{"id":"https://openalex.org/W7225398353","doi":"https://doi.org/10.5281/zenodo.24001170","title":"Predictive Cost Budget Control for Generative AI: Forecasting Future Computational Expenditure and Proactively Allocating Financial Resources","display_name":"Predictive Cost Budget Control for Generative AI: Forecasting Future Computational Expenditure and Proactively Allocating Financial Resources","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225398353","doi":"https://doi.org/10.5281/zenodo.24001170"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24001170","doi":"https://doi.org/10.5281/zenodo.24001170","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24001170","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.24001170","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":0.9961000084877014,"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":0.9961000084877014,"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":0.0017999999690800905,"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/T12127","display_name":"Software System Performance and Reliability","score":0.00019999999494757503,"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/budgeting","display_name":"budgeting","score":0.5410000085830688},{"id":"https://openalex.org/keywords/large-language-model-inference","display_name":"large language model inference","score":0.8029999732971191},{"id":"https://openalex.org/keywords/rolling-horizon-optimization","display_name":"rolling horizon optimization","score":0.890999972820282},{"id":"https://openalex.org/keywords/service-level-requirements","display_name":"service level requirements","score":0.7429999709129333},{"id":"https://openalex.org/keywords/cost-aware-scheduling","display_name":"cost-aware scheduling","score":0.5080000162124634},{"id":"https://openalex.org/keywords/service-reliability","display_name":"service reliability","score":0.6370000243186951},{"id":"https://openalex.org/keywords/cost-overruns","display_name":"cost overruns","score":0.7080000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088000178337097},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.506600022315979},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C119693030","wikidata":"https://www.wikidata.org/wiki/Q2180497","display_name":"Economic model","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24001170","doi":"https://doi.org/10.5281/zenodo.24001170","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24001170","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.24001171","doi":"https://doi.org/10.5281/zenodo.24001171","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24001171","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.24001170","doi":"https://doi.org/10.5281/zenodo.24001170","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24001170","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225423500","https://openalex.org/W7225381813","https://openalex.org/W7225405760","https://openalex.org/W7225376051","https://openalex.org/W7225390624","https://openalex.org/W7225431696","https://openalex.org/W7225267314","https://openalex.org/W7225409594","https://openalex.org/W7225392331","https://openalex.org/W7225425116"],"abstract_inverted_index":{"The":[0,166,236,289,346],"increasing":[1],"deployment":[2],"of":[3,57,198,213,374,386],"generative":[4,34,392],"artificial":[5],"intelligence":[6],"(AI)":[7],"systems":[8],"has":[9],"introduced":[10],"substantial":[11],"and":[12,30,88,120,159,191,217,232,249,281,302,328,340,371,400,405],"increasingly":[13],"variable":[14],"computational":[15,28,39,59,69,86,115,131,145,157,215,273,325,356,364,375,398],"expenditure":[16,40,56,87,116,132,174,181,188,274,297,318,336],"associated":[17],"with":[18,332],"large":[19],"language":[20],"model":[21,24],"(LLM)":[22],"inference,":[23],"serving,":[25],"response":[26],"generation,":[27],"preparation,":[29,158],"distributed":[31],"execution.":[32],"As":[33],"AI":[35,106,393],"services":[36],"expand,":[37],"controlling":[38],"becomes":[41],"an":[42,80,383],"important":[43],"infrastructure":[44,394],"management":[45,395],"problem.":[46],"Existing":[47],"cost":[48,177],"optimization":[49,265],"approaches":[50,75],"primarily":[51],"focus":[52],"on":[53],"reducing":[54],"the":[55,93,199,209,368,408],"individual":[58],"operations,":[60],"selecting":[61],"lower-cost":[62],"resources,":[63],"or":[64],"monitoring":[65],"accumulated":[66],"spending":[67],"after":[68,139],"activities":[70],"have":[71,257],"occurred.":[72],"However,":[73],"these":[74,255],"do":[76],"not":[77,349],"necessarily":[78],"provide":[79],"explicit":[81,384],"mechanism":[82,206],"for":[83,104,225,260],"predicting":[84],"future":[85,114,144,170,214,287,363,414],"allocating":[89],"financial":[90,124,160,193,211,251,283,304,372,379,409],"resources":[91],"before":[92,163],"corresponding":[94],"workloads":[95,216],"materialize.":[96],"This":[97],"paper":[98],"introduces":[99,292],"Predictive":[100],"Cost":[101],"Budget":[102],"Control":[103],"Generative":[105],"(PCBC-GAI),":[107],"a":[108,134,202],"conceptual":[109],"framework":[110,168,200,237,290],"that":[111,136,150,207,254,351],"investigates":[112,360],"how":[113,219],"can":[117,151,366],"be":[118,223],"forecast":[119,241],"proactively":[121,406],"incorporated":[122],"into":[123],"budget":[125,183,186,204,221,277,294,300,315,320,323,380],"allocation":[126,205,316],"decisions.":[127],"Rather":[128],"than":[129],"treating":[130],"as":[133,147,382],"consequence":[135],"is":[137,201,267,309],"evaluated":[138],"inference":[140,176,234],"execution,":[141],"PCBC-GAI":[142,389],"considers":[143],"costs":[146,365],"predictive":[148,185,203,296,352,387,391],"variables":[149],"influence":[152],"resource":[153,161,180,401],"authorization,":[154],"task":[155],"selection,":[156],"distribution":[162],"execution":[164],"begins.":[165],"proposed":[167],"integrates":[169],"workload":[171],"forecasting,":[172],"GPU":[173],"prediction,":[175],"estimation,":[178],"cloud":[179],"modeling,":[182],"reservation,":[184],"allocation,":[187,295],"risk":[189],"assessment,":[190],"adaptive":[192,299],"control.":[194],"A":[195,263],"central":[196],"component":[197],"estimates":[208],"expected":[210,271],"requirements":[212,402],"determines":[218],"much":[220],"should":[222],"reserved":[224,245],"anticipated":[226],"demand,":[227],"discretionary":[228],"precomputation,":[229],"uncertain":[230,286],"workloads,":[231],"unexpected":[233,322],"requirements.":[235],"further":[238],"distinguishes":[239],"between":[240],"expenditure,":[242,244,248],"committed":[243],"budget,":[246],"realized":[247],"available":[250],"capacity,":[252],"recognizing":[253],"quantities":[256],"different":[258],"implications":[259],"operational":[261],"decision-making.":[262],"rolling-horizon":[264],"formulation":[266],"developed":[268],"to":[269,311,412],"minimize":[270],"total":[272],"while":[275],"maintaining":[276],"feasibility,":[278],"service-level":[279],"requirements,":[280],"sufficient":[282],"reserves":[284],"under":[285],"demand.":[288,415],"also":[291],"uncertainty-aware":[293],"thresholds,":[298],"reallocation,":[301],"task-level":[303],"authorization.":[305],"An":[306],"experimental":[307],"methodology":[308],"established":[310],"evaluate":[312],"forecasting":[313],"accuracy,":[314],"efficiency,":[317],"deviations,":[319],"utilization,":[321],"overruns,":[324],"completion":[326],"rates,":[327],"service":[329],"reliability.":[330],"Comparisons":[331],"fixed":[333],"budgeting,":[334,339],"reactive":[335],"monitoring,":[337],"historical-average":[338],"conventional":[341],"cost-aware":[342],"scheduling":[343],"are":[344],"proposed.":[345],"research":[347],"does":[348],"assume":[350],"budgeting":[353],"automatically":[354],"reduces":[355],"expenditure.":[357],"Instead,":[358],"it":[359],"whether":[361],"anticipating":[362,397,404],"improve":[367],"timing,":[369],"distribution,":[370],"control":[373],"resources.":[376],"By":[377],"introducing":[378],"anticipation":[381],"layer":[385],"computing,":[388],"extends":[390],"from":[396],"demand":[399],"toward":[403],"managing":[407],"commitments":[410],"required":[411],"satisfy":[413]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}