{"id":"https://openalex.org/W4387005683","doi":"https://doi.org/10.1109/e-science58273.2023.10254871","title":"I/O Burst Prediction for HPC Clusters Using Darshan Logs","display_name":"I/O Burst Prediction for HPC Clusters Using Darshan Logs","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387005683","doi":"https://doi.org/10.1109/e-science58273.2023.10254871"},"language":"en","primary_location":{"id":"doi:10.1109/e-science58273.2023.10254871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","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/A5065553357","display_name":"Ehsan Saeedizade","orcid":"https://orcid.org/0000-0002-8455-8313"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ehsan Saeedizade","raw_affiliation_strings":["University of Nevada,Reno","University of Nevada, Reno"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Reno","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Nevada, Reno","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092475871","display_name":"Roya Taheri","orcid":null},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roya Taheri","raw_affiliation_strings":["University of Nevada,Reno","University of Nevada, Reno"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Reno","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Nevada, Reno","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019077099","display_name":"Engin Arslan","orcid":"https://orcid.org/0000-0002-2355-057X"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Engin Arslan","raw_affiliation_strings":["University of Texas,Arlington","University of Texas, Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas,Arlington","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"University of Texas, Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065553357"],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":null,"apc_paid":null,"fwci":1.4044,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82609399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T11181","display_name":"Advanced Data Storage Technologies","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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8022230267524719},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6187055110931396},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4415853023529053},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4315575361251831},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.4159894585609436},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27076637744903564},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.08107981085777283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022230267524719},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6187055110931396},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4415853023529053},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4315575361251831},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.4159894585609436},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27076637744903564},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.08107981085777283},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/e-science58273.2023.10254871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6000000238418579,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G7835679800","display_name":null,"funder_award_id":"2145742,2007789","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W579623069","https://openalex.org/W839531409","https://openalex.org/W1572047826","https://openalex.org/W2039546699","https://openalex.org/W2096812688","https://openalex.org/W2412848782","https://openalex.org/W2559796885","https://openalex.org/W2566279479","https://openalex.org/W2899477092","https://openalex.org/W2903745441","https://openalex.org/W2954028704","https://openalex.org/W2985168981","https://openalex.org/W3000723004","https://openalex.org/W3038118166","https://openalex.org/W3159974995","https://openalex.org/W3169404295","https://openalex.org/W4206038948","https://openalex.org/W4239195043","https://openalex.org/W4285503921","https://openalex.org/W6752118281","https://openalex.org/W6794914594"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W44553394"],"abstract_inverted_index":{"Understanding":[0],"cluster-wide":[1],"I/O":[2,17,34,51,67,85,97,135,143,155,192],"patterns":[3],"of":[4,16,83,133,142,188],"large-scale":[5],"HPC":[6],"clusters":[7],"is":[8],"essential":[9],"to":[10,45,79,190,203,206],"minimize":[11],"the":[12,81,121,131,134,185,197],"occurrence":[13,82],"and":[14,29,32,49,65,109,166],"impact":[15],"interference.":[18],"Yet,":[19],"most":[20],"previous":[21],"work":[22],"in":[23,53,63,69,148,209],"this":[24,174],"area":[25],"focused":[26],"on":[27],"monitoring":[28],"predicting":[30],"task":[31],"node-level":[33],"burst":[35],"events.":[36],"This":[37],"paper":[38],"analyzes":[39],"Darshan":[40],"reports":[41],"from":[42],"three":[43,71],"supercomputers":[44],"extract":[46],"system-level":[47,84],"read":[48,64],"write":[50,66],"rates":[52,68],"five":[54,106],"minutes":[55,88,107],"intervals.":[56],"We":[57,73,117,137,194],"observe":[58],"significant":[59],"(over":[60],"100\u00d7)":[61],"fluctuations":[62],"all":[70],"clusters.":[72],"then":[74],"train":[75],"machine":[76],"learning":[77],"models":[78,123],"estimate":[80],"bursts":[86,98,144],"5\u2013120":[87],"ahead.":[89,116],"Evaluation":[90],"results":[91],"show":[92,119,195],"that":[93,120,139,182,196],"we":[94,176],"can":[95,145,183,201],"predict":[96],"with":[99],"more":[100,110,125],"than":[101,111,126],"90%":[102],"accuracy":[103,113,128],"(F-1":[104],"score)":[105],"ahead":[108],"87%":[112],"two":[114],"hours":[115],"also":[118],"ML":[122],"attain":[124],"70%":[127],"when":[129],"estimating":[130],"degree":[132],"burst.":[136],"believe":[138],"high-accuracy":[140],"predictions":[141],"be":[146],"used":[147],"multiple":[149],"ways,":[150],"such":[151],"as":[152],"postponing":[153],"delay-tolerant":[154],"operations":[156],"(e.g.,":[157,162],"checkpointing),":[158],"pausing":[159],"nonessential":[160],"applications":[161,189],"file":[163],"system":[164],"scrubbers),":[165],"devising":[167],"I/O-aware":[168],"job":[169,180,199],"scheduling":[170,200],"methods.":[171],"To":[172],"validate":[173],"claim,":[175],"simulated":[177],"a":[178],"burst-aware":[179,198],"scheduler":[181],"postpone":[184],"start":[186],"time":[187],"avoid":[191],"bursts.":[193],"lead":[202],"an":[204],"up":[205],"5\u00d7":[207],"decrease":[208],"application":[210],"runtime.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
