{"id":"https://openalex.org/W7150758300","doi":"https://doi.org/10.1109/access.2026.3681290","title":"DSFRO: Dynamic Scheduling and Fine-Grained Resource Optimization for Distributed Large Model Training in Heterogeneous Clusters","display_name":"DSFRO: Dynamic Scheduling and Fine-Grained Resource Optimization for Distributed Large Model Training in Heterogeneous Clusters","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7150758300","doi":"https://doi.org/10.1109/access.2026.3681290"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3681290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3681290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3681290","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"da Gao","orcid":"https://orcid.org/0009-0002-0317-0673"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"da Gao","raw_affiliation_strings":["China Telecom Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0317-0673","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116460447","display_name":"Guanlin Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanlin Dai","raw_affiliation_strings":["China Telecom Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9288-7803","affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133002821","display_name":"Lin Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Tian","raw_affiliation_strings":["China Telecom Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005812741","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-3465-6468"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["China Telecom Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133042286","display_name":"Liang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Guo","raw_affiliation_strings":["China Academy of Information and Communications Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Academy of Information and Communications Technology, Beijing, China","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133023011","display_name":"Chao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zheng","raw_affiliation_strings":["China Telecom Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69682129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"59409","last_page":"59421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6371999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.6371999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0430000014603138,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.027000000700354576,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/scheduling","display_name":"Scheduling (production processes)","score":0.6093999743461609},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5277000069618225},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.5246000289916992},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.42329999804496765},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.3698999881744385},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406000137329102},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6093999743461609},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.5246000289916992},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5130000114440918},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.42329999804496765},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C3017813396","wikidata":"https://www.wikidata.org/wiki/Q17078173","display_name":"Resource constraints","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3681290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3681290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4052fb497a3d4bf49fbbcf9290b2109e","is_oa":true,"landing_page_url":"https://doaj.org/article/4052fb497a3d4bf49fbbcf9290b2109e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 59409-59421 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3681290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3681290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,86,111,157],"exponential":[2],"evolution":[3],"of":[4,46,113],"artificial":[5],"intelligence":[6],"and":[7,19,33,65,91,104,138,147,164,177,192],"big":[8],"data":[9],"technologies,":[10],"distributed":[11,114,208],"large-scale":[12],"models":[13],"(such":[14],"as":[15,80,202],"Large":[16],"Language":[17],"Models":[18],"Foundation":[20],"Models)":[21],"have":[22],"become":[23],"pivotal":[24],"infrastructures":[25],"across":[26],"various":[27],"industrial":[28],"sectors,":[29],"including":[30],"finance,":[31],"healthcare,":[32],"autonomous":[34],"driving.":[35],"However,":[36],"training":[37,116,210],"these":[38,95],"models,":[39],"which":[40],"often":[41,77],"contain":[42],"billions":[43],"to":[44,62,84,189],"trillions":[45],"parameters,":[47],"presents":[48],"significant":[49],"challenges.":[50],"These":[51],"include":[52],"exorbitant":[53],"computational":[54],"resource":[55,67,129,150,182],"consumption,":[56],"complex":[57],"task":[58,72,145],"scheduling":[59,75,179,194],"requirements":[60],"due":[61],"heterogeneous":[63],"hardware,":[64],"suboptimal":[66],"utilization":[68,183],"caused":[69],"by":[70,117,185,196],"stochastic":[71],"loads.":[73],"Existing":[74],"frameworks":[76],"treat":[78],"resources":[79],"coarse-grained":[81],"units,":[82],"failing":[83],"capture":[85],"dynamic":[87,178],"interference":[88],"between":[89],"computation":[90],"communication.":[92],"To":[93],"address":[94],"issues,":[96],"this":[97],"paper":[98],"proposes":[99],"DSFRO,":[100],"a":[101,127,153,203],"Dynamic":[102],"Scheduling":[103],"Fine-Grained":[105],"Resource":[106],"Optimization":[107],"framework.":[108],"DSFRO":[109,172],"enhances":[110],"efficiency":[112],"large-model":[115],"leveraging":[118],"an":[119],"advanced":[120],"LSTM-based":[121],"task-load":[122],"prediction":[123],"model":[124],"combined":[125],"with":[126],"multi-dimensional":[128],"allocation":[130],"strategy":[131],"that":[132,171],"accounts":[133],"for":[134,206],"CPU,":[135],"GPU,":[136],"I/O,":[137],"network":[139],"bandwidth":[140],"simultaneously.":[141],"By":[142],"accurately":[143],"forecasting":[144],"loads":[146],"dynamically":[148],"optimizing":[149],"distribution":[151],"using":[152],"multi-objective":[154],"genetic":[155],"algorithm,":[156],"proposed":[158],"method":[159],"ensures":[160],"high":[161],"system":[162],"throughput":[163],"effective":[165],"load":[166],"balancing.":[167],"Experimental":[168],"results":[169],"demonstrate":[170],"significantly":[173],"outperforms":[174],"existing":[175],"static":[176],"approaches,":[180],"improving":[181],"rates":[184],"over":[186,197],"20%":[187],"compared":[188],"default":[190],"configurations":[191],"reducing":[193],"latency":[195],"40%,":[198],"indicating":[199],"its":[200],"potential":[201],"robust":[204],"solution":[205],"next-generation":[207],"AI":[209],"environments.":[211]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-04-07T00:00:00"}