{"id":"https://openalex.org/W7225433507","doi":"https://doi.org/10.5281/zenodo.24004923","title":"Predictive Computing Simulation Environment for Generative AI: Modeling Heterogeneous Request Distributions, Hardware Configurations, and Dynamic Computational Pricing","display_name":"Predictive Computing Simulation Environment for Generative AI: Modeling Heterogeneous Request Distributions, Hardware Configurations, and Dynamic Computational Pricing","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225433507","doi":"https://doi.org/10.5281/zenodo.24004923"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24004923","doi":"https://doi.org/10.5281/zenodo.24004923","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24004923","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.24004923","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9692000150680542,"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":0.9692000150680542,"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":0.013000000268220901,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.00800000037997961,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8960000276565552},{"id":"https://openalex.org/keywords/electricity-pricing","display_name":"electricity pricing","score":0.8450000286102295},{"id":"https://openalex.org/keywords/speculative-computation","display_name":"speculative computation","score":0.6150000095367432},{"id":"https://openalex.org/keywords/resource-orchestration","display_name":"resource orchestration","score":0.5389999747276306},{"id":"https://openalex.org/keywords/discrete-event-simulation","display_name":"discrete event simulation","score":0.6349999904632568},{"id":"https://openalex.org/keywords/workload-modeling","display_name":"workload modeling","score":0.4779999852180481},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"energy consumption","score":0.515999972820282},{"id":"https://openalex.org/keywords/response-latency","display_name":"response latency","score":0.6060000061988831},{"id":"https://openalex.org/keywords/gpu-memory-constraints","display_name":"GPU memory constraints","score":0.42100000381469727},{"id":"https://openalex.org/keywords/heterogeneous-hardware","display_name":"heterogeneous hardware","score":0.5049999952316284},{"id":"https://openalex.org/keywords/simulation-environment","display_name":"simulation environment","score":0.44600000977516174},{"id":"https://openalex.org/keywords/resource-contention","display_name":"resource contention","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113999962806702},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6581000089645386},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5206999778747559},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C85106507","wikidata":"https://www.wikidata.org/wiki/Q1188445","display_name":"Utility computing","level":4,"score":0.27730000019073486},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24004923","doi":"https://doi.org/10.5281/zenodo.24004923","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24004923","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.24004924","doi":"https://doi.org/10.5281/zenodo.24004924","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24004924","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.24004923","doi":"https://doi.org/10.5281/zenodo.24004923","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24004923","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/W7225405760","https://openalex.org/W7225400146","https://openalex.org/W7225409594","https://openalex.org/W7225376051","https://openalex.org/W7225423500","https://openalex.org/W7225425116","https://openalex.org/W7225267314","https://openalex.org/W7225375373","https://openalex.org/W7225431696","https://openalex.org/W7225396636"],"abstract_inverted_index":{"The":[0,147,190,310],"development":[1],"of":[2,26,69,356],"predictive":[3,33,44,140,163,184,347,362],"computing":[4,34,141],"for":[5,14,123,320,324,331,339],"generative":[6],"artificial":[7],"intelligence":[8],"(AI)":[9],"has":[10,36],"introduced":[11],"new":[12],"opportunities":[13],"anticipating":[15],"computational":[16,42,74,135,218,229,291],"demand,":[17],"preparing":[18],"inference":[19,280],"resources,":[20],"and":[21,47,94,137,157,165,171,177,182,187,202,217,237,257,278,303,335,364,374,381],"optimizing":[22],"the":[23,118,357],"economic":[24,304],"efficiency":[25],"large":[27],"language":[28],"model":[29,133],"(LLM)":[30],"services.":[31],"Existing":[32],"research":[35],"investigated":[37],"future":[38],"request":[39,83,159,194,209,268],"prediction,":[40],"proactive":[41],"preparation,":[43],"infrastructure":[45,172],"orchestration,":[46],"economic-aware":[48,365],"resource":[49,96,254,274,301],"scheduling.":[50],"However,":[51],"evaluating":[52,321],"these":[53],"approaches":[54],"under":[55,103,113,143,360],"a":[56,127,316],"single":[57],"workload,":[58],"hardware":[59,170],"configuration,":[60],"or":[61,110],"pricing":[62,180],"environment":[63,149,312],"may":[64,107],"provide":[65,367],"an":[66],"incomplete":[67],"understanding":[68],"their":[70],"practical":[71,375],"effectiveness.":[72],"Predictive":[73,119,322,328,337],"strategies":[75,142],"are":[76,243],"inherently":[77],"sensitive":[78],"to":[79,132,266,288,379],"environmental":[80,358],"conditions,":[81],"including":[82,197,226],"arrival":[84,195],"distributions,":[85,196],"workload":[86,160],"characteristics,":[87],"GPU":[88,179,224,252,295],"capabilities,":[89],"memory":[90,231],"limitations,":[91],"electricity":[92,176,247],"prices,":[93,253],"cloud":[95,178,238,251],"costs.":[97],"A":[98,260,282],"strategy":[99],"that":[100,346],"provides":[101],"benefits":[102,305],"one":[104],"operating":[105,145],"condition":[106],"become":[108],"inefficient":[109],"even":[111],"counterproductive":[112],"another.":[114],"This":[115],"paper":[116],"introduces":[117],"Computing":[120,323,338],"Simulation":[121],"Environment":[122],"Generative":[124,325,332,340],"AI":[125,326,333,341],"(PCSE-GAI),":[126],"configurable":[128,246],"simulation":[129,153,262,371],"framework":[130,191],"designed":[131],"heterogeneous":[134,169,223],"environments":[136],"systematically":[138],"evaluate":[139],"diverse":[144],"conditions.":[146],"proposed":[148,311],"integrates":[150],"five":[151],"interconnected":[152],"components:":[154],"(1)":[155],"synthetic":[156],"trace-driven":[158],"generation,":[161],"(2)":[162],"demand":[164],"forecasting":[166],"simulation,":[167,181],"(3)":[168],"modeling,":[173],"(4)":[174],"dynamic":[175],"(5)":[183],"computation":[185,348],"execution":[186,235],"performance":[188],"evaluation.":[189],"supports":[192],"multiple":[193],"stationary,":[198],"nonstationary,":[199],"bursty,":[200],"periodic,":[201],"heavy-tailed":[203],"workloads,":[204],"together":[205],"with":[206],"variations":[207],"in":[208,228],"complexity,":[210],"semantic":[211],"recurrence,":[212],"prompt":[213],"length,":[214,216],"output":[215],"requirements.":[219],"It":[220],"further":[221],"models":[222],"configurations,":[225],"differences":[227],"throughput,":[230],"capacity,":[232],"energy":[233,299],"consumption,":[234,300],"overhead,":[236],"instance":[239],"availability.":[240],"Economic":[241],"conditions":[242,359],"represented":[244],"through":[245],"price":[248],"trajectories,":[249],"time-dependent":[250],"allocation":[255],"costs,":[256],"interruption-related":[258],"expenditure.":[259],"discrete-event":[261],"architecture":[263],"is":[264,286,313,349],"formulated":[265],"coordinate":[267],"arrivals,":[269],"prediction":[270,293],"decisions,":[271],"speculative":[272],"computation,":[273],"contention,":[275],"cache":[276],"operations,":[277],"online":[279],"execution.":[281],"unified":[283],"evaluation":[284],"methodology":[285],"established":[287],"measure":[289],"total":[290],"expenditure,":[292],"effectiveness,":[294],"utilization,":[296],"response":[297],"latency,":[298],"efficiency,":[302],"across":[306],"different":[307],"experimental":[308,318],"scenarios.":[309],"positioned":[314],"as":[315],"reproducible":[317],"foundation":[319],"(PCGA),":[327],"Computational":[329],"Orchestration":[330],"(PCO-GAI),":[334],"Economic-Aware":[336],"(EAPC-GAI).":[342],"Rather":[343],"than":[344],"assuming":[345],"universally":[350],"advantageous,":[351],"PCSE-GAI":[352],"enables":[353],"systematic":[354],"investigation":[355],"which":[361],"preparation":[363],"orchestration":[366],"measurable":[368],"benefits.":[369],"Its":[370],"fidelity,":[372],"generalizability,":[373],"usefulness":[376],"remain":[377],"subject":[378],"implementation":[380],"empirical":[382],"validation.":[383]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}