{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:40:45Z","timestamp":1786390845475,"version":"3.56.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302404"],"award-info":[{"award-number":["62302404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2682025GH021"],"award-info":[{"award-number":["2682025GH021"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2682026ZT007"],"award-info":[{"award-number":["2682026ZT007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tsc.2026.3707550","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T19:45:08Z","timestamp":1782416708000},"page":"2646-2659","source":"Crossref","is-referenced-by-count":0,"title":["A Provably Cost-Efficient Approach to Deploying MoE Inference Models at the Network Edge"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3911-4645","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"first","affiliation":[{"name":"Southwest Jiaotong University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3031-7856","authenticated-orcid":false,"given":"Danyang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University","place":["Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6345-7265","authenticated-orcid":false,"given":"Huanlai","family":"Xing","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University","place":["Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4932-8766","authenticated-orcid":false,"given":"Chen","family":"Yang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University","place":["Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5670-8196","authenticated-orcid":false,"given":"Xiaojun","family":"Cao","sequence":"additional","affiliation":[{"name":"Georgia State University","place":["Atlanta, GA, USA"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4102-233X","authenticated-orcid":false,"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Leeds","place":["Leeds, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9535-7245","authenticated-orcid":false,"given":"Fei","family":"Teng","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University","place":["Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2023.3335255"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3465447"},{"key":"ref3","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref4","article-title":"On-device language models: A comprehensive review","author":"Xu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621128"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2025.3574131"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3529929"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1675"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3571753"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0515"},{"issue":"120","key":"ref12","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","article-title":"Hunyuan-large: An open-source moe model with 52 billion activated parameters by tencent","author":"Sun","year":"2024"},{"key":"ref14","article-title":"Introducing DBRX: A new state-of-the-art open LLM","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2024.111002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621314"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3590723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3527641"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3424533"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2906744"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3279587"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3120297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486320"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155529"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3475248"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044451"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3586653"},{"key":"ref28","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw. Storage Anal.","author":"Narayanan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0540"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901542"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00046"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11160773"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3581478"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC62479.2024.10681712"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3731806.3731859"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0256"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044447"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044508"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3546466"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3585163"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11161045"},{"key":"ref45","volume-title":"Knapsack Problems: Algorithms and Computer Implementations","author":"Martello","year":"1990"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref48","first-page":"32332","article-title":"KIVI: A tuning-free asymmetric 2 bit quantization for KV cache","volume-title":"Proc. Mach. Learn. Res","volume":"235","author":"Liu"},{"key":"ref49","article-title":"DeepSeek-V3 technical report","author":"Liu","year":"2024"},{"key":"ref50","article-title":"The new LLM bottleneck: A systems perspective on latent attention and mixture-of-experts","author":"Yun","year":"2025"},{"key":"ref51","article-title":"25GFH-SFP28\u201310","year":"2025"},{"key":"ref52","article-title":"Akash network","year":"2025"},{"key":"ref53","article-title":"Render network","year":"2025"},{"key":"ref54","article-title":"Nvidia GPU resources","year":"2025"},{"key":"ref55","article-title":"Azure pricing calculator","year":"2025"},{"key":"ref56","article-title":"Azure bandwidth pricing","year":"2025"},{"key":"ref57","article-title":"Grok open source","year":"2024"},{"key":"ref58","article-title":"DeepSeek-V2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11644734\/11579461.pdf?arnumber=11579461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:13:25Z","timestamp":1786389205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11579461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2026.3707550","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}