{"id":"https://openalex.org/W4401409197","doi":"https://doi.org/10.1145/3674912.3674914","title":"HPC Jobs Classification and Resource Prediction to Minimize Job Failures","display_name":"HPC Jobs Classification and Resource Prediction to Minimize Job Failures","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4401409197","doi":"https://doi.org/10.1145/3674912.3674914"},"language":"en","primary_location":{"id":"doi:10.1145/3674912.3674914","doi":"https://doi.org/10.1145/3674912.3674914","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674912.3674914","pdf_url":null,"source":{"id":"https://openalex.org/S4210222260","display_name":"International Conference on Computer Systems and Technologies (CompSysTech)","issn_l":"1313-8936","issn":["1313-8936","1313-9037"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Systems and Technologies 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5017410471","display_name":"Tariq Daradkeh","orcid":"https://orcid.org/0000-0002-1294-7117","observed_orcids":["https://orcid.org/0000-0002-1294-7117"]},"institutions":[{"id":"https://openalex.org/I85507684","display_name":"Yarmouk University","ror":"https://ror.org/004mbaj56","country_code":"JO","type":"education","lineage":["https://openalex.org/I85507684"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Tariq Daradkeh","raw_affiliation_strings":["Yarmouk University, Jordan"],"raw_orcid":"https://orcid.org/0000-0002-1294-7117","affiliations":[{"raw_affiliation_string":"Yarmouk University, Jordan","institution_ids":["https://openalex.org/I85507684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092473976","display_name":"Gillian Roper","orcid":"https://orcid.org/0009-0005-4385-1723","observed_orcids":["https://orcid.org/0009-0005-4385-1723"]},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gillian Roper","raw_affiliation_strings":["Concordia University, Canada"],"raw_orcid":"https://orcid.org/0009-0005-4385-1723","affiliations":[{"raw_affiliation_string":"Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082875446","display_name":"Carlos Alarcon Meza","orcid":"https://orcid.org/0009-0002-3366-6821","observed_orcids":["https://orcid.org/0009-0002-3366-6821"]},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Carlos Alarcon Meza","raw_affiliation_strings":["Concordia University, Canada"],"raw_orcid":"https://orcid.org/0009-0002-3366-6821","affiliations":[{"raw_affiliation_string":"Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047782865","display_name":"Serguei A. Mokhov","orcid":"https://orcid.org/0000-0002-8791-4790","observed_orcids":["https://orcid.org/0000-0002-8791-4790"]},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serguei A. Mokhov","raw_affiliation_strings":["Concordia University, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8791-4790","affiliations":[{"raw_affiliation_string":"Concordia University, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5571,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81086743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.7271000146865845,"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":0.7271000146865845,"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":0.23250000178813934,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.00839999970048666,"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/resource-forecasting","display_name":"resource prediction","score":0.859000027179718},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.6169999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111565470695496},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4803222715854645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3728266954421997},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.34492576122283936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3252130448818207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1376415491104126},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06184074282646179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674912.3674914","doi":"https://doi.org/10.1145/3674912.3674914","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674912.3674914","pdf_url":null,"source":{"id":"https://openalex.org/S4210222260","display_name":"International Conference on Computer Systems and Technologies (CompSysTech)","issn_l":"1313-8936","issn":["1313-8936","1313-9037"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Systems and Technologies 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2162342269","https://openalex.org/W2516806418","https://openalex.org/W2944938400","https://openalex.org/W3048021565","https://openalex.org/W3206868782","https://openalex.org/W3207603082","https://openalex.org/W4200345482","https://openalex.org/W4281261651","https://openalex.org/W4285325287","https://openalex.org/W4285503930"],"related_works":["https://openalex.org/W2806434281","https://openalex.org/W3046790217","https://openalex.org/W2516806418","https://openalex.org/W4394784972","https://openalex.org/W1630477762","https://openalex.org/W7172422959","https://openalex.org/W1486648961","https://openalex.org/W4381890996","https://openalex.org/W2083393867","https://openalex.org/W2885592611"],"abstract_inverted_index":{"In":[0],"this":[1,109],"work,":[2],"we":[3,89,111],"focus":[4],"on":[5,108],"HPC":[6,12,73],"job":[7,58,69,98,104,114,119,133],"classification":[8],"and":[9,21,43,48,75,101,121],"resource":[10],"prediction.":[11],"users":[13,37],"at":[14],"Concordia":[15],"University":[16],"come":[17],"from":[18,79],"different":[19],"departments,":[20],"not":[22],"all":[23],"of":[24,31,126],"them":[25,81],"have":[26],"an":[27],"IT":[28],"background.":[29],"One":[30],"the":[32,83,113,124,132],"most":[33],"challenging":[34],"issues":[35],"for":[36,52],"is":[38],"how":[39],"to":[40,71,117,122],"properly":[41],"estimate":[42],"request":[44],"sufficient":[45],"cluster":[46],"resources":[47,74],"wall":[49,62,84],"clock":[50,63,85],"time":[51,64,86],"their":[53],"jobs.":[54],"Additionally,":[55],"when":[56],"a":[57,91,97],"terminates":[59],"before":[60],"its":[61],"limit":[65],"has":[66],"expired,":[67],"that":[68,93,102],"continues":[70],"reserve":[72],"blocks":[76],"other":[77],"jobs":[78],"using":[80],"until":[82],"expires.":[87],"Therefore,":[88],"propose":[90],"module":[92],"can":[94],"predict":[95],"whether":[96],"will":[99],"fail":[100],"classifies":[103],"failure":[105,134],"types.":[106],"Based":[107],"classification,":[110],"adjust":[112],"submission":[115],"parameters":[116],"avoid":[118],"failures":[120],"prevent":[123],"misallocation":[125],"resources.":[127],"Our":[128],"proposed":[129],"model":[130],"reduces":[131],"ratio":[135],"by":[136],"92%.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2024-08-09T00:00:00"}
