{"id":"https://openalex.org/W7225377014","doi":"https://doi.org/10.5281/zenodo.24000004","title":"Predictive Distributed Computing for Generative AI: Anticipating Cross-Node Computational Demand and Preparing Distributed Execution Resources Before Requests Arrive","display_name":"Predictive Distributed Computing for Generative AI: Anticipating Cross-Node Computational Demand and Preparing Distributed Execution Resources Before Requests Arrive","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225377014","doi":"https://doi.org/10.5281/zenodo.24000004"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24000004","doi":"https://doi.org/10.5281/zenodo.24000004","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24000004","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24000004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.7612000107765198,"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":0.7612000107765198,"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":0.2045000046491623,"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/T14098","display_name":"Energy Efficiency in Computing","score":0.011800000444054604,"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/large-language-model-inference","display_name":"large language model inference","score":0.9179999828338623},{"id":"https://openalex.org/keywords/workload-prediction","display_name":"workload prediction","score":0.8339999914169312},{"id":"https://openalex.org/keywords/data-replication","display_name":"data replication","score":0.7269999980926514},{"id":"https://openalex.org/keywords/data-migration","display_name":"data migration","score":0.6890000104904175},{"id":"https://openalex.org/keywords/communication-resource-allocation","display_name":"communication resource allocation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/node-selection","display_name":"node selection","score":0.6200000047683716},{"id":"https://openalex.org/keywords/workload-placement","display_name":"workload placement","score":0.703000009059906},{"id":"https://openalex.org/keywords/data-locality","display_name":"data locality","score":0.4189999997615814},{"id":"https://openalex.org/keywords/network-latency","display_name":"network latency","score":0.3869999945163727},{"id":"https://openalex.org/keywords/gpu-utilization","display_name":"GPU utilization","score":0.6510000228881836},{"id":"https://openalex.org/keywords/task-completion-time","display_name":"task completion time","score":0.6200000047683716},{"id":"https://openalex.org/keywords/service-reliability","display_name":"service reliability","score":0.6769999861717224},{"id":"https://openalex.org/keywords/task-scheduling","display_name":"task scheduling","score":0.3930000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8547000288963318},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7882000207901001},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5442000031471252},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C3739613","wikidata":"https://www.wikidata.org/wiki/Q679003","display_name":"Distributed Computing Environment","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2776174695","wikidata":"https://www.wikidata.org/wiki/Q5283162","display_name":"Distributed management","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24000004","doi":"https://doi.org/10.5281/zenodo.24000004","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24000004","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24000005","doi":"https://doi.org/10.5281/zenodo.24000005","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24000005","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24000004","doi":"https://doi.org/10.5281/zenodo.24000004","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24000004","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225376051","https://openalex.org/W7225416383","https://openalex.org/W7225375373","https://openalex.org/W7225405760","https://openalex.org/W7225390238","https://openalex.org/W7225267314","https://openalex.org/W7225425116","https://openalex.org/W7225397015","https://openalex.org/W7225396760","https://openalex.org/W7225405737"],"abstract_inverted_index":{"The":[0,178,278,388],"increasing":[1],"computational":[2,60,70,121,154,167,192,234,269,307,368,420,428],"complexity":[3],"of":[4,39,284,292,324,418,433],"generative":[5,445],"artificial":[6],"intelligence":[7],"(AI)":[8],"systems":[9,57],"has":[10],"created":[11],"growing":[12],"demand":[13,264],"for":[14,109,135],"distributed":[15,27,31,141,187,215,262,293,349,354,382,395,434],"inference":[16,44],"infrastructures":[17,447],"involving":[18],"multiple":[19,153],"GPUs,":[20],"computing":[21,32,425],"nodes,":[22,155,159,274],"storage":[23],"systems,":[24],"and":[25,52,62,88,126,164,173,199,206,218,223,250,265,275,304,319,338,362,385,415,463],"geographically":[26],"execution":[28,142,216,235,294,383,435,472],"environments.":[29],"Although":[30],"techniques":[33],"have":[34],"substantially":[35],"improved":[36],"the":[37,267,289,416,465],"scalability":[38],"large":[40],"language":[41],"model":[42,50,297],"(LLM)":[43],"through":[45],"parallel":[46],"execution,":[47,355],"workload":[48,95,188,200,405],"partitioning,":[49],"distribution,":[51],"communication":[53,81,162,174,210,240,302,372,411],"optimization,":[54],"most":[55],"existing":[56],"primarily":[58],"determine":[59],"placement":[61],"data":[63,85,169,204,242,276,299,313,317,379,413],"transfer":[64,380],"operations":[65],"after":[66],"actual":[67],"requests":[68,130],"or":[69,100],"workloads":[71,148],"become":[72],"available.":[73],"This":[74,103],"reactive":[75,353],"operational":[76],"paradigm":[77,442],"may":[78,326],"introduce":[79],"avoidable":[80],"overhead,":[82,247,381],"resource":[83,211,263,360],"contention,":[84],"movement":[86,205,323],"delays,":[87],"cross-node":[89,120,191],"coordination":[90,432],"costs,":[91,236,239,412],"particularly":[92],"when":[93,330],"future":[94,119,147,272,332],"characteristics":[96],"exhibit":[97],"predictable":[98],"temporal":[99],"structural":[101],"patterns.":[102],"paper":[104],"introduces":[105],"Predictive":[106],"Distributed":[107],"Computing":[108],"Generative":[110],"AI":[111,446],"(PDC-GAI),":[112],"a":[113,440],"conceptual":[114],"framework":[115,279,389],"that":[116,321,393,459],"investigates":[117,280,439],"whether":[118,281],"requirements":[122],"can":[123,287],"be":[124,327,454,469],"anticipated":[125],"prepared":[127],"before":[128,471],"corresponding":[129],"materialize.":[131],"Rather":[132],"than":[133],"waiting":[134],"an":[136],"incoming":[137],"request":[138],"to":[139,151,231,346,430],"trigger":[140],"planning,":[143],"PDC-GAI":[144],"predicts":[145],"which":[146,444],"are":[149],"likely":[150],"require":[152],"identifies":[156],"potentially":[157],"participating":[158],"estimates":[160],"inter-node":[161,301],"requirements,":[163],"selectively":[165],"prepares":[166],"resources,":[168],"replicas,":[170],"intermediate":[171,306],"representations,":[172],"paths":[175],"in":[176,443],"advance.":[177],"proposed":[179,345],"architecture":[180],"integrates":[181],"seven":[182],"interconnected":[183],"functions:":[184],"(1)":[185],"predictive":[186,196,209,312,316,348,359,394,424],"identification,":[189],"(2)":[190],"dependency":[193],"prediction,":[194],"(3)":[195],"node":[197,244,407],"selection":[198],"placement,":[201,298],"(4)":[202],"proactive":[203,290],"replication,":[207],"(5)":[208],"allocation,":[212,361],"(6)":[213],"uncertainty-aware":[214],"coordination,":[217],"(7)":[219],"adaptive":[220],"computational-state":[221],"synchronization":[222,246],"evaluation.":[224],"A":[225,254],"unified":[226],"optimization":[227],"formulation":[228],"is":[229,257,344,397],"developed":[230],"jointly":[232],"consider":[233],"network":[237,370,409],"transmission":[238],"latency,":[241,373],"availability,":[243,408],"utilization,":[245,378],"replication":[248,314],"expenditure,":[249,369],"task":[251,374],"completion":[252,375],"deadlines.":[253],"central":[255],"distinction":[256],"established":[258],"between":[259],"predicting":[260,266],"aggregate":[261],"specific":[268],"relationships":[270,286],"among":[271],"workloads,":[273],"dependencies.":[277,421],"advance":[282,322,427,431],"knowledge":[283],"these":[285],"support":[288],"preparation":[291,350,429],"environments,":[295,436],"including":[296],"localization,":[300],"capacity,":[303],"reusable":[305],"states.":[308],"It":[309],"further":[310],"distinguishes":[311],"from":[315,426],"migration":[318],"recognizes":[320],"information":[325,467],"beneficial":[328],"only":[329,450],"expected":[331],"reuse":[333],"justifies":[334],"its":[335],"transfer,":[336],"storage,":[337],"consistency-maintenance":[339],"costs.":[340],"An":[341],"experimental":[342],"methodology":[343],"compare":[347],"against":[351],"conventional":[352],"traditional":[356],"workload-aware":[357],"scheduling,":[358],"communication-unaware":[363],"precomputation.":[364],"Evaluation":[365],"considers":[366],"total":[367],"traffic,":[371],"time,":[376],"GPU":[377],"efficiency,":[384],"service":[386],"reliability.":[387],"does":[390],"not":[391,449],"assume":[392],"computation":[396,452,460],"universally":[398],"beneficial.":[399],"Its":[400],"practical":[401],"effectiveness":[402],"depends":[403],"on":[404],"predictability,":[406],"topology,":[410],"compatibility,":[414],"reliability":[417],"predicted":[419],"By":[422],"extending":[423],"this":[437],"research":[438],"broader":[441],"anticipate":[448],"what":[451],"will":[453],"required,":[455],"but":[456],"also":[457],"where":[458],"should":[461,468],"occur":[462],"how":[464],"necessary":[466],"positioned":[470],"begins.":[473]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}