{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,11]],"date-time":"2025-05-11T04:01:46Z","timestamp":1746936106837,"version":"3.40.5"},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,24]]},"DOI":"10.1109\/wcnc61545.2025.10978306","type":"proceedings-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:53:33Z","timestamp":1746813213000},"page":"01-07","source":"Crossref","is-referenced-by-count":0,"title":["Active Prompt Caching in Edge Networks for Generative AI and LLMs: An RL-Based Approach"],"prefix":"10.1109","author":[{"given":"Emna","family":"Baccour","sequence":"first","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation,Doha,Qatar"}]},{"given":"Aiman","family":"Erbad","sequence":"additional","affiliation":[{"name":"College of Engineering, Qatar University,Doha,Qatar"}]},{"given":"Amr","family":"Mohamed","sequence":"additional","affiliation":[{"name":"College of Engineering, Qatar University,Doha,Qatar"}]},{"given":"Mounir","family":"Hamdi","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation,Doha,Qatar"}]},{"given":"Mohsen","family":"Guizani","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,UAE"}]}],"member":"263","reference":[{"volume-title":"A survey of large language models","year":"2024","author":"Zhao","key":"ref1"},{"volume-title":"Deakin\u2019s genie: A virtual digital assistant out of the bottle","year":"2019","author":"University","key":"ref2"},{"volume-title":"Edgeshard: Efficient llm inference via collaborative edge computing","year":"2024","author":"Zhang","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/WCNC57260.2024.10571127"},{"volume-title":"Flexgen: High-throughput generative inference of large language models with a single gpu","year":"2023","author":"Sheng","key":"ref5"},{"volume-title":"Efficient prompt caching via embedding similarity","year":"2024","author":"Zhu","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1016\/j.jnca.2020.102801"},{"volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2022","author":"Nichol","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/COMST.2022.3200740"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TNSE.2022.3165472"},{"volume-title":"A block successive upper bound minimization method of multipliers for linearly constrained convex optimization","year":"2014","author":"Hong","key":"ref11"}],"event":{"name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","start":{"date-parts":[[2025,3,24]]},"location":"Milan, Italy","end":{"date-parts":[[2025,3,27]]}},"container-title":["2025 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10978109\/10978116\/10978306.pdf?arnumber=10978306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:39:10Z","timestamp":1746859150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10978306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/wcnc61545.2025.10978306","relation":{},"subject":[],"published":{"date-parts":[[2025,3,24]]}}}