{"id":"https://openalex.org/W2058678332","doi":"https://doi.org/10.1145/1383422.1383426","title":"Performability modeling for scheduling and fault tolerance strategies for scientific workflows","display_name":"Performability modeling for scheduling and fault tolerance strategies for scientific workflows","publication_year":2008,"publication_date":"2008-06-23","ids":{"openalex":"https://openalex.org/W2058678332","doi":"https://doi.org/10.1145/1383422.1383426","mag":"2058678332"},"language":"en","primary_location":{"id":"doi:10.1145/1383422.1383426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1383422.1383426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international symposium on High performance distributed 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/A5038208900","display_name":"Lavanya Ramakrishnan","orcid":"https://orcid.org/0000-0003-1761-4132"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lavanya Ramakrishnan","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008222900","display_name":"Daniel A. Reed","orcid":"https://orcid.org/0000-0001-7331-1473"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel A. Reed","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038208900"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":5.1571,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95578236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"34"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976000189781189,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.855962872505188},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.8188863396644592},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7002930641174316},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6982868313789368},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6625638604164124},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6268177628517151},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6013619899749756},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.578813910484314},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5498723983764648},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.5355415940284729},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4782083034515381},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.4322351813316345},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4190221428871155},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2719898223876953},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17234396934509277},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14562088251113892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855962872505188},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.8188863396644592},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7002930641174316},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6982868313789368},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6625638604164124},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6268177628517151},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6013619899749756},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.578813910484314},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5498723983764648},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.5355415940284729},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4782083034515381},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.4322351813316345},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4190221428871155},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2719898223876953},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17234396934509277},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14562088251113892},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1383422.1383426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1383422.1383426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international symposium on High performance distributed computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310133","display_name":"Rice University","ror":"https://ror.org/008zs3103"},{"id":"https://openalex.org/F4320332600","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W9942251","https://openalex.org/W125869453","https://openalex.org/W145805655","https://openalex.org/W746497258","https://openalex.org/W1546861699","https://openalex.org/W1558516248","https://openalex.org/W1587236616","https://openalex.org/W1763890264","https://openalex.org/W1964285734","https://openalex.org/W1981065283","https://openalex.org/W2004982420","https://openalex.org/W2025397485","https://openalex.org/W2040932846","https://openalex.org/W2053352232","https://openalex.org/W2055043387","https://openalex.org/W2064651666","https://openalex.org/W2070215238","https://openalex.org/W2094806030","https://openalex.org/W2103342689","https://openalex.org/W2117848690","https://openalex.org/W2130542946","https://openalex.org/W2135069172","https://openalex.org/W2152389848","https://openalex.org/W2165439624","https://openalex.org/W2172979163","https://openalex.org/W2543371480","https://openalex.org/W3016793792","https://openalex.org/W3189652510","https://openalex.org/W4236054614","https://openalex.org/W6666601123","https://openalex.org/W7023737834"],"related_works":["https://openalex.org/W1948607442","https://openalex.org/W3004004161","https://openalex.org/W2044615423","https://openalex.org/W4247766898","https://openalex.org/W4244765761","https://openalex.org/W2361584951","https://openalex.org/W2365327041","https://openalex.org/W4225348249","https://openalex.org/W31122515","https://openalex.org/W2354832693"],"abstract_inverted_index":{"Scientific":[0],"applications":[1,26],"have":[2,46],"diverse":[3],"characteristics":[4],"and":[5,39,43,97,133,145],"resource":[6,123,166],"requirements.":[7],"When":[8],"combined":[9],"with":[10,63],"the":[11,37,56,101,109,115,127,160],"complexity":[12],"of":[13,41,55,59,111],"underlying":[14,102],"distributed":[15],"resources":[16],"on":[17],"which":[18],"they":[19],"execute":[20],"(e.g.":[21],"Grid,":[22],"cloud":[23],"computing),":[24],"these":[25],"can":[27,73],"experience":[28],"significant":[29],"performance":[30,38,96,117],"fluctuations":[31],"as":[32],"machine":[33],"reliability":[34,40,98],"varies.":[35],"Although":[36],"cluster":[42],"Grid":[44],"systems":[45,156],"been":[47,52],"studied":[48],"separately,":[49],"there":[50],"has":[51],"little":[53],"analysis":[54],"lost":[57],"Quality":[58],"Service":[60],"(QoS)":[61],"experienced":[62],"varying":[64,122],"availability":[65],"levels.":[66],"To":[67],"enable":[68],"a":[69],"dynamic":[70],"environment":[71],"that":[72,90,118],"account":[74],"for":[75,100,165],"such":[76],"changes":[77],"while":[78],"providing":[79],"required":[80],"QoS,":[81],"next":[82],"generation":[83],"tools":[84],"will":[85],"need":[86],"extensible":[87],"application":[88],"interfaces":[89],"allow":[91],"users":[92],"to":[93,113,130,141,157],"qualitatively":[94],"express":[95],"requirements":[99],"systems.":[103],"In":[104],"this":[105],"paper,":[106],"we":[107],"use":[108,146],"concept":[110],"performability":[112],"capture":[114],"degraded":[116],"might":[119],"result":[120],"from":[121,153],"availability.":[124,167],"We":[125,137],"apply":[126],"resulting":[128],"model":[129,144],"workflow":[131],"planning":[132],"fault":[134],"tolerance":[135],"strategies.":[136],"present":[138],"experimental":[139],"data":[140,152],"validate":[142],"our":[143],"simulation":[147],"results":[148],"driven":[149],"by":[150],"failure":[151],"real":[154],"HPC":[155],"demonstrate":[158],"how":[159],"proposed":[161],"scheme":[162],"better":[163],"accounts":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
