{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T07:30:31Z","timestamp":1770276631811,"version":"3.49.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T00:00:00Z","timestamp":1751587200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T00:00:00Z","timestamp":1751587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-21-CE25-0019"],"award-info":[{"award-number":["ANR-21-CE25-0019"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-21-CE25-0019"],"award-info":[{"award-number":["ANR-21-CE25-0019"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Netw Syst Manage"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s10922-025-09935-y","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T07:06:31Z","timestamp":1751612791000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Policy-Gradient-Based Reinforcement Learning for Maximizing Operator\u2019s Profit in Open-RAN"],"prefix":"10.1007","volume":"33","author":[{"given":"Mahdi","family":"Sharara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sahar","family":"Hoteit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannick","family":"Carlinet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonia Maria","family":"Masucci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nancy","family":"Perrot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,4]]},"reference":[{"key":"9935_CR1","first-page":"1","volume":"2","author":"C Mobile","year":"2011","unstructured":"Mobile, C.: C-RAN: the road towards green RAN. White Paper Ver. 2, 1\u201310 (2011)","journal-title":"White Paper Ver."},{"key":"9935_CR2","doi-asserted-by":"publisher","unstructured":"Kumar, A., Hallur, G.G.: Economic and technical implications of implementation of OpenRAN by \"RAKUTEN MOBILE\". In: 2022 International Conference on Decision Aid Sciences and Applications (DASA), pp. 959\u2013964 (2022). https:\/\/doi.org\/10.1109\/DASA54658.2022.9764985","DOI":"10.1109\/DASA54658.2022.9764985"},{"issue":"10","key":"9935_CR3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MCOM.101.2001120","volume":"59","author":"L Bonati","year":"2021","unstructured":"Bonati, L., D\u2019Oro, S., Polese, M., Basagni, S., Melodia, T.: Intelligence and learning in O-RAN for data-driven nextG cellular networks. IEEE Commun. Mag. 59(10), 21\u201327 (2021). https:\/\/doi.org\/10.1109\/MCOM.101.2001120","journal-title":"IEEE Commun. Mag."},{"key":"9935_CR4","unstructured":"Cloud Architecture and Deployment Scenarios for O-RAN Virtualized RAN (2019)"},{"key":"9935_CR5","unstructured":"Polese, M., Bonati, L., D\u2019Oro, S., Basagni, S., Melodia, T.: Understanding O-RAN: architecture, interfaces, algorithms, security, and research challenges. Preprint at http:\/\/arxiv.org\/2202.01032 (2022)"},{"key":"9935_CR6","doi-asserted-by":"publisher","unstructured":"Sharara, M., Hoteit, S., V\u00e8que, V.: Reinforcement learning based model for maximizing operator\u2019s profit in open-RAN. In: NOMS 2023-2023 IEEE\/IFIP Network Operations and Management Symposium, pp. 1\u20135 (2023). https:\/\/doi.org\/10.1109\/NOMS56928.2023.10154452","DOI":"10.1109\/NOMS56928.2023.10154452"},{"key":"9935_CR7","doi-asserted-by":"publisher","unstructured":"Shi, Y., Sagduyu, Y.E., Erpek, T.: Reinforcement learning for dynamic resource optimization in 5G radio access network slicing. In: 2020 IEEE 25th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), pp. 1\u20136 (2020). https:\/\/doi.org\/10.1109\/CAMAD50429.2020.9209299","DOI":"10.1109\/CAMAD50429.2020.9209299"},{"key":"9935_CR8","doi-asserted-by":"publisher","unstructured":"Elsayed, M., Erol-Kantarci, M.: AI-enabled radio resource allocation in 5G for URLLC and eMBB users. In: 2019 IEEE 2nd 5G World Forum (5GWF), pp. 590\u2013595 (2019). https:\/\/doi.org\/10.1109\/5GWF.2019.8911618","DOI":"10.1109\/5GWF.2019.8911618"},{"issue":"9","key":"9935_CR9","doi-asserted-by":"publisher","first-page":"6063","DOI":"10.1109\/TCOMM.2021.3090423","volume":"69","author":"J Mei","year":"2021","unstructured":"Mei, J., Wang, X., Zheng, K., Boudreau, G., Sediq, A.B., Abou-Zeid, H.: Intelligent radio access network slicing for service provisioning in 6G: a hierarchical deep reinforcement learning approach. IEEE Trans. Commun. 69(9), 6063\u20136078 (2021). https:\/\/doi.org\/10.1109\/TCOMM.2021.3090423","journal-title":"IEEE Trans. Commun."},{"key":"9935_CR10","doi-asserted-by":"publisher","unstructured":"Sharara, M., Hoteit, S., V\u00e9que, V.: Reinforcement learning for inter-operator sharing in open-ran. In: IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp. 01\u201306 (2024). https:\/\/doi.org\/10.1109\/INFOCOMWKSHPS61880.2024.10620880","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620880"},{"key":"9935_CR11","doi-asserted-by":"publisher","unstructured":"Murti, F.W., Ali, S., Latva-aho, M.: Deep reinforcement based optimization of function splitting in virtualized radio access networks. In: 2021 IEEE International Conference on Communications Workshops (ICC Workshops), pp. 1\u20136 (2021). https:\/\/doi.org\/10.1109\/ICCWorkshops50388.2021.9473703","DOI":"10.1109\/ICCWorkshops50388.2021.9473703"},{"key":"9935_CR12","unstructured":"Sharara, M., Hoteit, S., Brown, P., V\u00e8que, V.: Coordination between radio and computing schedulers in cloud-RAN. In: 2021 IFIP\/IEEE International Symposium on Integrated Network Management (IM) (2021)"},{"issue":"3","key":"9935_CR13","doi-asserted-by":"publisher","first-page":"2990","DOI":"10.1109\/TNSM.2022.3222068","volume":"20","author":"M Sharara","year":"2023","unstructured":"Sharara, M., Hoteit, S., Brown, P., V\u00e8que, V.: On coordinated scheduling of radio and computing resources in cloud-ran. IEEE Trans. Netw. Serv. Manage. 20(3), 2990\u20133003 (2023). https:\/\/doi.org\/10.1109\/TNSM.2022.3222068","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"key":"9935_CR14","doi-asserted-by":"crossref","unstructured":"Sharara, M., Hoteit, S., V\u00e8que, V.: A Recurrent neural network based approach for coordinating radio and computing resources allocation in cloud-RAN. In: 2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR) (2021)","DOI":"10.1109\/HPSR52026.2021.9481812"},{"key":"9935_CR15","doi-asserted-by":"publisher","unstructured":"Hojeij, H., Sharara, M., Hoteit, S., V\u00e8que, V.: Dynamic placement of O-CU and O-DU functionalities in open-RAN architecture. In: 2023 20th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON), pp. 330\u2013338 (2023). https:\/\/doi.org\/10.1109\/SECON58729.2023.10287529","DOI":"10.1109\/SECON58729.2023.10287529"},{"key":"9935_CR16","doi-asserted-by":"publisher","unstructured":"Sharara, M., Hoteit, S., V\u00e8que, V., Bassi, F.: Minimizing power consumption by joint radio and computing resource allocation in cloud-ran. In: 2022 IEEE Symposium on Computers and Communications (ISCC), pp. 1\u20136 (2022). https:\/\/doi.org\/10.1109\/ISCC55528.2022.9912943","DOI":"10.1109\/ISCC55528.2022.9912943"},{"key":"9935_CR17","doi-asserted-by":"publisher","first-page":"109870","DOI":"10.1016\/j.comnet.2023.109870","volume":"234","author":"M Sharara","year":"2023","unstructured":"Sharara, M., Fossati, F., Hoteit, S., V\u00e8que, V., Bassi, F.: Minimizing energy consumption by joint radio and computing resource allocation in cloud-RAN. Comput. Netw. 234, 109870 (2023). https:\/\/doi.org\/10.1016\/j.comnet.2023.109870","journal-title":"Comput. Netw."},{"key":"9935_CR18","doi-asserted-by":"publisher","unstructured":"Shekhawat, J.S., Agrawal, R., Shenoy, K.G., Shashidhara, R.: A reinforcement learning framework for QoS-driven radio resource scheduler. In: GLOBECOM 2020 - 2020 IEEE Global Communications Conference, pp. 1\u20137 (2020). https:\/\/doi.org\/10.1109\/GLOBECOM42002.2020.9322182","DOI":"10.1109\/GLOBECOM42002.2020.9322182"},{"key":"9935_CR19","doi-asserted-by":"publisher","unstructured":"Sharara, M., Pamuklu, T., Hoteit, S., V\u00e8que, V., Erol-Kantarci, M.: Policy-gradient-based reinforcement learning for computing resources allocation in O-RAN. In: 2022 IEEE 11th International Conference on Cloud Networking (CloudNet), pp. 229\u2013236 (2022). https:\/\/doi.org\/10.1109\/CloudNet55617.2022.9978863","DOI":"10.1109\/CloudNet55617.2022.9978863"},{"key":"9935_CR20","doi-asserted-by":"crossref","unstructured":"Mollahasani, S., Erol-Kantarci, M., Hirab, M., Dehghan, H., Wilson, R.: Actor-Critic Learning Based QoS-Aware Scheduler for Reconfigurable Wireless Networks (2021)","DOI":"10.1109\/TNSE.2021.3070476"},{"key":"9935_CR21","unstructured":"Mollahasani, S., Erol-Kantarci, M., Wilson, R.: Dynamic CU-DU Selection for Resource Allocation in O-RAN Using Actor-Critic Learning"},{"key":"9935_CR22","doi-asserted-by":"publisher","unstructured":"Varga, J., Hilt, A., Rotter, C., J\u00e1r\u00f3, G.: Providing ultra-reliable low latency services for 5G with unattended datacenters. In: 2018 11th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP), pp. 1\u20134 (2018). https:\/\/doi.org\/10.1109\/CSNDSP.2018.8471756","DOI":"10.1109\/CSNDSP.2018.8471756"},{"key":"9935_CR23","doi-asserted-by":"publisher","first-page":"37","DOI":"10.36244\/ICJ.2018.4.6","volume":"2018","author":"J Varga","year":"2018","unstructured":"Varga, J., Hilt, A., B\u00edr\u00f3, J., Rotter, C., J\u00e1r\u00f3, G.: Reducing operational costs of ultra-reliable low latency services in 5G. Infocommun. J. 2018, 37\u201345 (2018)","journal-title":"Infocommun. J."},{"key":"9935_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24488-9","volume-title":"Combinatorial Optimization: Theory and Algorithms","author":"B Korte","year":"2012","unstructured":"Korte, B., Vygen, J.: Combinatorial Optimization: Theory and Algorithms, 5th edn. Springer, Berlin (2012)","edition":"5"},{"key":"9935_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"key":"9935_CR26","unstructured":"5G; NR; Physical Layer Procedures for Data, ETSI TS 138 214 V15.3.0"},{"key":"9935_CR27","doi-asserted-by":"publisher","unstructured":"Khatibi, S., Shah, K., Roshdi, M.: Modelling of computational resources for 5G RAN. In: 2018 European Conference on Networks and Communications (EuCNC), pp. 1\u20135 (2018). https:\/\/doi.org\/10.1109\/EuCNC.2018.8442563","DOI":"10.1109\/EuCNC.2018.8442563"},{"key":"9935_CR28","unstructured":"Andrychowicz, M., Raichuk, A., Stanczyk, P., Orsini, M., Girgin, S., Marinier, R., Hussenot, L., Geist, M., Pietquin, O., Michalski, M., Gelly, S., Bachem, O.: What matters in on-policy reinforcement learning? A large-scale empirical study. CoRR. Preprint at http:\/\/arxiv.org\/2006.05990 (2020)"},{"key":"9935_CR29","doi-asserted-by":"crossref","unstructured":"D\u2019Oro, S., Polese, M., Bonati, L., Cheng, H., Melodia, T.: dApps: distributed applications for real-time inference and control in O-RAN. Preprint at http:\/\/arxiv.org\/2203.02370 (2022)","DOI":"10.1109\/MCOM.002.2200079"},{"key":"9935_CR30","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1016\/j.neunet.2022.10.022","volume":"157","author":"J Pan","year":"2023","unstructured":"Pan, J., Huang, J., Cheng, G., Zeng, Y.: Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach. Neural Netw. 157, 288\u2013304 (2023). https:\/\/doi.org\/10.1016\/j.neunet.2022.10.022","journal-title":"Neural Netw."}],"container-title":["Journal of Network and Systems Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10922-025-09935-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10922-025-09935-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10922-025-09935-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T20:02:59Z","timestamp":1758830579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10922-025-09935-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,4]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["9935"],"URL":"https:\/\/doi.org\/10.1007\/s10922-025-09935-y","relation":{},"ISSN":["1064-7570","1573-7705"],"issn-type":[{"value":"1064-7570","type":"print"},{"value":"1573-7705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,4]]},"assertion":[{"value":"27 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"83"}}