{"id":"https://openalex.org/W7225425602","doi":"https://doi.org/10.5281/zenodo.23997416","title":"Predictive Thermal Management for Generative AI: Forecasting GPU Temperature and Anticipating Thermal Constraints Before Computational Execution","display_name":"Predictive Thermal Management for Generative AI: Forecasting GPU Temperature and Anticipating Thermal Constraints Before Computational Execution","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225425602","doi":"https://doi.org/10.5281/zenodo.23997416"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23997416","doi":"https://doi.org/10.5281/zenodo.23997416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997416","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.23997416","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9765999913215637,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9765999913215637,"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/T14098","display_name":"Energy Efficiency in Computing","score":0.0071000000461936,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.006899999920278788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/thermal-constraints","display_name":"thermal constraints","score":0.7160000205039978},{"id":"https://openalex.org/keywords/thermal-aware-scheduling","display_name":"thermal-aware scheduling","score":0.8830000162124634},{"id":"https://openalex.org/keywords/gpu-resource-allocation","display_name":"GPU resource allocation","score":0.8539999723434448},{"id":"https://openalex.org/keywords/workload-distribution","display_name":"workload distribution","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651000022888184},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.40389999747276306},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.3702999949455261},{"id":"https://openalex.org/C204530211","wikidata":"https://www.wikidata.org/wiki/Q752823","display_name":"Thermal","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.2921999990940094},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C70452415","wikidata":"https://www.wikidata.org/wiki/Q3182448","display_name":"Predictive maintenance","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.2563999891281128}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23997416","doi":"https://doi.org/10.5281/zenodo.23997416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997416","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.23997417","doi":"https://doi.org/10.5281/zenodo.23997417","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997417","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.23997416","doi":"https://doi.org/10.5281/zenodo.23997416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997416","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/W7225234645","https://openalex.org/W7225392849","https://openalex.org/W4408100911","https://openalex.org/W7225432460","https://openalex.org/W7225384738","https://openalex.org/W7225375373","https://openalex.org/W7225378531","https://openalex.org/W7225408802","https://openalex.org/W7225405737","https://openalex.org/W7225405760"],"abstract_inverted_index":{"The":[0,156,247],"increasing":[1],"deployment":[2],"of":[3,107,116,262,273,350],"generative":[4,377],"artificial":[5],"intelligence":[6],"(AI)":[7],"systems":[8,47],"has":[9,75],"intensified":[10],"the":[11,105,113,260,270,315,348],"computational":[12,85,136,171,194,210,230,303,331,360],"demands":[13],"placed":[14],"on":[15,60,337],"GPU-based":[16],"inference":[17,199,242,312],"infrastructure.":[18,379],"Large":[19],"language":[20],"models":[21],"(LLMs),":[22],"image-generation":[23],"systems,":[24],"video-generation":[25],"models,":[26],"and":[27,38,53,63,112,152,177,215,231,244,259,280,310,347],"multimodal":[28],"AI":[29,95,378],"applications":[30],"execute":[31],"computationally":[32],"intensive":[33],"operations":[34],"that":[35,100,321],"produce":[36],"substantial":[37],"dynamically":[39],"varying":[40],"GPU":[41,45,73,109,122,142,159,174,239,252,275,278,305,369],"workloads.":[42],"Although":[43],"existing":[44],"management":[46,57,115,371],"monitor":[48],"temperature,":[49,151,253,256],"power":[50,144],"consumption,":[51,145,307],"utilization,":[52,143],"hardware":[54],"performance,":[55],"thermal":[56,80,110,117,154,165,179,257,265,271,299,342,356],"frequently":[58],"relies":[59],"current":[61],"measurements":[62],"reactive":[64,368],"control":[65],"mechanisms.":[66],"Such":[67],"approaches":[68],"may":[69],"respond":[70],"only":[71],"after":[72],"temperature":[74,123,132,163,187,237,296,322,370],"already":[76],"increased":[77],"substantially":[78],"or":[79,329],"constraints":[81],"have":[82],"begun":[83],"affecting":[84],"performance.":[86,332],"This":[87],"paper":[88],"introduces":[89],"Predictive":[90],"Thermal":[91],"Management":[92],"for":[93,376],"Generative":[94],"(PTM-GAI),":[96],"a":[97,134,365],"conceptual":[98],"framework":[99,157,248,317],"extends":[101],"predictive":[102,178,359],"computing":[103,375],"toward":[104,372],"forecasting":[106,338,357],"future":[108,255],"states":[111],"proactive":[114],"constraints.":[118],"Rather":[119],"than":[120],"treating":[121],"as":[124,133],"an":[125],"exclusively":[126],"real-time":[127],"monitoring":[128],"variable,":[129],"PTM-GAI":[130],"considers":[131,269],"predictable":[135],"state":[137],"influenced":[138],"by":[139,285],"workload":[140,340],"characteristics,":[141,344],"memory":[146,281],"activity,":[147],"cooling":[148,220,345],"conditions,":[149],"ambient":[150],"historical":[153],"behavior.":[155],"integrates":[158],"telemetry":[160],"acquisition,":[161],"multi-horizon":[162],"forecasting,":[164],"constraint":[166,300],"prediction,":[167],"workload-to-temperature":[168],"estimation,":[169],"thermal-aware":[170,374],"scheduling,":[172],"adaptive":[173],"resource":[175],"allocation,":[176],"risk":[180],"management.":[181],"Its":[182,333],"architecture":[183],"investigates":[184,364],"whether":[185],"anticipated":[186],"increases":[188],"can":[189],"be":[190],"translated":[191],"into":[192,358],"advance":[193],"decisions,":[195],"including":[196,277],"shifting":[197],"speculative":[198],"preparation":[200],"to":[201,228,293],"cooler":[202],"periods,":[203],"distributing":[204],"workloads":[205],"across":[206],"alternative":[207],"GPUs,":[208],"adjusting":[209],"intensity,":[211],"modifying":[212],"task":[213],"priorities,":[214],"coordinating":[216],"execution":[217],"with":[218],"available":[219,286],"capacity.":[221],"A":[222],"unified":[223],"optimization":[224],"formulation":[225],"is":[226,291],"developed":[227],"minimize":[229],"thermal-management":[232],"costs":[233],"while":[234],"satisfying":[235],"predicted":[236,254],"constraints,":[238],"capacity":[240],"limitations,":[241],"deadlines,":[243],"service-level":[245],"requirements.":[246],"distinguishes":[249],"between":[250],"instantaneous":[251],"headroom,":[258],"probability":[261],"approaching":[263],"hardware-specific":[264],"thresholds.":[266],"It":[267],"also":[268],"characteristics":[272],"different":[274],"components,":[276],"cores":[279],"subsystems,":[282],"where":[283],"supported":[284],"telemetry.":[287],"An":[288],"experimental":[289],"methodology":[290],"proposed":[292,316],"evaluate":[294],"multi-step":[295],"prediction":[297,323],"accuracy,":[298,339],"violation":[301],"rates,":[302],"throughput,":[304],"energy":[306,327],"cooling-related":[308],"expenditure,":[309],"total":[311],"cost.":[313],"Importantly,":[314],"does":[318],"not":[319],"assume":[320],"automatically":[324],"produces":[325],"lower":[326],"consumption":[328],"higher":[330],"potential":[334],"benefits":[335],"depend":[336],"predictability,":[341],"response":[343],"infrastructure,":[346],"effectiveness":[349],"subsequent":[351],"scheduling":[352],"decisions.":[353],"By":[354],"integrating":[355],"orchestration,":[361],"this":[362],"research":[363],"transition":[366],"from":[367],"anticipatory":[373]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}