{"id":"https://openalex.org/W2988255906","doi":"https://doi.org/10.1145/3295500.3356185","title":"Predicting faults in high performance computing systems","display_name":"Predicting faults in high performance computing systems","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2988255906","doi":"https://doi.org/10.1145/3295500.3356185","mag":"2988255906"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356185","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5052202416","display_name":"David Jauk","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"David Jauk","raw_affiliation_strings":["Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101065119","display_name":"Dai Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dai Yang","raw_affiliation_strings":["Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052202416"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.5216,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93567078,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9988999962806702,"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":0.9988999962806702,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9936000108718872,"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/resilience","display_name":"Resilience (materials science)","score":0.8297481536865234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525632977485657},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5222775936126709},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.513727068901062},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.43361955881118774},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.37485218048095703},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13909709453582764},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07935237884521484}],"concepts":[{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.8297481536865234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525632977485657},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5222775936126709},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.513727068901062},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.43361955881118774},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.37485218048095703},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13909709453582764},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07935237884521484},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3295500.3356185","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W191651381","https://openalex.org/W200983080","https://openalex.org/W1480376833","https://openalex.org/W1507079426","https://openalex.org/W1553890549","https://openalex.org/W1577893785","https://openalex.org/W1589384255","https://openalex.org/W1604749136","https://openalex.org/W1670263352","https://openalex.org/W1930624869","https://openalex.org/W1954021262","https://openalex.org/W1966243865","https://openalex.org/W1987117298","https://openalex.org/W1987454953","https://openalex.org/W1988099502","https://openalex.org/W1990697197","https://openalex.org/W1991133427","https://openalex.org/W1995945562","https://openalex.org/W1998221613","https://openalex.org/W1999900893","https://openalex.org/W2030826766","https://openalex.org/W2032858539","https://openalex.org/W2034679365","https://openalex.org/W2038028331","https://openalex.org/W2040352153","https://openalex.org/W2041218528","https://openalex.org/W2042273126","https://openalex.org/W2049885667","https://openalex.org/W2083393867","https://openalex.org/W2087387294","https://openalex.org/W2093062132","https://openalex.org/W2094127360","https://openalex.org/W2094924503","https://openalex.org/W2095157729","https://openalex.org/W2099840467","https://openalex.org/W2107263349","https://openalex.org/W2107461003","https://openalex.org/W2120591095","https://openalex.org/W2120738897","https://openalex.org/W2122249806","https://openalex.org/W2123883612","https://openalex.org/W2125165932","https://openalex.org/W2130286559","https://openalex.org/W2133218851","https://openalex.org/W2136797898","https://openalex.org/W2141676918","https://openalex.org/W2142812297","https://openalex.org/W2143158360","https://openalex.org/W2145071552","https://openalex.org/W2152671254","https://openalex.org/W2155043308","https://openalex.org/W2158907675","https://openalex.org/W2159963962","https://openalex.org/W2161234420","https://openalex.org/W2164463086","https://openalex.org/W2169411532","https://openalex.org/W2176067516","https://openalex.org/W2293030740","https://openalex.org/W2296524286","https://openalex.org/W2306944593","https://openalex.org/W2336207029","https://openalex.org/W2338973660","https://openalex.org/W2396011504","https://openalex.org/W2557113531","https://openalex.org/W2567223979","https://openalex.org/W2571268788","https://openalex.org/W2664249172","https://openalex.org/W2735418241","https://openalex.org/W2751125473","https://openalex.org/W2754002858","https://openalex.org/W2757481678","https://openalex.org/W2757703774","https://openalex.org/W2770542984","https://openalex.org/W2799669964","https://openalex.org/W2902896512","https://openalex.org/W2903241786","https://openalex.org/W2949800959","https://openalex.org/W3003432522","https://openalex.org/W3080528907","https://openalex.org/W3106889297","https://openalex.org/W3124377424","https://openalex.org/W4238631751","https://openalex.org/W6743584807"],"related_works":["https://openalex.org/W2284759612","https://openalex.org/W4402320089","https://openalex.org/W4378555281","https://openalex.org/W2953081822","https://openalex.org/W2752145644","https://openalex.org/W4376453582","https://openalex.org/W1887981150","https://openalex.org/W4229446828","https://openalex.org/W2016027324","https://openalex.org/W2884088167"],"abstract_inverted_index":{"As":[0],"we":[1],"near":[2],"exascale,":[3],"resilience":[4,17],"remains":[5],"a":[6],"major":[7],"technical":[8],"hurdle.":[9],"Any":[10],"technique":[11],"with":[12],"the":[13,51,59,65],"goal":[14],"of":[15,34,61],"achieving":[16],"suffers":[18],"from":[19],"having":[20],"to":[21],"be":[22,48],"reactive,":[23],"as":[24],"failures":[25,42],"can":[26,47],"appear":[27],"at":[28,37],"any":[29],"time.":[30],"A":[31],"wide":[32],"body":[33],"research":[35],"aims":[36],"predicting":[38],"failures,":[39],"i.e.,":[40],"forecasting":[41],"so":[43],"that":[44],"evasive":[45],"actions":[46],"taken":[49],"while":[50],"system":[52,67],"is":[53],"still":[54],"fully":[55],"functional,":[56],"which":[57],"has":[58],"benefit":[60],"giving":[62],"insight":[63],"into":[64],"global":[66],"state.":[68]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}