{"id":"https://openalex.org/W7117490305","doi":"https://doi.org/10.1109/ipccc66453.2025.11304692","title":"Towards Profits Optimization in LLM Inference Model Deployment at the Network Edge","display_name":"Towards Profits Optimization in LLM Inference Model Deployment at the Network Edge","publication_year":2025,"publication_date":"2025-11-15","ids":{"openalex":"https://openalex.org/W7117490305","doi":"https://doi.org/10.1109/ipccc66453.2025.11304692"},"language":null,"primary_location":{"id":"doi:10.1109/ipccc66453.2025.11304692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc66453.2025.11304692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Performance, Computing, and Communications Conference (IPCCC)","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/A5053774480","display_name":"Yuqi Zhang","orcid":"https://orcid.org/0000-0002-0818-6810"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Zhang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121479353","display_name":"Danyang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danyang Zheng","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121489977","display_name":"Huanlai Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanlai Xing","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064192743","display_name":"Honghui Xu","orcid":"https://orcid.org/0000-0002-9128-8454"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honghui Xu","raw_affiliation_strings":["Kennesaw State University,Department of Information Technology,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University,Department of Information Technology,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089154506","display_name":"Chengzong Peng","orcid":"https://orcid.org/0000-0002-1056-880X"},"institutions":[{"id":"https://openalex.org/I24201400","display_name":"Chengdu University of Information Technology","ror":"https://ror.org/01yxwrh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I24201400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzong Peng","raw_affiliation_strings":["School of Cybersecurity, Chengdu University of Information Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Chengdu University of Information Technology,China","institution_ids":["https://openalex.org/I24201400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121496630","display_name":"Chao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Georgia State University,Department of Computer Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121444726","display_name":"Xiaojun Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojun Cao","raw_affiliation_strings":["Georgia State University,Department of Computer Science,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.24289999902248383,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.24289999902248383,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.1421000063419342,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05730000138282776,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/inference","display_name":"Inference","score":0.7573000192642212},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7508999705314636},{"id":"https://openalex.org/keywords/profit-maximization","display_name":"Profit maximization","score":0.6100999712944031},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.4828999936580658},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4681999981403351},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4496999979019165}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7573000192642212},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7508999705314636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340999841690063},{"id":"https://openalex.org/C2777780509","wikidata":"https://www.wikidata.org/wiki/Q1377422","display_name":"Profit maximization","level":3,"score":0.6100999712944031},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc66453.2025.11304692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc66453.2025.11304692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6680276989936829}],"awards":[{"id":"https://openalex.org/G2440421249","display_name":null,"funder_award_id":"2682025GH021","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2915584714","display_name":null,"funder_award_id":"62302404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5417512370","display_name":null,"funder_award_id":"2024NSFSC1456","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2210790443","https://openalex.org/W2903252781","https://openalex.org/W3034004337","https://openalex.org/W4394998727","https://openalex.org/W4396790588","https://openalex.org/W4403320241","https://openalex.org/W4405812941","https://openalex.org/W4412722064"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,48,126],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"have":[7],"empowered":[8],"robots":[9],"and":[10,63,107],"drones":[11],"with":[12],"autonomous":[13],"decision-making":[14],"capabilities.":[15],"Due":[16],"to":[17],"the":[18,31,65,78,110],"stringent":[19],"real-time":[20],"requirements":[21],"of":[22],"these":[23,59],"applications,":[24],"LLM":[25,51,71,105],"inference":[26,72],"must":[27],"be":[28],"performed":[29],"at":[30],"network":[32,131],"edge.":[33],"However,":[34],"hosting":[35,104],"high-precision":[36],"LLMs":[37],"on":[38],"a":[39,90],"single":[40],"edge":[41,54,100],"server":[42,101],"is":[43],"often":[44],"infeasible,":[45],"creating":[46],"challenges":[47,60],"efficiently":[49],"distributing":[50],"deployments":[52],"across":[53,129],"networks.":[55],"This":[56],"work":[57],"addresses":[58],"by":[61],"formulating":[62],"solving":[64],"profit":[66,128],"maximization":[67],"problem":[68],"for":[69,103],"distributed":[70],"deployment.":[73],"We":[74],"first":[75],"formally":[76],"define":[77],"Profit-Centric":[79],"Inference":[80,112],"Chain":[81,113],"Deployment":[82,114],"(PC-InCD)":[83],"problem.":[84],"To":[85],"solve":[86],"PC-InCD,":[87],"we":[88,108],"introduce":[89],"novel":[91],"Local":[92],"Maximal":[93],"Profit":[94],"(LMP)":[95],"factor":[96],"that":[97,120],"enables":[98],"effective":[99],"selection":[102],"sub-modules,":[106],"propose":[109],"LMP-based":[111],"(LMP-InCD)":[115],"algorithm.":[116],"Extensive":[117],"simulations":[118],"demonstrate":[119],"LMP-InCD":[121],"significantly":[122],"outperforms":[123],"benchmark":[124],"methods":[125],"maximizing":[127],"diverse":[130],"conditions.":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-29T00:00:00"}
