{"id":"https://openalex.org/W3167937798","doi":"https://doi.org/10.1109/vts50974.2021.9441059","title":"On Workload-Aware DRAM Failure Prediction in Large-Scale Data Centers","display_name":"On Workload-Aware DRAM Failure Prediction in Large-Scale Data Centers","publication_year":2021,"publication_date":"2021-04-25","ids":{"openalex":"https://openalex.org/W3167937798","doi":"https://doi.org/10.1109/vts50974.2021.9441059","mag":"3167937798"},"language":"en","primary_location":{"id":"doi:10.1109/vts50974.2021.9441059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vts50974.2021.9441059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 39th VLSI Test Symposium (VTS)","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/A5100737866","display_name":"Xingyi Wang","orcid":"https://orcid.org/0009-0005-3388-9808"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingyi Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345728","display_name":"Yu Li","orcid":"https://orcid.org/0000-0002-2246-8005"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053247827","display_name":"Yiquan Chen","orcid":"https://orcid.org/0009-0004-8714-6949"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiquan Chen","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723323","display_name":"Shiwen Wang","orcid":"https://orcid.org/0000-0001-6294-4865"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Wang","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102224851","display_name":"Yin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Du","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330315","display_name":"Cheng He","orcid":"https://orcid.org/0000-0001-6337-6046"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng He","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736149","display_name":"Yu\u2010Zhong Zhang","orcid":"https://orcid.org/0000-0002-2017-1005"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YuZhong Zhang","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070710885","display_name":"Pinan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinan Chen","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353869","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-4510-2436"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101877063","display_name":"Wenjun Song","orcid":"https://orcid.org/0000-0002-4397-1363"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Song","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088556682","display_name":"Qiang Xu","orcid":"https://orcid.org/0000-0001-6747-126X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang xu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China","The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677298","display_name":"Li Jiang","orcid":"https://orcid.org/0009-0001-8085-3788"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5100737866"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.8386,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91831997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9922000169754028,"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":0.9922000169754028,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9876999855041504,"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":0.9764000177383423,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.9369637370109558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8014506101608276},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5132879614830017},{"id":"https://openalex.org/keywords/universal-memory","display_name":"Universal memory","score":0.5128248333930969},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5066664814949036},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.48350122570991516},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3739117681980133},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3349938690662384},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3285199999809265},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24178194999694824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17955273389816284},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.1573050320148468},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.13442331552505493},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09568223357200623}],"concepts":[{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.9369637370109558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014506101608276},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5132879614830017},{"id":"https://openalex.org/C195053848","wikidata":"https://www.wikidata.org/wiki/Q7894141","display_name":"Universal memory","level":5,"score":0.5128248333930969},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5066664814949036},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.48350122570991516},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3739117681980133},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3349938690662384},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3285199999809265},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24178194999694824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17955273389816284},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.1573050320148468},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.13442331552505493},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09568223357200623},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vts50974.2021.9441059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vts50974.2021.9441059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 39th VLSI Test Symposium (VTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1559781097","https://openalex.org/W1678356000","https://openalex.org/W2018913979","https://openalex.org/W2021708499","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2149706766","https://openalex.org/W2295598076","https://openalex.org/W2752311492","https://openalex.org/W2772956929","https://openalex.org/W2911964244","https://openalex.org/W3004493283","https://openalex.org/W3009207130","https://openalex.org/W3102476541","https://openalex.org/W4236137412"],"related_works":["https://openalex.org/W2516517078","https://openalex.org/W2161286015","https://openalex.org/W2150909864","https://openalex.org/W4382618825","https://openalex.org/W4386903460","https://openalex.org/W2900372418","https://openalex.org/W2924367614","https://openalex.org/W4211178602","https://openalex.org/W2094308961","https://openalex.org/W1992487929"],"abstract_inverted_index":{"DRAM":[0,37,104,118,137,145,152,162],"failures":[1,38],"are":[2,51,87,100,174],"one":[3],"of":[4,12,115,169],"the":[5,10,17,55,66,84,94,113,122,151,167,179,202],"major":[6,60],"hardware":[7],"threats":[8],"to":[9,25,31,149,165,201],"reliability":[11],"large-scale":[13],"data":[14,186],"centers":[15],"since":[16],"uncorrectable":[18],"errors":[19,49,82],"in":[20,39],"DRAMs":[21,75],"may":[22],"cause":[23],"servers":[24],"shut":[26],"down.":[27],"Existing":[28],"works":[29],"try":[30],"solve":[32],"this":[33,108],"problem":[34],"by":[35,70,89],"predicting":[36],"advance":[40],"with":[41],"Machine":[42],"Learning":[43],"models.":[44],"In":[45,107],"these":[46],"works,":[47],"correctable":[48],"(CEs)":[50],"generally":[52],"deemed":[53],"as":[54,80],"most":[56],"important":[57,102],"feature.":[58],"The":[59,188],"reason":[61],"behind":[62],"CEs'":[63],"emergence":[64],"is":[65],"accumulated":[67],"stress":[68],"caused":[69],"intensive":[71],"workloads.":[72,92],"Moreover,":[73],"defective":[74,85],"will":[76],"not":[77],"manifest":[78],"themselves":[79],"system":[81],"until":[83],"cells":[86],"accessed":[88],"some":[90],"specific":[91],"Therefore,":[93],"running":[95],"workloads":[96,116],"on":[97,112,117,178],"a":[98,183],"server":[99],"also":[101],"for":[103,161],"failure":[105,163],"prediction.":[106],"paper,":[109],"we":[110,142],"focus":[111],"impact":[114],"failures.":[119],"We":[120,155],"design":[121],"workload":[123],"features":[124,196],"from":[125,182],"both":[126,192],"macroscopical":[127],"and":[128,135,194],"microscopical":[129],"aspects,":[130],"i.e.":[131],"node-level":[132],"performance":[133],"metrics":[134],"cell-level":[136],"access":[138,153],"pattern,":[139],"respectively.":[140],"Furthermore,":[141],"propose":[143],"Hierarchical":[144],"Error":[146],"Code":[147],"(HiDEC)":[148],"represent":[150],"pattern.":[154],"leverage":[156],"several":[157],"Decision":[158],"Tree-based":[159],"models":[160],"prediction":[164,203],"highlight":[166],"generality":[168],"our":[170],"designed":[171],"features.":[172],"Experiments":[173],"carried":[175],"out":[176],"based":[177],"dataset":[180],"collected":[181],"real-world":[184],"commercial":[185],"center.":[187],"results":[189],"show":[190],"that":[191],"macroscopic":[193],"microscopic":[195],"can":[197],"bring":[198],"significant":[199],"improvements":[200],"performance.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
