{"id":"https://openalex.org/W3148902696","doi":"https://doi.org/10.1109/ipdps.2006.1639698","title":"OVIS: a tool for intelligent, real-time monitoring of computational clusters","display_name":"OVIS: a tool for intelligent, real-time monitoring of computational clusters","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W3148902696","doi":"https://doi.org/10.1109/ipdps.2006.1639698","mag":"3148902696"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2006.1639698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel &amp; Distributed Processing Symposium","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/A5015075548","display_name":"Jim Brandt","orcid":"https://orcid.org/0000-0002-8605-5795"},"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":"J.M. Brandt","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105008605","display_name":"Ann C. 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":"A.C. Gentile","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109270164","display_name":"Dennis Hale","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":"D.J. Hale","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","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":"P.P. Pebay","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015075548"],"corresponding_institution_ids":["https://openalex.org/I192454743"],"apc_list":null,"apc_paid":null,"fwci":1.2071,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83260775,"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":"8 pp.","last_page":"8 pp."},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9947999715805054,"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":0.9947999715805054,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9937999844551086,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216495275497437},{"id":"https://openalex.org/keywords/singleton","display_name":"Singleton","score":0.6484965682029724},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5538460612297058},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5440303087234497},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5389315485954285},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5075455904006958},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5000402927398682},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4863000810146332},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4793420732021332},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4396977722644806},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.41427552700042725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34390249848365784},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11288678646087646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216495275497437},{"id":"https://openalex.org/C117354338","wikidata":"https://www.wikidata.org/wiki/Q1165112","display_name":"Singleton","level":3,"score":0.6484965682029724},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5538460612297058},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5440303087234497},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5389315485954285},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5075455904006958},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5000402927398682},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4863000810146332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4793420732021332},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4396977722644806},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.41427552700042725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34390249848365784},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11288678646087646},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C2779234561","wikidata":"https://www.wikidata.org/wiki/Q11995","display_name":"Pregnancy","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2006.1639698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel &amp; Distributed Processing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2111996486","https://openalex.org/W2147921378"],"related_works":["https://openalex.org/W2407375987","https://openalex.org/W3049691116","https://openalex.org/W2505726097","https://openalex.org/W2010643158","https://openalex.org/W2106867672","https://openalex.org/W3081214562","https://openalex.org/W4310268968","https://openalex.org/W2950975704","https://openalex.org/W4297815943","https://openalex.org/W2053745677"],"abstract_inverted_index":{"Traditional":[0],"cluster":[1,80,98,189],"monitoring":[2,24],"approaches":[3],"consider":[4],"nodes":[5],"in":[6,135,188,200],"singleton,":[7],"using":[8],"manufacturer-specified":[9],"extreme":[10],"limits":[11],"as":[12,81,87,151],"thresholds":[13],"for":[14,23,96,118,164],"failure":[15],"\"prediction\".":[16],"We":[17,181],"have":[18],"developed":[19],"a":[20,34,45,82,109,123,156],"tool,":[21],"OVIS,":[22],"and":[25,72,93,100,125,184,191,194,197],"analysis":[26],"of":[27,44,48,54,60,78,103,122,132,160,167],"large":[28,46],"computational":[29],"platforms":[30],"which,":[31],"instead,":[32],"uses":[33],"statistical":[35],"approach":[36],"to":[37,114,126,175,195],"characterize":[38],"single":[39],"device":[40],"behaviors":[41],"from":[42],"those":[43],"number":[47],"statistically":[49],"similar":[50],"devices.":[51],"Baseline":[52],"capabilities":[53],"OVIS":[55,107,183],"include":[56],"the":[57,79,119,130,136,145,165],"visual":[58],"display":[59],"deterministic":[61],"information":[62],"about":[63],"state":[64],"variables":[65],"(e.g.,":[66],"temperature,":[67],"CPU":[68],"utilization,":[69],"fan":[70],"speed)":[71],"their":[73],"aggregate":[74],"statistics.":[75],"Visual":[76],"consideration":[77],"comparative":[83],"ensemble,":[84],"rather":[85],"than":[86,162],"singleton":[88],"nodes,":[89],"is":[90,171],"an":[91],"easy":[92],"useful":[94],"method":[95],"tuning":[97,193],"configuration":[99,190],"determining":[101],"effects":[102],"realtime":[104],"changes.":[105],"Additionally,":[106],"incorporates":[108],"novel":[110],"Bayesian":[111],"inference":[112],"scheme":[113],"dynamically":[115],"infer":[116],"models":[117],"normal":[120],"behavior":[121],"system":[124],"determine":[127],"bounds":[128],"on":[129],"probability":[131],"values":[133,140],"evinced":[134],"system.":[137],"Individual":[138],"node":[139],"that":[141,170],"are":[142,149],"unlikely":[143],"given":[144],"current":[146],"applicable":[147],"model":[148],"flagged":[150],"aberrant.":[152],"This":[153],"can":[154],"be":[155],"much":[157],"earlier":[158],"indicator":[159],"problems":[161],"waiting":[163],"crossing":[166],"some":[168],"threshold":[169],"necessarily":[172],"set":[173],"high":[174],"preclude":[176],"too":[177],"many":[178],"false":[179],"alarms.":[180],"present":[182],"discuss":[185],"its":[186],"applications":[187],"environmental":[192],"abnormality":[196],"problem":[198],"discovery":[199],"our":[201],"production":[202],"clusters":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
