{"id":"https://openalex.org/W2891041086","doi":"https://doi.org/10.1109/tpds.2018.2870403","title":"Online Diagnosis of Performance Variation in HPC Systems Using Machine Learning","display_name":"Online Diagnosis of Performance Variation in HPC Systems Using Machine Learning","publication_year":2018,"publication_date":"2018-09-14","ids":{"openalex":"https://openalex.org/W2891041086","doi":"https://doi.org/10.1109/tpds.2018.2870403","mag":"2891041086"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2870403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2870403","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1474092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083584547","display_name":"Ozan Tuncer","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ozan Tuncer","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4222-1648","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074885535","display_name":"Emre Ate\u015f","orcid":"https://orcid.org/0000-0002-2292-2626"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emre Ates","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2292-2626","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101712600","display_name":"Yijia Zhang","orcid":"https://orcid.org/0000-0001-6925-7777"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijia Zhang","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108270551","display_name":"Ata T\u00fcrk","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ata Turk","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015075548","display_name":"Jim Brandt","orcid":"https://orcid.org/0000-0002-8605-5795"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jim Brandt","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032598206","display_name":"Vitus J. Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitus J. Leung","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044975798","display_name":"Manuel Egele","orcid":"https://orcid.org/0000-0001-5038-2682"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuel Egele","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064676631","display_name":"Ayse K. Coskun","orcid":"https://orcid.org/0000-0002-6554-088X"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayse K. Coskun","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6554-088X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6864,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.96327931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"30","issue":"4","first_page":"883","last_page":"896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"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":0.9968000054359436,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8082578182220459},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7735439538955688},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6751604080200195},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6738482713699341},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5973643064498901},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5325044393539429},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4737977385520935},{"id":"https://openalex.org/keywords/system-monitoring","display_name":"System monitoring","score":0.45058178901672363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4352963864803314},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37109214067459106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35064566135406494},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33548542857170105},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2566636800765991},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.245110422372818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082578182220459},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7735439538955688},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6751604080200195},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6738482713699341},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5973643064498901},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5325044393539429},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4737977385520935},{"id":"https://openalex.org/C200749887","wikidata":"https://www.wikidata.org/wiki/Q1165574","display_name":"System monitoring","level":2,"score":0.45058178901672363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4352963864803314},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37109214067459106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35064566135406494},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33548542857170105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2566636800765991},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.245110422372818},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2018.2870403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2870403","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1474092","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1474092","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1474092","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1474092","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2209453243","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1520857056","https://openalex.org/W1594031697","https://openalex.org/W1596515083","https://openalex.org/W1922735843","https://openalex.org/W1949554883","https://openalex.org/W1971961903","https://openalex.org/W1983545421","https://openalex.org/W1986905947","https://openalex.org/W1988404188","https://openalex.org/W1988790447","https://openalex.org/W2003797551","https://openalex.org/W2009223344","https://openalex.org/W2017504389","https://openalex.org/W2029979651","https://openalex.org/W2038924755","https://openalex.org/W2042273126","https://openalex.org/W2045587977","https://openalex.org/W2056413992","https://openalex.org/W2082486309","https://openalex.org/W2093606067","https://openalex.org/W2095954861","https://openalex.org/W2099741732","https://openalex.org/W2100997884","https://openalex.org/W2101778912","https://openalex.org/W2116335710","https://openalex.org/W2123983325","https://openalex.org/W2141041105","https://openalex.org/W2147598193","https://openalex.org/W2166481425","https://openalex.org/W2169620771","https://openalex.org/W2340816002","https://openalex.org/W2388631849","https://openalex.org/W2414171621","https://openalex.org/W2440381464","https://openalex.org/W2470262141","https://openalex.org/W2502136739","https://openalex.org/W2539171456","https://openalex.org/W2545001194","https://openalex.org/W2562383263","https://openalex.org/W2567538275","https://openalex.org/W2568011300","https://openalex.org/W2577261366","https://openalex.org/W2604128650","https://openalex.org/W2613580061","https://openalex.org/W2757481678","https://openalex.org/W2911964244","https://openalex.org/W4255375128","https://openalex.org/W4294350009","https://openalex.org/W4297957988","https://openalex.org/W6703970976","https://openalex.org/W6718285065","https://openalex.org/W6729149246","https://openalex.org/W6731382724"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2488249226","https://openalex.org/W1516401916","https://openalex.org/W2947869719"],"abstract_inverted_index":{"As":[0],"the":[1,51,60,73,77,92,146,156],"size":[2],"and":[3,18,37,47,53,68,71,79,95,154,184,196],"complexity":[4],"of":[5,55,62,129,158,193],"high":[6],"performance":[7,26,41,63,115],"computing":[8],"(HPC)":[9],"systems":[10,22],"grow":[11],"in":[12,16],"line":[13],"with":[14,170],"advancements":[15],"hardware":[17],"software":[19],"technology,":[20],"HPC":[21,56,182],"increasingly":[23],"suffer":[24],"from":[25],"variations":[27,42,78],"due":[28],"to":[29,45,87,112,126,151,167],"shared":[30],"resource":[31,123],"contention":[32],"as":[33,35],"well":[34],"software-":[36],"hardware-related":[38],"problems.":[39],"Such":[40],"can":[43],"lead":[44],"failures":[46],"inefficiencies,":[48],"which":[49],"impact":[50,61],"cost":[52],"resilience":[54],"systems.":[57],"To":[58],"minimize":[59],"variations,":[64],"one":[65],"must":[66],"quickly":[67],"accurately":[69],"detect":[70,152],"diagnose":[72,114,168],"anomalies":[74,89,116,169,195],"that":[75,148,186],"cause":[76],"take":[80],"mitigating":[81],"actions.":[82],"However,":[83],"it":[84],"is":[85],"difficult":[86],"identify":[88,145],"based":[90,110],"on":[91,179],"voluminous,":[93],"high-dimensional,":[94],"noisy":[96],"data":[97,125,138],"collected":[98,135],"by":[99],"system":[100],"monitoring":[101],"infrastructures.":[102],"This":[103],"paper":[104],"presents":[105],"a":[106,180],"novel":[107],"machine":[108],"learning":[109],"framework":[111,120,176],"automatically":[113],"at":[117],"runtime.":[118],"Our":[119],"leverages":[121],"historical":[122],"usage":[124],"extract":[127,155],"signatures":[128,157,166],"previously-observed":[130],"anomalies.":[131,160],"We":[132,143,173],"first":[133],"convert":[134],"time":[136],"series":[137],"into":[139],"easy-to-compute":[140],"statistical":[141],"features.":[142],"then":[144],"features":[147],"are":[149],"required":[150],"anomalies,":[153],"these":[159,165],"At":[161],"runtime,":[162],"we":[163],"use":[164],"negligible":[171],"overhead.":[172],"evaluate":[174],"our":[175,187],"using":[177],"experiments":[178],"real-world":[181],"supercomputer":[183],"demonstrate":[185],"approach":[188],"successfully":[189],"identifies":[190],"98":[191],"percent":[192],"injected":[194],"consistently":[197],"outperforms":[198],"existing":[199],"anomaly":[200],"diagnosis":[201],"techniques.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}