{"id":"https://openalex.org/W4404741562","doi":"https://doi.org/10.1109/icbase63199.2024.10762029","title":"TSM-LLM: Task Scheduling Management System for Large Language Models","display_name":"TSM-LLM: Task Scheduling Management System for Large Language Models","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4404741562","doi":"https://doi.org/10.1109/icbase63199.2024.10762029"},"language":"en","primary_location":{"id":"doi:10.1109/icbase63199.2024.10762029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbase63199.2024.10762029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Big Data &amp;amp; Artificial Intelligence &amp;amp; Software Engineering (ICBASE)","raw_type":"proceedings-article"},"type":"article","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/A5013127195","display_name":"Zeyi Wen","orcid":"https://orcid.org/0000-0003-3370-6053"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqiang Wen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076638782","display_name":"Guoping Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Zhu","raw_affiliation_strings":["China Electronics Cloud Computing Technology Co., Ltd,Cloud Product R&#x0026;D Department,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"China Electronics Cloud Computing Technology Co., Ltd,Cloud Product R&#x0026;D Department,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424453","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0002-5391-5808"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["China Electronics Cloud Computing Technology Co., Ltd,Cloud Product R&#x0026;D Department,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"China Electronics Cloud Computing Technology Co., Ltd,Cloud Product R&#x0026;D Department,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090227637","display_name":"Haijun Luo","orcid":"https://orcid.org/0000-0002-2723-5833"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Luo","raw_affiliation_strings":["China Electronics Cloud Computing Technology Co., Ltd,Cloud Product R&#x0026;D Department,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"China Electronics Cloud Computing Technology Co., Ltd,Cloud Product R&#x0026;D Department,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114060933","display_name":"N Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nianchao Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013127195"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24122125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"463","last_page":"467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.916100025177002,"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":0.916100025177002,"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/computer-science","display_name":"Computer science","score":0.80792635679245},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5834376811981201},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.5545455813407898},{"id":"https://openalex.org/keywords/task-management","display_name":"Task management","score":0.5318880677223206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5101011395454407},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.15951406955718994},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.127448171377182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09071195125579834},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.08163875341415405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80792635679245},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5834376811981201},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.5545455813407898},{"id":"https://openalex.org/C2780021488","wikidata":"https://www.wikidata.org/wiki/Q759682","display_name":"Task management","level":3,"score":0.5318880677223206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5101011395454407},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.15951406955718994},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.127448171377182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09071195125579834},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.08163875341415405},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icbase63199.2024.10762029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbase63199.2024.10762029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Big Data &amp;amp; Artificial Intelligence &amp;amp; Software Engineering (ICBASE)","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":8,"referenced_works":["https://openalex.org/W4387321091","https://openalex.org/W4404575065","https://openalex.org/W6695237428","https://openalex.org/W6739901393","https://openalex.org/W6778883912","https://openalex.org/W6810081322","https://openalex.org/W6846659131","https://openalex.org/W6860500267"],"related_works":["https://openalex.org/W2408144987","https://openalex.org/W2394534730","https://openalex.org/W2066180340","https://openalex.org/W588853005","https://openalex.org/W1758813645","https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2979618895","https://openalex.org/W2102390841","https://openalex.org/W2286770186"],"abstract_inverted_index":{"As":[0],"large":[1,45,90],"model":[2,18,102],"services":[3],"gain":[4],"popularity;":[5],"the":[6,25,42,62,85],"high":[7],"cost":[8],"of":[9,27,44,88],"deployment":[10,43],"presents":[11],"a":[12,34,107,114,122],"challenge.":[13],"Thus,":[14],"focusing":[15],"on":[16,84],"improving":[17],"efficiency":[19],"in":[20,110,117,124],"high-load":[21],"scenarios":[22],"while":[23],"managing":[24],"scheduling":[26,71],"multiple":[28],"models.":[29],"This":[30],"paper":[31],"introduces":[32],"TSMLLM,":[33],"Task":[35],"Scheduling":[36],"Management":[37],"System":[38],"designed":[39],"for":[40,65],"optimizing":[41,61],"language":[46],"models":[47],"(LLMs).":[48],"The":[49,92],"proposed":[50],"system":[51],"leverages":[52],"an":[53],"adaptive":[54],"time":[55],"window":[56],"to":[57,79,99,121],"group":[58],"realtime":[59],"requests,":[60],"batching":[63],"process":[64],"better":[66],"resource":[67],"utilization.":[68],"A":[69],"two-step":[70],"method,":[72],"involving":[73],"filtering":[74],"and":[75],"scoring,":[76],"is":[77],"employed":[78],"tailor":[80],"task":[81],"distribution":[82],"based":[83],"specific":[86],"characteristics":[87],"each":[89],"model.":[91],"system\u2019s":[93],"scalable":[94],"architecture":[95],"supports":[96],"seamless":[97],"expansion":[98],"accommodate":[100],"evolving":[101],"requirements.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"significant":[108],"increase":[109],"throughput":[111],"with":[112],"only":[113],"slight":[115],"rise":[116],"response":[118],"time,":[119],"contributing":[120],"reduction":[123],"overall":[125],"service":[126],"costs.":[127]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
