{"id":"https://openalex.org/W2138635902","doi":"https://doi.org/10.1109/grid.2005.1542743","title":"A scalable and efficient self-organizing failure detector for grid applications","display_name":"A scalable and efficient self-organizing failure detector for grid applications","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2138635902","doi":"https://doi.org/10.1109/grid.2005.1542743","mag":"2138635902"},"language":"en","primary_location":{"id":"doi:10.1109/grid.2005.1542743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/grid.2005.1542743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 6th IEEE/ACM International Workshop on Grid Computing, 2005.","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/A5084895467","display_name":"Yuuki Horita","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Horita","raw_affiliation_strings":["University of Tokyo, Japan","Tokyo, University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Tokyo, University, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009359355","display_name":"Kenjiro Taura","orcid":"https://orcid.org/0000-0001-5224-382X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Taura","raw_affiliation_strings":["University of Tokyo Japan Science and Technology Corporation, Japan","Tokyo, University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo Japan Science and Technology Corporation, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Tokyo, University, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047513472","display_name":"Takashi Chikayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Chikayama","raw_affiliation_strings":["University of Tokyo, Japan","Tokyo, University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Tokyo, University, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1997","issue":null,"first_page":"9 pp.","last_page":"9 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":0.9998999834060669,"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":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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/scalability","display_name":"Scalability","score":0.8630908727645874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7963396310806274},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6678427457809448},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6469079852104187},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6306842565536499},{"id":"https://openalex.org/keywords/dissemination","display_name":"Dissemination","score":0.6168947815895081},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5994773507118225},{"id":"https://openalex.org/keywords/heartbeat","display_name":"Heartbeat","score":0.5476318001747131},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5393758416175842},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.49688175320625305},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4916382431983948},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4248873293399811},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.42063796520233154},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3628673553466797},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16299983859062195},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08782434463500977}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8630908727645874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963396310806274},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6678427457809448},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6469079852104187},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6306842565536499},{"id":"https://openalex.org/C101780184","wikidata":"https://www.wikidata.org/wiki/Q840576","display_name":"Dissemination","level":2,"score":0.6168947815895081},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5994773507118225},{"id":"https://openalex.org/C13852961","wikidata":"https://www.wikidata.org/wiki/Q17021880","display_name":"Heartbeat","level":2,"score":0.5476318001747131},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5393758416175842},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.49688175320625305},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4916382431983948},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4248873293399811},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.42063796520233154},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3628673553466797},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16299983859062195},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08782434463500977},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/grid.2005.1542743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/grid.2005.1542743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 6th IEEE/ACM International Workshop on Grid Computing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.120.8837","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.120.8837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.logos.t.u-tokyo.ac.jp/~tau/papers/papers/horita-grid2005-scalable.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.543.4454","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.543.4454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.logos.ic.i.u-tokyo.ac.jp/~horita/thesis/grid05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1535772783","https://openalex.org/W1560512596","https://openalex.org/W1609618519","https://openalex.org/W1867704852","https://openalex.org/W1985006281","https://openalex.org/W2002162204","https://openalex.org/W2038562061","https://openalex.org/W2051975225","https://openalex.org/W2054129151","https://openalex.org/W2083209848","https://openalex.org/W2103075920","https://openalex.org/W2105227455","https://openalex.org/W2106991835","https://openalex.org/W2124617909","https://openalex.org/W2137042154","https://openalex.org/W2142590813","https://openalex.org/W2166755212","https://openalex.org/W3014366097","https://openalex.org/W4245605934","https://openalex.org/W4247100129","https://openalex.org/W4323053766","https://openalex.org/W6633392203","https://openalex.org/W6678459575"],"related_works":["https://openalex.org/W4385543909","https://openalex.org/W3039320222","https://openalex.org/W3199640442","https://openalex.org/W1898280036","https://openalex.org/W2315807364","https://openalex.org/W2382278803","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"Failure":[0],"detection":[1,77],"and":[2,22,33,67,114,128,144,167],"group":[3],"membership":[4],"management":[5],"are":[6,124],"basic":[7],"building":[8],"blocks":[9],"for":[10],"self-repairing":[11],"systems":[12],"in":[13,24,31,54,81],"distributed":[14],"environments,":[15,56],"which":[16],"need":[17],"to":[18,164],"be":[19,44,63,105],"scalable,":[20],"reliable,":[21],"efficient":[23],"practice.":[25],"As":[26],"available":[27],"resources":[28],"become":[29],"larger":[30],"size":[32],"more":[34,39],"widely":[35],"distributed,":[36],"it":[37,171],"is":[38],"essential":[40],"that":[41,79,101,133],"they":[42],"can":[43],"easily":[45],"used":[46],"with":[47,95,150],"a":[48,74,108,138,141,145],"small":[49,109],"amount":[50],"of":[51,111],"manual":[52,98],"configuration":[53,99],"grid":[55,82],"where":[57],"connectivities":[58],"between":[59],"different":[60],"networks":[61],"may":[62],"limited":[64],"by":[65,107],"firewalls":[66],"NATs.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,131],"present":[73],"scalable":[75],"failure":[76,85,135],"protocol":[78],"self-organizes":[80],"environments.":[83],"Our":[84],"detectors":[86],"autonomously":[87],"create":[88],"dispersed":[89],"monitoring":[90,120],"relationships":[91,121],"among":[92],"participating":[93],"processes":[94,152],"almost":[96],"no":[97],"so":[100],"each":[102],"process":[103],"will":[104],"monitored":[106],"number":[110],"other":[112],"processes,":[113],"quickly":[115],"disseminate":[116],"notifications":[117],"along":[118],"the":[119,159],"when":[122,158,170],"failures":[123],"detected.":[125],"With":[126],"simulations":[127],"real":[129],"experiments,":[130],"showed":[132],"our":[134],"detector":[136],"has":[137],"practical":[139],"scalability,":[140],"high":[142],"reliability,":[143],"good":[146],"efficiency.":[147],"The":[148],"overhead":[149],"313":[151],"was":[153,162,172],"at":[154],"most":[155],"2-percent":[156],"even":[157],"heartbeat":[160],"interval":[161],"set":[163],"0.1":[165],"second,":[166],"accordingly":[168],"smaller":[169],"longer.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
