{"id":"https://openalex.org/W2014767141","doi":"https://doi.org/10.1109/hpcs.2010.5547140","title":"Using replication and checkpointing for reliable task management in computational Grids","display_name":"Using replication and checkpointing for reliable task management in computational Grids","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2014767141","doi":"https://doi.org/10.1109/hpcs.2010.5547140","mag":"2014767141"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs.2010.5547140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs.2010.5547140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing &amp; Simulation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102068461","display_name":"Sangho Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sangho Yi","raw_affiliation_strings":["INRIA, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087185379","display_name":"Derrick Kondo","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Derrick Kondo","raw_affiliation_strings":["INRIA, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054761941","display_name":"Bongjae Kim","orcid":"https://orcid.org/0000-0002-4310-6687"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bongjae Kim","raw_affiliation_strings":["Seoul National University, South Korea","Seoul National University (Korea)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University (Korea)","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020079006","display_name":"Geunyoung Park","orcid":"https://orcid.org/0000-0002-6944-8757"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geunyoung Park","raw_affiliation_strings":["Seoul National University, South Korea","Seoul National University (Korea)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University (Korea)","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077905149","display_name":"Yookun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yookun Cho","raw_affiliation_strings":["Seoul National University, South Korea","Seoul National University (Korea)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University (Korea)","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"125","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8441377878189087},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.7632558345794678},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7497149705886841},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7426567077636719},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7037560939788818},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6979357004165649},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.6598517894744873},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.570266604423523},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.5164730548858643},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.49661093950271606},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46146494150161743},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4543910622596741},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41863542795181274},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13231003284454346},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09605753421783447},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07932719588279724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441377878189087},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.7632558345794678},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7497149705886841},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7426567077636719},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7037560939788818},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6979357004165649},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.6598517894744873},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.570266604423523},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.5164730548858643},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.49661093950271606},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46146494150161743},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4543910622596741},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41863542795181274},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13231003284454346},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09605753421783447},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07932719588279724},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcs.2010.5547140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs.2010.5547140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing &amp; Simulation","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00788867v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00788867","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on High Performance Computing & Simulation (HPCS), 2010, Caen, France. pp.125-131, &#x27E8;10.1109/HPCS.2010.5547140&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W327467635","https://openalex.org/W1480341372","https://openalex.org/W1558516248","https://openalex.org/W1763890264","https://openalex.org/W1974489066","https://openalex.org/W2007397415","https://openalex.org/W2019208548","https://openalex.org/W2055467946","https://openalex.org/W2100970777","https://openalex.org/W2103342689","https://openalex.org/W2116680417","https://openalex.org/W2124043382","https://openalex.org/W2130542946","https://openalex.org/W2131629153","https://openalex.org/W2135377267","https://openalex.org/W2140915526","https://openalex.org/W3196112465","https://openalex.org/W6611243341"],"related_works":["https://openalex.org/W2153096481","https://openalex.org/W2148616436","https://openalex.org/W2102525122","https://openalex.org/W4306316843","https://openalex.org/W2036953450","https://openalex.org/W2130594209","https://openalex.org/W4245282135","https://openalex.org/W2170004886","https://openalex.org/W4300955944","https://openalex.org/W2527822502"],"abstract_inverted_index":{"In":[0,19,89],"large-scale":[1],"Grid":[2],"computing":[3,31],"environments,":[4],"providing":[5],"fault-tolerance":[6],"is":[7,74,96],"required":[8],"for":[9,26,86],"both":[10],"scientific":[11],"computation":[12],"and":[13,43,50,83,111,130],"file-sharing":[14],"to":[15],"increase":[16],"their":[17,63],"reliability.":[18],"previous":[20],"works,":[21],"several":[22],"mechanisms":[23,57],"were":[24],"proposed":[25],"the":[27,55,67,76,91,108,126],"Grids":[28],"or":[29],"distributed":[30],"systems.":[32],"However,":[33],"some":[34],"of":[35,62,72,78,94,102,104,114,128],"them":[36],"used":[37,45],"only":[38,46],"space":[39],"redundancy":[40,48],"(hardware":[41],"replication),":[42],"others":[44],"time":[47],"(checkpointing":[49],"rollback).":[51],"For":[52],"this":[53],"reason,":[54],"existing":[56,135],"are":[58],"inefficient":[59],"in":[60],"terms":[61],"resource":[64],"utilization":[65],"on":[66,100],"Grids.":[68],"The":[69],"main":[70],"goal":[71],"ART":[73,122],"reducing":[75],"number":[77,93,127],"replications":[79,95,129],"by":[80],"using":[81],"checkpointing":[82],"rollback":[84],"scheme":[85],"each":[87,115],"replication.":[88],"ART,":[90],"minimum":[92],"adaptively":[97],"selected":[98],"based":[99],"analysis":[101],"probability":[103],"successful":[105],"execution":[106],"within":[107],"given":[109],"deadline":[110],"reliability":[112],"requirement":[113],"task.":[116],"Our":[117],"simulation":[118],"results":[119],"show":[120],"that":[121],"can":[123],"significantly":[124],"reduce":[125],"improve":[131],"scalability":[132],"compared":[133],"with":[134],"mechanisms.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
