{"id":"https://openalex.org/W7147473280","doi":"https://doi.org/10.48550/arxiv.2603.28790","title":"Mitigating Temporal Blindness in Kubernetes Autoscaling: An Attention-Double-LSTM Framework","display_name":"Mitigating Temporal Blindness in Kubernetes Autoscaling: An Attention-Double-LSTM Framework","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7147473280","doi":"https://doi.org/10.48550/arxiv.2603.28790"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.28790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114539398","display_name":"Faraz Shaikh","orcid":"https://orcid.org/0009-0005-7815-8283"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shaikh, Faraz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070042849","display_name":"Gianluca Reali","orcid":"https://orcid.org/0000-0002-8567-5917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reali, Gianluca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053723295","display_name":"Mauro Femminella","orcid":"https://orcid.org/0000-0002-6695-5956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Femminella, Mauro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114539398"],"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/T12127","display_name":"Software System Performance and Reliability","score":0.27320000529289246,"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/T12127","display_name":"Software System Performance and Reliability","score":0.27320000529289246,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.19200000166893005,"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/T13553","display_name":"Age of Information Optimization","score":0.13279999792575836,"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/deep-learning","display_name":"Deep learning","score":0.49790000915527344},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4941999912261963},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.46709999442100525},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4205000102519989},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.3950999975204468},{"id":"https://openalex.org/keywords/replica","display_name":"Replica","score":0.3856000006198883},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.34279999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4941999912261963},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4668999910354614},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C93173128","wikidata":"https://www.wikidata.org/wiki/Q287827","display_name":"Inattentional blindness","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C2780929884","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Blindness","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.28790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,7,28,142,186],"emerging":[2],"landscape":[3],"of":[4,12,137],"edge":[5,80,210],"computing,":[6],"stochastic":[8],"and":[9,49,96,161],"bursty":[10],"nature":[11],"serverless":[13],"workloads":[14],"presents":[15],"a":[16,60,88,106,119,145,162,202],"critical":[17,135],"challenge":[18],"for":[19,204],"autonomous":[20],"resource":[21,50],"orchestration.":[22],"Traditional":[23],"reactive":[24],"controllers,":[25],"such":[26],"as":[27],"Kubernetes":[29],"Horizontal":[30],"Pod":[31],"Autoscaler":[32],"(HPA),":[33],"suffer":[34,67],"from":[35,68],"inherent":[36],"reaction":[37],"latency,":[38],"leading":[39],"to":[40,73,124,185],"Service":[41],"Level":[42],"Objective":[43],"(SLO)":[44],"violations":[45],"during":[46,52],"traffic":[47],"spikes":[48],"flapping":[51],"ramp-downs.":[53],"While":[54],"Deep":[55],"Reinforcement":[56],"Learning":[57],"(DRL)":[58],"offers":[59],"pathway":[61],"toward":[62],"proactive":[63],"management,":[64],"standard":[65],"agents":[66],"temporal":[69,121,195],"blindness,":[70],"an":[71,99],"inability":[72],"effectively":[74,129],"capture":[75],"long-term":[76],"dependencies":[77],"in":[78,208],"non-Markovian":[79],"environments.":[81,211],"To":[82],"bridge":[83],"this":[84],"gap,":[85],"we":[86],"propose":[87],"novel":[89],"stability-aware":[90],"autoscaling":[91,207],"framework":[92,143],"unifying":[93],"workload":[94],"forecasting":[95],"control":[97],"via":[98],"Attention-Enhanced":[100],"Double-Stacked":[101],"LSTM":[102,164,188],"architecture":[103],"integrated":[104],"within":[105],"Proximal":[107],"Policy":[108],"Optimization":[109],"(PPO)":[110],"agent.":[111],"Unlike":[112],"shallow":[113],"recurrent":[114],"models,":[115],"our":[116,168],"approach":[117,169],"employs":[118],"deep":[120,198],"attention":[122],"mechanism":[123],"selectively":[125],"weight":[126],"historical":[127],"states,":[128],"filtering":[130],"high-frequency":[131],"noise":[132],"while":[133,177],"retaining":[134],"precursors":[136],"demand":[138],"shifts.":[139],"We":[140],"validate":[141],"on":[144],"heterogeneous":[146],"cluster":[147],"using":[148],"real-world":[149],"Azure":[150],"Functions":[151],"traces.":[152],"Comparative":[153],"analysis":[154],"against":[155],"industry-standard":[156],"HPA,":[157],"stateless":[158],"Double":[159],"DQN,":[160],"single-layer":[163,187],"ablation":[165],"demonstrates":[166],"that":[167,193],"reduces":[170],"90th":[171],"percentile":[172],"latency":[173],"by":[174,182],"approximately":[175],"29%":[176],"simultaneously":[178],"decreasing":[179],"replica":[180],"churn":[181],"39%,":[183],"relative":[184],"baseline.":[189],"These":[190],"results":[191],"confirm":[192],"mitigating":[194],"blindness":[196],"through":[197],"attentive":[199],"memory":[200],"is":[201],"prerequisite":[203],"reliable,":[205],"low-jitter":[206],"production":[209]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-02T00:00:00"}