{"id":"https://openalex.org/W7134968163","doi":"https://doi.org/10.1109/comsnets67989.2026.11418252","title":"Memory-aware Hierarchical Scheduling of ML Tasks in Heterogeneous Clusters of Edge Computing Devices with GPUs","display_name":"Memory-aware Hierarchical Scheduling of ML Tasks in Heterogeneous Clusters of Edge Computing Devices with GPUs","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7134968163","doi":"https://doi.org/10.1109/comsnets67989.2026.11418252"},"language":null,"primary_location":{"id":"doi:10.1109/comsnets67989.2026.11418252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comsnets67989.2026.11418252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 18th International Conference on COMmunication Systems and NETworks (COMSNETS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006526563","display_name":"Saumya Mathkar","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saumya Mathkar","raw_affiliation_strings":["BITS,Department of CSIS,Pilani,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS,Department of CSIS,Pilani,Goa,India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004990749","display_name":"Pinki Pinki","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pinki Pinki","raw_affiliation_strings":["BITS,Department of CSIS,Pilani,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS,Department of CSIS,Pilani,Goa,India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128763529","display_name":"Vinayak Naik","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinayak Naik","raw_affiliation_strings":["BITS,Department of CSIS,Pilani,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BITS,Department of CSIS,Pilani,Goa,India","institution_ids":["https://openalex.org/I74796645"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74796645"],"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":"51","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.2524999976158142,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.2524999976158142,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.1890999972820282,"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":0.1582999974489212,"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/scheduling","display_name":"Scheduling (production processes)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.36000001430511475},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.3167000114917755},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.31150001287460327},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.2865999937057495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541999816894531},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3544999957084656},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/comsnets67989.2026.11418252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comsnets67989.2026.11418252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 18th International Conference on COMmunication Systems and NETworks (COMSNETS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2942661450","https://openalex.org/W2996377014","https://openalex.org/W3014807190","https://openalex.org/W3197286643","https://openalex.org/W4206882634","https://openalex.org/W4221135215","https://openalex.org/W4282934545","https://openalex.org/W4292117610","https://openalex.org/W4320005538","https://openalex.org/W4380078817","https://openalex.org/W4389639041","https://openalex.org/W4399205883","https://openalex.org/W4404030109","https://openalex.org/W4405809116","https://openalex.org/W4407783477"],"related_works":[],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"(ML)":[2],"workloads":[3,138],"represent":[4],"a":[5,60,147,180,189],"major":[6],"share":[7],"of":[8,25,46,54,63,106,136,143,171,191],"edge":[9,20,194],"computing":[10],"tasks,":[11,108],"where":[12],"efficient":[13],"scheduling":[14,149],"is":[15,59],"critical":[16],"to":[17,132,207,210,217],"exploit":[18],"heterogeneous":[19,55,172,192],"devices\u2019":[21],"capabilities":[22],"in":[23,51,80],"terms":[24],"their":[26],"GPUs.":[27,144],"We":[28,145,174],"find":[29],"that":[30,128,199],"conventional":[31],"schedulers":[32],"allocate":[33],"resources":[34],"opportunistically,":[35],"focusing":[36],"on":[37,86,188],"availability":[38],"rather":[39],"than":[40],"optimizing":[41],"the":[42,87,103,111,116,134,141,155,162,203],"overall":[43],"execution":[44,167],"time":[45,105],"ML":[47,137],"jobs.":[48],"This":[49,92],"results":[50,197],"inefficient":[52],"utilization":[53,170],"resources.":[56,173],"An":[57],"example":[58],"heuristic-based":[61],"strategy":[62],"First":[64,66,187,213],"Come":[65],"Serve":[67],"(FCFS),":[68],"combined":[69],"with":[70,179],"Least":[71],"Loaded":[72,186,212],"First.":[73],"In":[74],"this":[75],"approach,":[76],"jobs":[77],"are":[78],"assigned":[79],"an":[81,122],"FCFS":[82],"manner":[83],"and":[84,158,168,184,214],"placed":[85],"least":[88],"loaded":[89],"resourceful":[90],"device.":[91],"allocation":[93],"blocks":[94],"subsequent":[95],"larger":[96],"tasks":[97],"requiring":[98],"high":[99],"resources,":[100],"thereby":[101],"increasing":[102],"completion":[104],"all":[107],"known":[109],"as":[110],"makespan":[112,135,204],"[1].":[113],"To":[114],"alleviate":[115],"problem,":[117],"we":[118],"propose":[119],"MemBatch":[120,177,200],"ILP,":[121],"Integer":[123],"Linear":[124],"Programming":[125],"(ILP)-based":[126],"scheduler":[127,183],"performs":[129],"memory-aware":[130,152],"batching":[131,153],"minimize":[133],"while":[139],"reducing":[140],"idling":[142],"employ":[146],"hierarchical":[148],"technique":[150],"\u2013":[151],"at":[154,161],"cluster":[156],"level":[157],"fine-grained":[159],"task-splitting":[160],"device":[163],"level,":[164],"enabling":[165],"parallel":[166],"balanced":[169],"compare":[175],"our":[176],"ILP":[178,182,201],"baseline":[181,218],"FCFS-Least":[185,211],"testbed":[190],"Jetson":[193],"devices.":[195],"Our":[196],"show":[198],"reduces":[202],"by":[205],"up":[206],"48%":[208],"compared":[209,216],"61%":[215],"ILP.":[219]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-12T00:00:00"}