{"id":"https://openalex.org/W7160528006","doi":"https://doi.org/10.48550/arxiv.2605.04074","title":"A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers","display_name":"A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7160528006","doi":"https://doi.org/10.48550/arxiv.2605.04074"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.04074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033792995","display_name":"Mohammad AlShaikh Saleh","orcid":"https://orcid.org/0000-0002-0971-075X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saleh, Mohammad AlShaikh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037947876","display_name":"Sanjay Chawla","orcid":"https://orcid.org/0000-0002-8102-2572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chawla, Sanjay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056037710","display_name":"Serta\u00e7 Bayhan","orcid":"https://orcid.org/0000-0003-2027-532X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bayhan, Sertac","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098969426","display_name":"Prof. Dr. Haitham Abu-Rub","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abu-Rub, Haitham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014049864","display_name":"Ali Ghrayeb","orcid":"https://orcid.org/0000-0002-6808-5886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghrayeb, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.6783999800682068,"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":0.6783999800682068,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.06769999861717224,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.032999999821186066,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.5127000212669373},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4966000020503998},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.462799996137619},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4627000093460083},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.37779998779296875},{"id":"https://openalex.org/keywords/electricity","display_name":"Electricity","score":0.37529999017715454},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.374099999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843000054359436},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39989998936653137},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C187819001","wikidata":"https://www.wikidata.org/wiki/Q187665","display_name":"Thermostat","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C161657586","wikidata":"https://www.wikidata.org/wiki/Q1203326","display_name":"Technology forecasting","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.04074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[{"display_name":"Affordable and clean energy","score":0.8001090884208679,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"AI":[0,76,144],"data":[1,77,145],"centers":[2],"experience":[3],"rapid":[4],"fluctuations":[5],"in":[6,43,184],"power":[7,24,72,118,169],"demand":[8],"due":[9],"to":[10,19,56,135,176],"the":[11,23,44,47,57,62,84,121,155,161,165,177],"heterogeneity":[12],"of":[13,26,30,46,59,74,101],"computational":[14],"tasks":[15],"that":[16,68,113,132],"they":[17],"have":[18],"support.":[20],"For":[21],"example,":[22],"profile":[25,163],"inference":[27],"and":[28,38,116,124,127,139,148,171,180,191,202],"training":[29],"large":[31],"language":[32],"models":[33,115,158],"(LLMs)":[34],"is":[35,103,149],"quite":[36],"distinct":[37],"big":[39],"divergences":[40],"can":[41,69],"result":[42],"instability":[45],"underlying":[48,166],"electricity":[49],"grid.":[50],"In":[51],"this":[52],"paper":[53],"we":[54,133],"propose,":[55],"best":[58],"our":[60],"knowledge,":[61],"first":[63],"physics-informed":[64],"DLinear":[65],"time-series":[66],"model":[67],"accurately":[70],"forecast":[71,162],"utilization":[73,126],"an":[75],"center":[78,146],"5-80":[79],"minutes":[80],"(short-term":[81],"forecasting)":[82],"into":[83],"future.":[85],"The":[86,129],"physics,":[87],"based":[88],"on":[89,141],"a":[90,142],"multi-node":[91],"lumped":[92],"thermal":[93],"resistance-capacitance":[94],"(RC)":[95],"network":[96],"consistent":[97],"with":[98,120],"Newton's":[99],"law":[100],"cooling,":[102],"captured":[104],"using":[105],"newly":[106],"derived":[107],"time-dependent":[108],"ordinary":[109],"differential":[110],"equations":[111],"(ODE)":[112],"separately":[114],"interlinks":[117],"consumption":[119],"GPU":[122],"compute":[123],"memory":[125],"temperature.":[128],"resulting":[130],"model,":[131],"refer":[134],"as":[136],"PI-DLinear,":[137],"trained":[138],"evaluated":[140],"real":[143],"dataset":[147],"not":[150],"only":[151],"more":[152],"accurate":[153],"than":[154],"state-of-the-art":[156],"(SOTA)":[157],"tested,":[159],"but":[160],"respects":[164],"physics":[167],"under":[168],"throttling":[170],"load":[172],"transient":[173],"events.":[174],"Relative":[175],"SOTA":[178],"transformer-based":[179],"non-transformer-based":[181],"models,":[182],"improvements":[183],"forecasting":[185],"accuracy":[186],"(averaged":[187],"across":[188],"all":[189],"look-back":[190],"prediction":[192],"windows)":[193],"range":[194],"from":[195],"0.782%-39.08%":[196],"for":[197,200,204],"MSE,":[198],"0.993%-51.82%":[199],"MAE,":[201],"0.370%-22.28%":[203],"RMSE.":[205]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-08T00:00:00"}