{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:36:07Z","timestamp":1777487767209,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.K. EPSRC NGCDI","award":["EP\/R004935\/1"],"award-info":[{"award-number":["EP\/R004935\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnsm.2023.3316074","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:39:51Z","timestamp":1694799591000},"page":"1115-1128","source":"Crossref","is-referenced-by-count":14,"title":["Deep Reinforcement Learning for Robust VNF Reconfigurations in O-RAN"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3520-6350","authenticated-orcid":false,"given":"Esmaeil","family":"Amiri","sequence":"first","affiliation":[{"name":"5G\/6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3053-0515","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"5G\/6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-5086","authenticated-orcid":false,"given":"Mohammad","family":"Shojafar","sequence":"additional","affiliation":[{"name":"5G\/6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-4021","authenticated-orcid":false,"given":"Mutasem Q.","family":"Hamdan","sequence":"additional","affiliation":[{"name":"5G\/6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5716-1396","authenticated-orcid":false,"given":"Chuan Heng","family":"Foh","sequence":"additional","affiliation":[{"name":"5G\/6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6062-8639","authenticated-orcid":false,"given":"Rahim","family":"Tafazolli","sequence":"additional","affiliation":[{"name":"5G\/6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]}],"member":"263","reference":[{"key":"ref1","article-title":"Understanding O-RAN: Architecture, interfaces, algorithms, security, and research challenges","author":"Polese","year":"2022","journal-title":"arXiv:2202.01032"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3040791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCN53696.2022.9843310"},{"key":"ref4","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016","journal-title":"arXiv:1611.09940"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93031-2_12"},{"key":"ref6","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mirhoseini"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3065049"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2974484"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3179811"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959183"},{"key":"ref11","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45586-8_4"},{"key":"ref13","article-title":"Constrained combinatorial optimization with reinforcement learning","author":"Solozabal","year":"2020","journal-title":"arXiv:2006.11984"},{"key":"ref14","volume-title":"Small Cell Virtualization: Functional Splits and Use Cases","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2868805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/lwc.2023.3298548"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2019.2948457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3171525"},{"issue":"1987","key":"ref19","first-page":"1","article-title":"IBM ILOG CPLEX optimization studio","volume":"12","author":"Manual","year":"1987","journal-title":"Version"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488786"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3205415"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108682"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3221670"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107809"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM52442.2021.9615541"},{"key":"ref26","volume-title":"Gurobi optimizer reference manual","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001658"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3001227"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500721"},{"key":"ref30","volume-title":"O-RAN: Towards an open and smart RAN","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/KBEI.2019.8734982"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICWR51868.2021.9443024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-019-00594-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.11591\/eei.v9i4.2393"},{"key":"ref35","volume-title":"O-RAN Working Group 2 (Non-RT RIC and A1 Interface WG) Non-RT RIC Architecture (O-RAN.WG2.Non-RT-RIC-ARCH-TS-v02.01)","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2004.09.016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800155"},{"key":"ref38","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018","journal-title":"arXiv:1805.11074"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2874142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2022.100514"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4275028\/10423826\/10252014.pdf?arnumber=10252014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T19:15:02Z","timestamp":1707765302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10252014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":40,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2023.3316074","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}