Dissertaçõeshttps://pergamumweb.udesc.br/biblioteca/index.phpPRIhttps://repositorio-api.udesc.br/server/oai/requestri@udesc.bropendoar:63912024-12-07T20:48:43Repositório Institucional da Udesc - Universidade do Estado de Santa Catarina (UDESC)false |
dc.title.none.fl_str_mv |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
title |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
spellingShingle |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements Raugust A.S.* |
title_short |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
title_full |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
title_fullStr |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
title_full_unstemmed |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
title_sort |
Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements |
author |
Raugust A.S.* |
author_facet |
Raugust A.S.* Loch W.J.* Rodrigo De Souza F. Pillon, Mauricio Aronne Miers, Charles Christian Koslovski, Guilherme Piegas |
author_role |
author |
author2 |
Loch W.J.* Rodrigo De Souza F. Pillon, Mauricio Aronne Miers, Charles Christian Koslovski, Guilherme Piegas |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Raugust A.S.* Loch W.J.* Rodrigo De Souza F. Pillon, Mauricio Aronne Miers, Charles Christian Koslovski, Guilherme Piegas |
description |
Copyright © 2019 Inderscience Enterprises Ltd.The diversity of services, prices, and geographical footprints has turned the clouds into a complex and heterogeneous environment. Moreover, the survivability and reliability aspects are often disregarded by tenants, eventually resulting in heavy losses due to unavailability of services that are hosted on Virtual Infrastructures (VIs). We present an alternative to improve Vis’ survivability and reliability, which considers the use of replicas and the spreading of virtual resources atop providers, regions, and zones. We formulate the VI allocation with survivability and reliability requirements as a mixed integer program, and three strategies to solve the formulation are proposed. First, the binary constraints are relaxed to obtain a Linear Program (LP), and the LP solution is given as input for the simulated annealing technique. Then, two GPU-accelerated algorithms are proposed to speed up the allocation of large-scale scenarios. Simulation with different reliability requests indicate an increasing in survivability without inflating costs. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019 2024-12-06T12:40:38Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
1741-8488 10.1504/IJGUC.2019.102752 https://repositorio.udesc.br/handle/UDESC/5762 |
dc.identifier.dark.fl_str_mv |
ark:/33523/0013000006f50 |
identifier_str_mv |
1741-8488 10.1504/IJGUC.2019.102752 ark:/33523/0013000006f50 |
url |
https://repositorio.udesc.br/handle/UDESC/5762 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
International Journal of Grid and Utility Computing 10 6 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
p. 708 - 723 |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da Udesc instname:Universidade do Estado de Santa Catarina (UDESC) instacron:UDESC |
instname_str |
Universidade do Estado de Santa Catarina (UDESC) |
instacron_str |
UDESC |
institution |
UDESC |
reponame_str |
Repositório Institucional da Udesc |
collection |
Repositório Institucional da Udesc |
repository.name.fl_str_mv |
Repositório Institucional da Udesc - Universidade do Estado de Santa Catarina (UDESC) |
repository.mail.fl_str_mv |
ri@udesc.br |
_version_ |
1842258093221609472 |