{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T10:43:38Z","timestamp":1786099418000,"version":"3.56.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302404"],"award-info":[{"award-number":["62302404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682025GH021"],"award-info":[{"award-number":["2682025GH021"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682026ZT007"],"award-info":[{"award-number":["2682026ZT007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.comnet.2026.112609","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T15:47:13Z","timestamp":1785167233000},"page":"112609","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Profit-aware deployment of large language model-enabled inference chains in data centers"],"prefix":"10.1016","volume":"288","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1426-8673","authenticated-orcid":false,"given":"Yuqi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7009-4209","authenticated-orcid":false,"given":"Haochen","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3031-7856","authenticated-orcid":false,"given":"Danyang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanlai","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5670-8196","authenticated-orcid":false,"given":"Xiaojun","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.comnet.2026.112609_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3771090","article-title":"A survey on recent advances in LLM-based multi-turn dialogue systems","volume":"58","author":"Yi","year":"2025","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"10.1016\/j.comnet.2026.112609_b2","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1007\/s10845-023-02294-y","article-title":"Embodied intelligence in manufacturing: Leveraging large language models for autonomous industrial robotics","volume":"36","author":"Fan","year":"2025","journal-title":"J. Intell. Manuf."},{"issue":"10","key":"10.1016\/j.comnet.2026.112609_b3","doi-asserted-by":"crossref","first-page":"8186","DOI":"10.1109\/LRA.2024.3440097","article-title":"Drivegpt4: Interpretable end-to-end autonomous driving via large language model","volume":"9","author":"Xu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"11","key":"10.1016\/j.comnet.2026.112609_b4","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s10462-024-10921-0","article-title":"Large language models in medical and healthcare fields: Applications, advances, and challenges","volume":"57","author":"Wang","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.comnet.2026.112609_b5","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.procir.2024.10.093","article-title":"Integrating large language model for natural language-based instruction toward robust human-robot collaboration","volume":"130","author":"Gao","year":"2024","journal-title":"Procedia CIRP"},{"issue":"1","key":"10.1016\/j.comnet.2026.112609_b6","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1109\/TIV.2023.3327715","article-title":"Drivellm: Charting the path toward full autonomous driving with large language models","volume":"9","author":"Cui","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.comnet.2026.112609_b7","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/OJVT.2024.3446799","article-title":"Large language models for UAVs: Current state and pathways to the future","volume":"5","author":"Javaid","year":"2024","journal-title":"IEEE Open J. Veh. Technol."},{"key":"10.1016\/j.comnet.2026.112609_b8","doi-asserted-by":"crossref","unstructured":"S.S. Kannan, V.L.N. Venkatesh, B.-C. Min, SMART-LLM: Smart Multi-Agent Robot Task Planning Using Large Language Models, in: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS, 2024, pp. 12140\u201312147.","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"10.1016\/j.comnet.2026.112609_b9","doi-asserted-by":"crossref","unstructured":"Y. Shentu, P. Wu, A. Rajeswaran, P. Abbeel, From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control, in: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS, 2024, pp. 8539\u20138546.","DOI":"10.1109\/IROS58592.2024.10801683"},{"key":"10.1016\/j.comnet.2026.112609_b10","series-title":"2024 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Tina: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation","author":"Li","year":"2024"},{"key":"10.1016\/j.comnet.2026.112609_b11","series-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024"},{"key":"10.1016\/j.comnet.2026.112609_b12","unstructured":"A. Agrawal, N. Kedia, A. Panwar, J. Mohan, N. Kwatra, B. Gulavani, A. Tumanov, R. Ramjee, Taming {Throughput-Latency} tradeoff in {LLM} inference with {Sarathi-Serve}, in: 18th USENIX Symposium on Operating Systems Design and Implementation, OSDI 24, 2024, pp. 117\u2013134."},{"key":"10.1016\/j.comnet.2026.112609_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2025.104080","article-title":"Collaborative deployment of Large AI Models on the edge: A microservice approach to heterogeneous training and quantized inference","volume":"181","author":"Ahmadpanah","year":"2026","journal-title":"Ad Hoc Netw."},{"issue":"6","key":"10.1016\/j.comnet.2026.112609_b14","doi-asserted-by":"crossref","first-page":"7941","DOI":"10.1109\/TCSS.2024.3423749","article-title":"Slob: Suboptimal load balancing scheduling in local heterogeneous gpu clusters for large language model inference","volume":"11","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.comnet.2026.112609_b15","first-page":"586","article-title":"Helix: Serving large language models over heterogeneous gpus and network via max-flow","volume":"vol. 1","author":"Mei","year":"2025"},{"key":"10.1016\/j.comnet.2026.112609_b16","doi-asserted-by":"crossref","DOI":"10.62306\/7ds08r28","article-title":"A survey on integrated training-inference architectures for large language models on multi-GPU stream processors","author":"Tsang","year":"2025","journal-title":"Digit. Sci."},{"key":"10.1016\/j.comnet.2026.112609_b17","series-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"Gems: Gpu-enabled memory-aware model-parallelism system for distributed dnn training","author":"Jain","year":"2020"},{"key":"10.1016\/j.comnet.2026.112609_b18","series-title":"2024 IEEE High Performance Extreme Computing Conference","first-page":"1","article-title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","author":"Li","year":"2024"},{"key":"10.1016\/j.comnet.2026.112609_b19","doi-asserted-by":"crossref","first-page":"11431","DOI":"10.1109\/TIFS.2025.3622954","article-title":"The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems","volume":"20","author":"Song","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"5","key":"10.1016\/j.comnet.2026.112609_b20","doi-asserted-by":"crossref","first-page":"106:1","DOI":"10.1145\/3744746","article-title":"A Comprehensive Overview of Large Language Models","volume":"16","author":"Naveed","year":"2025","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.comnet.2026.112609_b21","doi-asserted-by":"crossref","first-page":"3795","DOI":"10.1109\/OJCOMS.2025.3561605","article-title":"A Matching Game for LLM Layer Deployment in Heterogeneous Edge Networks","volume":"6","author":"Picano","year":"2025","journal-title":"IEEE Open J. Commun. Soc."},{"key":"10.1016\/j.comnet.2026.112609_b22","series-title":"2025 IEEE 31st International Symposium on Local and Metropolitan Area Networks","first-page":"1","article-title":"Model-Distributed Inference for Large Language Models at the Edge","author":"Macario","year":"2025"},{"issue":"10","key":"10.1016\/j.comnet.2026.112609_b23","doi-asserted-by":"crossref","first-page":"13119","DOI":"10.1109\/JIOT.2024.3524255","article-title":"EdgeShard: Efficient LLM Inference via Collaborative Edge Computing","volume":"12","author":"Zhang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.comnet.2026.112609_b24","series-title":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","first-page":"1","article-title":"Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices","author":"Ye","year":"2025"},{"key":"10.1016\/j.comnet.2026.112609_b25","series-title":"2025 IEEE Real-Time Systems Symposium","first-page":"148","article-title":"HCInfer: Hierarchical Coordination for Real-Time Collaborative Inference of LLM on the Edge","author":"Liu","year":"2025"},{"key":"10.1016\/j.comnet.2026.112609_b26","doi-asserted-by":"crossref","unstructured":"A. Albaseer, E. Bentafat, M. Hamood, M. Abdallah, A. Al-Fuqaha, M. Hamdi, Think Fast, Infer Smart: A Hybrid Distributed LLMs Inference at the Wireless Edge, in: 2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC, 2025, pp. 1\u20136.","DOI":"10.1109\/PIMRC62392.2025.11274878"},{"issue":"7","key":"10.1016\/j.comnet.2026.112609_b27","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/JSTSP.2025.3581478","article-title":"Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks","volume":"19","author":"Zhang","year":"2025","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.comnet.2026.112609_b28","unstructured":"G.-I. Yu, J.S. Jeong, G.-W. Kim, S. Kim, B.-G. Chun, Orca: A Distributed Serving System for Transformer-Based Generative Models, in: 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 22, 2022, pp. 521\u2013538."},{"key":"10.1016\/j.comnet.2026.112609_b29","doi-asserted-by":"crossref","unstructured":"W. Kwon, Z. Li, S. Zhuang, Y. Sheng, L. Zheng, C.H. Yu, J. Gonzalez, H. Zhang, I. Stoica, Efficient memory management for large language model serving with pagedattention, in: Proceedings of the 29th Symposium on Operating Systems Principles, 2023, pp. 611\u2013626.","DOI":"10.1145\/3600006.3613165"},{"key":"10.1016\/j.comnet.2026.112609_b30","unstructured":"A. Agrawal, N. Kedia, A. Panwar, J. Mohan, N. Kwatra, B. Gulavani, A. Tumanov, R. Ramjee, Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve, in: 18th USENIX Symposium on Operating Systems Design and Implementation, OSDI 24, 2024, pp. 117\u2013134."},{"key":"10.1016\/j.comnet.2026.112609_b31","unstructured":"Y. Zhong, S. Liu, J. Chen, J. Hu, Y. Zhu, X. Liu, X. Jin, H. Zhang, DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving, in: 18th USENIX Symposium on Operating Systems Design and Implementation, OSDI 24, 2024, pp. 193\u2013210."},{"issue":"1","key":"10.1016\/j.comnet.2026.112609_b32","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TNET.2024.3475248","article-title":"Provably Efficient Service Function Chain Embedding and Protection in Edge Networks","volume":"33","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Netw."},{"key":"10.1016\/j.comnet.2026.112609_b33","first-page":"1","article-title":"Towards Latency Differentials Optimization in Deploying URLLC Service Function Chains","author":"Zheng","year":"2026","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"6","key":"10.1016\/j.comnet.2026.112609_b34","doi-asserted-by":"crossref","first-page":"6194","DOI":"10.1109\/TNSE.2024.3477453","article-title":"Enhanced Profit-Driven Optimization for Flexible Server Deployment and Service Placement in Multi-User Mobile Edge Computing Systems","volume":"11","author":"Fang","year":"2024","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"10.1016\/j.comnet.2026.112609_b35","doi-asserted-by":"crossref","unstructured":"S. Singh, D. Ho Kim, Profit Optimization for Mobile Edge Computing Using Genetic Algorithm, in: 2021 IEEE Region 10 Symposium (TENSYMP), 2021, pp. 1\u20136.","DOI":"10.1109\/TENSYMP52854.2021.9550947"},{"issue":"3","key":"10.1016\/j.comnet.2026.112609_b36","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.1109\/TASE.2020.3000946","article-title":"Profit-Maximized Collaborative Computation Offloading and Resource Allocation in Distributed Cloud and Edge Computing Systems","volume":"18","author":"Yuan","year":"2021","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"12","key":"10.1016\/j.comnet.2026.112609_b37","doi-asserted-by":"crossref","first-page":"13364","DOI":"10.1109\/TVT.2021.3124483","article-title":"Platform Profit Maximization on Service Provisioning in Mobile Edge Computing","volume":"70","author":"Huang","year":"2021","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"10.1016\/j.comnet.2026.112609_b38","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/JIOT.2021.3082898","article-title":"Profit-Aware Edge Server Placement","volume":"9","author":"Li","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.comnet.2026.112609_b39","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1109\/TNSM.2025.3640927","article-title":"VNF-FG placement and Admission Control in SDN and NFV-Enabled IoT Networks: A Hierarchical Deep Reinforcement Learning Method","volume":"23","author":"Xu","year":"2026","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.comnet.2026.112609_b40","doi-asserted-by":"crossref","unstructured":"G. Zeng, H. Du, Q. Ye, C. Zhang, Collaborative Service Placement for Maximizing the Profit in Mobile Edge Computing, in: 2021 IEEE Global Communications Conference, GLOBECOM, 2021, pp. 1\u20136.","DOI":"10.1109\/GLOBECOM46510.2021.9685311"},{"key":"10.1016\/j.comnet.2026.112609_b41","series-title":"2025 IEEE International Performance, Computing, and Communications Conference","first-page":"1","article-title":"Towards profits optimization in LLM inference model deployment at the network edge","author":"Zhang","year":"2025"},{"key":"10.1016\/j.comnet.2026.112609_b42","series-title":"Pricing information via","author":"PacketFabric","year":"2026"},{"key":"10.1016\/j.comnet.2026.112609_b43","series-title":"GPU dedicated \/ VPS server hosting pricing","author":"CloudClusters","year":"2026"},{"key":"10.1016\/j.comnet.2026.112609_b44","series-title":"What is ChatGPT Plus?","author":"OpenAI","year":"2026"},{"key":"10.1016\/j.comnet.2026.112609_b45","series-title":"NVIDIA blackwell delivers massive performance leaps in MLPerf inference v5.0","author":"NVIDIA","year":"2026"}],"container-title":["Computer Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128626006213?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128626006213?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T09:47:16Z","timestamp":1786096036000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1389128626006213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S1389128626006213"],"URL":"https:\/\/doi.org\/10.1016\/j.comnet.2026.112609","relation":{},"ISSN":["1389-1286"],"issn-type":[{"value":"1389-1286","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Profit-aware deployment of large language model-enabled inference chains in data centers","name":"articletitle","label":"Article Title"},{"value":"Computer Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.comnet.2026.112609","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"112609"}}