{"id":"https://openalex.org/W1971961903","doi":"https://doi.org/10.1109/dsnw.2010.5542629","title":"Quantifying effectiveness of failure prediction and response in HPC systems: Methodology and example","display_name":"Quantifying effectiveness of failure prediction and response in HPC systems: Methodology and example","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W1971961903","doi":"https://doi.org/10.1109/dsnw.2010.5542629","mag":"1971961903"},"language":"en","primary_location":{"id":"doi:10.1109/dsnw.2010.5542629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsnw.2010.5542629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on Dependable Systems and Networks Workshops (DSN-W)","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/A5112853905","display_name":"James M. Brandt","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James Brandt","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018389594","display_name":"Fanglin Chen","orcid":"https://orcid.org/0000-0001-9942-8872"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Chen","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044695992","display_name":"Vincent De Sapio","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent De Sapio","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108111326","display_name":"Ann Gentile","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ann Gentile","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9152, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9152, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103336291","display_name":"Jackson Mayo","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jackson Mayo","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090559121","display_name":"Philippe P\u00e9ba\u00ff","orcid":"https://orcid.org/0000-0002-2311-3775"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philippe Pebay","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252724","display_name":"Diana C. Roe","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diana Roe","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9152, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9152, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000430651","display_name":"David Thompson","orcid":"https://orcid.org/0000-0002-8575-6469"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Thompson","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9159, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085975175","display_name":"Matthew Wong","orcid":"https://orcid.org/0000-0003-2680-961X"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wong","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, U.S.A","Sandia National Laboratories, MS 9152, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, U.S.A","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Laboratories, MS 9152, P.O. Box 969, Livermore, CA 94551 U.S.A.#TAB#","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5112853905"],"corresponding_institution_ids":["https://openalex.org/I192454743"],"apc_list":null,"apc_paid":null,"fwci":0.6937,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.81254226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.993399977684021,"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/T10260","display_name":"Software Engineering Research","score":0.993399977684021,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9796000123023987,"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":0.7637287378311157},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7055564522743225},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6278184056282043},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.6091600060462952},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5975744128227234},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5952274203300476},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5107929706573486},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4761795401573181},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.47409161925315857},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4693881869316101},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4451078772544861},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41095805168151855},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32170698046684265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20147410035133362},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12253755331039429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637287378311157},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7055564522743225},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6278184056282043},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.6091600060462952},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5975744128227234},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5952274203300476},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5107929706573486},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4761795401573181},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.47409161925315857},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4693881869316101},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4451078772544861},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41095805168151855},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32170698046684265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20147410035133362},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12253755331039429},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsnw.2010.5542629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsnw.2010.5542629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on Dependable Systems and Networks Workshops (DSN-W)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W376961572","https://openalex.org/W1530427892","https://openalex.org/W1539462193","https://openalex.org/W2042273126","https://openalex.org/W2059310136","https://openalex.org/W2096611465","https://openalex.org/W2106753104","https://openalex.org/W2131477709","https://openalex.org/W2145864256","https://openalex.org/W2158698691","https://openalex.org/W2162485312","https://openalex.org/W2164718882","https://openalex.org/W3148902696","https://openalex.org/W6631825601","https://openalex.org/W6632480607"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W1977636359","https://openalex.org/W2772305933","https://openalex.org/W2580722822"],"abstract_inverted_index":{"Effective":[0],"failure":[1,40,65],"prediction":[2,81],"and":[3,30,36,82,85,101],"mitigation":[4,83],"strategies":[5,84],"in":[6,14,60,66],"high-performance":[7],"computing":[8],"systems":[9],"could":[10],"provide":[11],"huge":[12],"gains":[13,23],"resilience":[15],"of":[16,57,80,103],"tightly":[17],"coupled":[18],"large-scale":[19],"scientific":[20],"codes.":[21],"These":[22],"would":[24],"come":[25],"from":[26],"prediction-directed":[27],"process":[28],"migration":[29],"resource":[31,34],"servicing,":[32],"intelligent":[33],"allocation,":[35],"checkpointing":[37],"driven":[38],"by":[39],"predictors":[41],"rather":[42],"than":[43],"at":[44],"regular":[45],"intervals":[46],"based":[47],"on":[48],"nominal":[49],"mean":[50],"time":[51],"to":[52],"failure.":[53],"Given":[54],"probabilistic":[55],"associations":[56],"outlier":[58],"behavior":[59],"hardware-related":[61],"metrics":[62],"with":[63],"eventual":[64],"hardware,":[67],"system":[68,91],"software,":[69],"and/or":[70],"applications,":[71],"this":[72],"paper":[73],"explores":[74],"approaches":[75],"for":[76,97],"quantifying":[77],"the":[78,99],"effects":[79],"demonstrates":[86],"these":[87],"using":[88],"actual":[89],"production":[90],"data.":[92],"We":[93],"describe":[94],"context-relevant":[95],"methodologies":[96],"determining":[98],"accuracy":[100],"cost-benefit":[102],"predictors.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
