{"id":"https://openalex.org/W3048079871","doi":"https://doi.org/10.1109/dsn-s50200.2020.00016","title":"Predicting Remediations for Hardware Failures in Large-Scale Datacenters","display_name":"Predicting Remediations for Hardware Failures in Large-Scale Datacenters","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3048079871","doi":"https://doi.org/10.1109/dsn-s50200.2020.00016","mag":"3048079871"},"language":"en","primary_location":{"id":"doi:10.1109/dsn-s50200.2020.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn-s50200.2020.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 50th Annual IEEE-IFIP International Conference on Dependable Systems and Networks-Supplemental Volume (DSN-S)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082391962","display_name":"Fred Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Fred Lin","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057510291","display_name":"Antonio Davoli","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Antonio Davoli","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101567583","display_name":"Imran Akbar","orcid":"https://orcid.org/0000-0002-4884-4259"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Imran Akbar","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052724657","display_name":"Sukumar Kalmanje","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sukumar Kalmanje","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101504411","display_name":"Leandro Silva","orcid":"https://orcid.org/0000-0002-2875-8329"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Leandro Silva","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054688648","display_name":"John Stamford","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"John Stamford","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089735255","display_name":"Yanai Golany","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yanai Golany","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011922382","display_name":"Jim Piazza","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jim Piazza","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103822281","display_name":"Sriram Sankar","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sriram Sankar","raw_affiliation_strings":["Facebook Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9984999895095825,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9922000169754028,"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":0.7704513072967529},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6289802193641663},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5929398536682129},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5455888509750366},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5293139815330505},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5185166597366333},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44668444991111755},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36824506521224976},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3447116017341614},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15982702374458313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09630978107452393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704513072967529},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6289802193641663},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5929398536682129},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5455888509750366},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5293139815330505},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5185166597366333},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44668444991111755},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36824506521224976},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3447116017341614},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15982702374458313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09630978107452393},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsn-s50200.2020.00016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn-s50200.2020.00016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 50th Annual IEEE-IFIP International Conference on Dependable Systems and Networks-Supplemental Volume (DSN-S)","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":14,"referenced_works":["https://openalex.org/W1669302834","https://openalex.org/W1678356000","https://openalex.org/W1976526581","https://openalex.org/W2001276096","https://openalex.org/W2141992894","https://openalex.org/W2144211451","https://openalex.org/W2169466806","https://openalex.org/W2883384187","https://openalex.org/W2963626623","https://openalex.org/W3023512926","https://openalex.org/W3035438476","https://openalex.org/W6681226105","https://openalex.org/W6770349254","https://openalex.org/W6777074873"],"related_works":["https://openalex.org/W4376453582","https://openalex.org/W3147033875","https://openalex.org/W1568390478","https://openalex.org/W2764722704","https://openalex.org/W318913410","https://openalex.org/W2355543518","https://openalex.org/W2601840227","https://openalex.org/W2131832954","https://openalex.org/W4205240067","https://openalex.org/W2374901194"],"abstract_inverted_index":{"Large-scale":[0],"service":[1],"environments":[2],"rely":[3],"on":[4,21,71,113],"autonomous":[5,15],"systems":[6],"for":[7,67,86],"remediating":[8],"hardware":[9,18,49],"failures":[10,19,42],"efficiently.":[11],"In":[12,53],"production,":[13],"the":[14,22,25,31,44,48,64,72,78,82,104,110,116],"system":[16],"diagnoses":[17],"based":[20,70],"rules":[23],"that":[24,62],"subject":[26],"matter":[27],"experts":[28],"put":[29],"in":[30,47,77,84,95],"system.":[32],"This":[33],"process":[34],"is":[35],"increasingly":[36],"complex":[37],"given":[38],"new":[39],"types":[40],"of":[41,115],"and":[43,50,99],"increasing":[45],"complexity":[46],"software":[51],"configurations.":[52],"this":[54],"paper,":[55],"we":[56],"present":[57],"a":[58,89,96],"machine":[59,90],"learning":[60,91],"framework":[61],"predicts":[63],"required":[65],"remediations":[66],"undiagnosed":[68],"failures,":[69],"similar":[73],"repair":[74,117],"tickets":[75],"closed":[76],"past.":[79],"We":[80,107],"explain":[81],"methodology":[83],"detail":[85],"setting":[87],"up":[88],"model,":[92],"deploying":[93],"it":[94],"production":[97],"environment,":[98],"monitoring":[100],"its":[101],"performance":[102,112],"with":[103],"necessary":[105],"metrics.":[106],"also":[108],"demonstrate":[109],"prediction":[111],"some":[114],"actions.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
