CoCaR: Enabling Efficient Dynamic DNN-Based Model Caching and Request Routing in MEC
Mobile edge computing (MEC) can pre-cache deep neural networks (DNNs) near end-users, providing low-latency services and improving users' quality of experience (QoE). However, caching all DNN models at edge servers with limited capacity is difficult, and the impact of model loading time on QoE...
Uloženo v:
| Vydáno v: | Annual Joint Conference of the IEEE Computer and Communications Societies s. 1 - 10 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
19.05.2025
|
| Témata: | |
| ISSN: | 2641-9874 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Mobile edge computing (MEC) can pre-cache deep neural networks (DNNs) near end-users, providing low-latency services and improving users' quality of experience (QoE). However, caching all DNN models at edge servers with limited capacity is difficult, and the impact of model loading time on QoE is underexplored. Hence, we introduce dynamic DNNs in edge scenarios, disassembling a complete DNN model into interrelated submodels for more fine-grained and flexible model caching and request routing solutions. Further, this raises the pressing issue of joint deciding request routing and sub model caching for dynamic DNNs to balance model inference precision and loading latency for QoE optimization. In this paper, we study the joint dynamic model caching and request routing problem in MEC networks, aiming to maximize user request inference precision under constraints of server resources, latency, and model loading time. To tackle this problem, we propose CoCaR, an algorithm based on linear programming and random rounding that leverages dynamic DNNs to optimize caching and routing schemes, achieving near-optimal performance. Simulation results show that the proposed CoCaR achieves significant performance improvements compared to state-of-the-art baselines. |
|---|---|
| AbstractList | Mobile edge computing (MEC) can pre-cache deep neural networks (DNNs) near end-users, providing low-latency services and improving users' quality of experience (QoE). However, caching all DNN models at edge servers with limited capacity is difficult, and the impact of model loading time on QoE is underexplored. Hence, we introduce dynamic DNNs in edge scenarios, disassembling a complete DNN model into interrelated submodels for more fine-grained and flexible model caching and request routing solutions. Further, this raises the pressing issue of joint deciding request routing and sub model caching for dynamic DNNs to balance model inference precision and loading latency for QoE optimization. In this paper, we study the joint dynamic model caching and request routing problem in MEC networks, aiming to maximize user request inference precision under constraints of server resources, latency, and model loading time. To tackle this problem, we propose CoCaR, an algorithm based on linear programming and random rounding that leverages dynamic DNNs to optimize caching and routing schemes, achieving near-optimal performance. Simulation results show that the proposed CoCaR achieves significant performance improvements compared to state-of-the-art baselines. |
| Author | Fan, Qilin Tan, Siyu Qiu, Shuting Shen, Dian Dong, Fang Zhou, Ruiting |
| Author_xml | – sequence: 1 givenname: Shuting surname: Qiu fullname: Qiu, Shuting email: qiushuting@seu.edu.cn organization: Southeast University,School of Computer Science and Engineering,Nanjing,China – sequence: 2 givenname: Fang surname: Dong fullname: Dong, Fang email: fdong@seu.edu.cn organization: Southeast University,School of Computer Science and Engineering,Nanjing,China – sequence: 3 givenname: Siyu surname: Tan fullname: Tan, Siyu email: sytan@seu.edu.cn organization: Southeast University,School of Computer Science and Engineering,Nanjing,China – sequence: 4 givenname: Dian surname: Shen fullname: Shen, Dian email: dshen@seu.edu.cn organization: Southeast University,School of Computer Science and Engineering,Nanjing,China – sequence: 5 givenname: Ruiting surname: Zhou fullname: Zhou, Ruiting email: ruitingzhou@seu.edu.cn organization: Southeast University,School of Computer Science and Engineering,Nanjing,China – sequence: 6 givenname: Qilin surname: Fan fullname: Fan, Qilin email: fanqilin@cqu.edu.cn organization: Chongqing University,School of Big Data and Software Engineering,Chongqing,China |
| BookMark | eNo1kE9PwjAchqvRREC-gYfG-7Bd_3vTMpSEQbLgmXTdr1ozOmXjwLc3RD09yZMn7-Edo6vUJUDonpIZpcQ8LNeLjd2UQkiuZznJxVlzzoW6QFOjjGaMCs6IoJdolEtOM6MVv0Hjvv8khGiVyxHa2s666hEXydVtTO-4CCH6CGnA81Ny--jxfL3Onl0PDS67Blpsnf84ly41uILvI_QDrrrjcHYx4bKwt-g6uLaH6R8n6G1RbO1rttq8LO3TKotU6SEDQ3xN8uAME1yyWnsg1DsZFAclmOcKTEM1ETWVDoxouDG8liawxgUuPZugu9_dCAC7r0Pcu8Np9_8C-wEoXlLO |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/INFOCOM55648.2025.11044457 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 9798331543051 |
| EISSN | 2641-9874 |
| EndPage | 10 |
| ExternalDocumentID | 11044457 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i178t-e90cb02fa935463b8ce01ca6f74e753c47e9d1805b16ae95d4994b69f3daf46c3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001540458000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Sep 17 06:32:46 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i178t-e90cb02fa935463b8ce01ca6f74e753c47e9d1805b16ae95d4994b69f3daf46c3 |
| PageCount | 10 |
| ParticipantIDs | ieee_primary_11044457 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-May-19 |
| PublicationDateYYYYMMDD | 2025-05-19 |
| PublicationDate_xml | – month: 05 year: 2025 text: 2025-May-19 day: 19 |
| PublicationDecade | 2020 |
| PublicationTitle | Annual Joint Conference of the IEEE Computer and Communications Societies |
| PublicationTitleAbbrev | INFOCOM |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0008726 |
| Score | 2.2989 |
| Snippet | Mobile edge computing (MEC) can pre-cache deep neural networks (DNNs) near end-users, providing low-latency services and improving users' quality of experience... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Artificial neural networks Computational modeling Heuristic algorithms Load modeling Loading Pressing Quality of experience Routing Servers Simulation |
| Title | CoCaR: Enabling Efficient Dynamic DNN-Based Model Caching and Request Routing in MEC |
| URI | https://ieeexplore.ieee.org/document/11044457 |
| WOSCitedRecordID | wos001540458000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27TsMwFLWgYoCFVxFveWBNayd2bDOSpoKhaVUVqVvlx41UCaWotHw_dtIWGBjYrCvZsmwlx9e-5xyEHoIom3T--1bcqogZA5FMRRn5s78yQQ7P2cZsQhSFnE7VaENWr7kwAFAXn0EnNOu3fLew63BV1vVQxRjjYh_tC5E2ZK3db1eKON2oilKiui9Ff5gNB5w3FVwx72x7__JRqWGkf_zPCZyg9jchD492UHOK9qA6Q0c_tATP0SRbZHr8iPNAhvIRnNfiEH483Gtc53GvKKInj1oOBwe0N5w1hZRYVw6PoQYIHCqEQmxe4UGetdFrP59kz9HGMiGaUyFXEShiDYlLrZKgc2-kBUKtTkvBwCcmlglQjkrCDU01KO58wsNMqsrE6ZKlNrlArWpRwSXCjjgam8Q6WVKmCShqDSe6tCbxWTNxV6gdFmj23qhizLZrc_1H_AYdhm0IL-9U3aLWarmGO3RgP1fzj-V9vZdftEad-w |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8IwGG4UTdSLXxi_7cFrod3arfXoGIEIgxBMuJF-LSExwyD4-203QD148Na8SZumzfb0bd_neQB49KJs3LjvWzAtEFXKIh7FOXJnf6G8HJ7RldlEnGV8MhHDNVm95MJYa8viM9vwzfIt38z1yl-VNR1UUUpZvAv2GKUBruha2x8vj4NorStKsGh2s_YgGfQZq2q4AtbY9P_lpFICSfv4n1M4AfVvSh4cbsHmFOzY4gwc_VATPAfjZJ7I0RNMPR3KRWBaykO48WCr8p2HrSxDzw63DPQeaG8wqUopoSwMHNkSIqCvEfKxWQH7aVIHr-10nHTQ2jQBzUjMl8gKrBUOcilCr3SvuLaYaBnlMbUuNdE0tsIQjpkikbSCGZfyUBWJPDQyp5EOL0CtmBf2EkCDDQlUqA3PCZXYCqIVwzLXKnR5MzZXoO4XaPpe6WJMN2tz_Uf8ARx0xv3etNfNXm7Aod8S_w5PxC2oLRcrewf29edy9rG4L_f1Cxy5oUI |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Annual+Joint+Conference+of+the+IEEE+Computer+and+Communications+Societies&rft.atitle=CoCaR%3A+Enabling+Efficient+Dynamic+DNN-Based+Model+Caching+and+Request+Routing+in+MEC&rft.au=Qiu%2C+Shuting&rft.au=Dong%2C+Fang&rft.au=Tan%2C+Siyu&rft.au=Shen%2C+Dian&rft.date=2025-05-19&rft.pub=IEEE&rft.eissn=2641-9874&rft.spage=1&rft.epage=10&rft_id=info:doi/10.1109%2FINFOCOM55648.2025.11044457&rft.externalDocID=11044457 |