{"id":"https://openalex.org/W7124930150","doi":"https://doi.org/10.1109/tc.2026.3655008","title":"Collaborative Prediction of Cloud DRAM Failures With Rules and Machine Learning","display_name":"Collaborative Prediction of Cloud DRAM Failures With Rules and Machine Learning","publication_year":2026,"publication_date":"2026-01-20","ids":{"openalex":"https://openalex.org/W7124930150","doi":"https://doi.org/10.1109/tc.2026.3655008"},"language":null,"primary_location":{"id":"doi:10.1109/tc.2026.3655008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2026.3655008","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5044580206","display_name":"Yaoguang Yong","orcid":null},"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":false,"raw_author_name":"Yaoguang Yong","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123387900","display_name":"Xiaoming 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":"Xiaoming Du","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123397054","display_name":"Yunong Wang","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":"Yunong Wang","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001471737","display_name":"Pengcheng Zhang","orcid":"https://orcid.org/0000-0002-2416-7556"},"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":false,"raw_author_name":"Pengcheng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-2416-7556","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043582893","display_name":"Xuhua Ma","orcid":"https://orcid.org/0009-0008-9852-2427"},"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":"Xuhua Ma","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bin Yao","orcid":"https://orcid.org/0000-0002-6478-4209"},"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":false,"raw_author_name":"Bin Yao","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-6478-4209","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060581895","display_name":"Xudong Zheng","orcid":"https://orcid.org/0009-0002-5629-5082"},"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":"Xudong Zheng","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Linquan Jiang","orcid":"https://orcid.org/0009-0001-5862-687X"},"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":"Linquan Jiang","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":"https://orcid.org/0009-0001-5862-687X","affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6106,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96469463,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"75","issue":"4","first_page":"1622","last_page":"1635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.4357999861240387,"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":0.4357999861240387,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.302700012922287,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.09929999709129333,"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/unavailability","display_name":"Unavailability","score":0.984499990940094},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.9146999716758728},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6696000099182129},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5787000060081482},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5138000249862671},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4616999924182892},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.40380001068115234}],"concepts":[{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.984499990940094},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.9146999716758728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550000190734863},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5271000266075134},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4065999984741211},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2778820799","wikidata":"https://www.wikidata.org/wiki/Q3454688","display_name":"Cost reduction","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2026.3655008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2026.3655008","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W429766147","https://openalex.org/W1559781097","https://openalex.org/W1978082708","https://openalex.org/W2009063162","https://openalex.org/W2118978333","https://openalex.org/W2120591095","https://openalex.org/W2142225982","https://openalex.org/W2490662969","https://openalex.org/W2664249172","https://openalex.org/W2772956929","https://openalex.org/W2883087177","https://openalex.org/W2903241786","https://openalex.org/W2908177913","https://openalex.org/W2983891539","https://openalex.org/W2989171707","https://openalex.org/W3009207130","https://openalex.org/W3023512926","https://openalex.org/W3093988908","https://openalex.org/W3116731709","https://openalex.org/W3132629440","https://openalex.org/W3167937798","https://openalex.org/W3205272658","https://openalex.org/W4213049518","https://openalex.org/W4226329490","https://openalex.org/W4248895726","https://openalex.org/W4287849472","https://openalex.org/W4313451571","https://openalex.org/W4321636490","https://openalex.org/W4360831854","https://openalex.org/W4385688947","https://openalex.org/W4399647672"],"related_works":[],"abstract_inverted_index":{"DRAM":[0,19,27],"faults":[1],"are":[2],"the":[3,85,122,126,146,176],"main":[4],"hardware":[5],"cause":[6,33],"of":[7,91],"node":[8,35,57,147],"unavailability":[9,58,148],"in":[10,38,50,175],"clouds.":[11],"To":[12],"enable":[13],"early":[14],"preventive":[15],"actions":[16],"and":[17,74,88,98,117,151,172],"mitigate":[18],"fault":[20],"impacts,":[21],"prior":[22],"studies":[23],"focus":[24],"on":[25],"predicting":[26],"uncorrectable":[28],"errors":[29],"(UEs)":[30],"that":[31,43,79,113,161],"typically":[32],"immediate":[34],"unavailability.":[36],"However,":[37],"Alibaba":[39],"Cloud,":[40],"we":[41,63,93,138],"observe":[42],"correctable":[44],"error(CE)":[45],"storm":[46],"(numerous":[47],"CEs":[48],"occur":[49],"a":[51,104,140],"short":[52],"period)":[53],"dominates":[54],"41%":[55],"DRAM-caused":[56],"(DCNU).":[59],"In":[60],"this":[61],"paper,":[62],"propose":[64,108,139],"to":[65,84,102,120,144],"predict":[66],"DCNU":[67,105],"by":[68,133],"taking":[69],"into":[70],"account":[71],"both":[72],"UEs":[73],"CE":[75],"storms.":[76],"Specifically,":[77],"observing":[78],"DCNUs":[80],"have":[81],"strong":[82],"relevance":[83],"temporal":[86],"statistics":[87],"spatial":[89],"patterns":[90],"CEs,":[92],"design":[94],"novel":[95,109],"spatio-temporal":[96],"features":[97],"use":[99],"soft":[100],"labels":[101],"build":[103],"predictor.":[106],"We":[107],"rule":[110],"mining":[111],"algorithms":[112],"can":[114],"generate":[115],"accurate":[116],"interpretable":[118],"rules":[119],"improve":[121],"prediction":[123],"performance.":[124],"Considering":[125],"predictor\u2019s":[127],"real":[128],"effects":[129],"cannot":[130],"be":[131],"evaluated":[132],"traditional":[134],"metrics":[135],"like":[136],"F1-score,":[137],"new":[141],"metric,":[142],"NURR,":[143],"quantify":[145],"reduction":[149],"rate":[150],"tune":[152],"model":[153],"hyperparameters":[154],"with":[155],"NURR.":[156],"The":[157],"comparative":[158],"study":[159],"shows":[160],"our":[162],"approach":[163],"achieves":[164],"over":[165],"40%":[166],"better":[167],"NURR":[168],"than":[169],"existing":[170],"methods":[171],"runs":[173],"stably":[174],"production":[177],"environment.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-21T00:00:00"}
