{"id":"https://openalex.org/W2166143798","doi":"https://doi.org/10.1109/clustr.2007.4629264","title":"A reliability-aware approach for an optimal checkpoint/restart model in HPC environments","display_name":"A reliability-aware approach for an optimal checkpoint/restart model in HPC environments","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2166143798","doi":"https://doi.org/10.1109/clustr.2007.4629264","mag":"2166143798"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2007.4629264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2007.4629264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"},"type":"article","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/A5003892229","display_name":"Yudan Liu","orcid":"https://orcid.org/0000-0002-7496-7033"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yudan Liu","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114093464","display_name":"Raja Nassar","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raja Nassar","raw_affiliation_strings":["College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110271347","display_name":"Chockchai Leangsuksun","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chockchai Leangsuksun","raw_affiliation_strings":["College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029063905","display_name":"Nichamon Naksinehaboon","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nichamon Naksinehaboon","raw_affiliation_strings":["College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005550984","display_name":"Mihaela P\u0103un","orcid":"https://orcid.org/0000-0002-3342-9140"},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihaela Paun","raw_affiliation_strings":["College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109843869","display_name":"Stephen L. Scott","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Scott","raw_affiliation_strings":["College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering & Science, Louisiana Technology University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3474,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.84336064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"4","issue":null,"first_page":"452","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.818474292755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8051812648773193},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6542189121246338},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6524994373321533},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6048845052719116},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.5074002146720886},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41971996426582336},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4095233380794525},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3362378478050232},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17934197187423706},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0834130048751831}],"concepts":[{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.818474292755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051812648773193},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6542189121246338},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6524994373321533},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6048845052719116},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5074002146720886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41971996426582336},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4095233380794525},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3362378478050232},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17934197187423706},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0834130048751831},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clustr.2007.4629264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2007.4629264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1567880","https://openalex.org/W191492107","https://openalex.org/W1530574078","https://openalex.org/W1538116128","https://openalex.org/W1558516248","https://openalex.org/W1971952282","https://openalex.org/W2033656974","https://openalex.org/W2044565821","https://openalex.org/W2045879521","https://openalex.org/W2048784665","https://openalex.org/W2098259808","https://openalex.org/W2106017997","https://openalex.org/W2113052966","https://openalex.org/W2119018856","https://openalex.org/W2129935547","https://openalex.org/W2132920089","https://openalex.org/W2133046454","https://openalex.org/W2135917956","https://openalex.org/W2799087070","https://openalex.org/W2992707587","https://openalex.org/W4232225775","https://openalex.org/W6600063193","https://openalex.org/W6607731702","https://openalex.org/W6631753506","https://openalex.org/W6632055538","https://openalex.org/W6633553838","https://openalex.org/W6678776837","https://openalex.org/W6679774514","https://openalex.org/W6750481014"],"related_works":["https://openalex.org/W2075454349","https://openalex.org/W2145855242","https://openalex.org/W2010356481","https://openalex.org/W2016184125","https://openalex.org/W4236084769","https://openalex.org/W2103295733","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"The":[0],"increase":[1],"in":[2,60],"the":[3,21,75,110],"physical":[4],"size":[5],"of":[6,31],"High":[7],"Performance":[8],"Computing":[9],"(HPC)":[10],"platform":[11],"makes":[12],"system":[13,64,77],"reliability":[14],"more":[15],"challenging.":[16],"In":[17,108],"order":[18],"to":[19,25,54],"minimize":[20],"performance":[22],"loss":[23],"due":[24],"unexpected":[26],"failures":[27],"or":[28],"unnecessary":[29],"overhead":[30,117],"fault":[32,56],"tolerant":[33],"mechanisms,":[34],"we":[35],"present":[36],"a":[37,61,90,98,125],"reliability-aware":[38],"method":[39],"for":[40,114],"an":[41],"optimal":[42,67],"checkpoint/restart":[43],"strategy":[44],"towards":[45],"minimizing":[46],"rollback":[47,119],"and":[48,89,102,118],"checkpoint":[49,68,81,92,100,116],"overheads.":[50],"Our":[51,121],"scheme":[52],"aims":[53],"address":[55],"tolerance":[57],"challenge":[58],"especially":[59],"large-scale":[62],"HPC":[63],"by":[65],"providing":[66],"placement":[69],"techniques":[70],"that":[71],"are":[72],"derived":[73],"from":[74],"actual":[76],"reliability.":[78],"Unlike":[79],"existing":[80,129],"models,":[82],"which":[83],"can":[84,96],"only":[85],"handle":[86],"Poisson":[87],"failure":[88,106],"constant":[91],"interval,":[93],"our":[94],"model":[95],"perform":[97],"varying":[99],"interval":[101],"deal":[103],"with":[104],"different":[105],"distributions.":[107],"addition,":[109],"approach":[111],"considers":[112],"optimality":[113],"both":[115],"time.":[120],"validation":[122],"results":[123],"suggest":[124],"significant":[126],"improvement":[127],"over":[128],"techniques.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
