{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:09:34Z","timestamp":1775326174633,"version":"3.50.1"},"reference-count":24,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T00:00:00Z","timestamp":1658188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Research Council of Canada"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Starting from the concept of the Cloud Radio Access Network (C-RAN), continuing with the virtual Radio Access Network (vRAN) and most recently with the Open RAN (O-RAN) initiative, Radio Access Network (RAN) architectures have significantly evolved in the past decade. In the last few years, the wireless industry has witnessed a strong trend towards disaggregated, virtualized and open RANs, with numerous tests and deployments worldwide. One unique aspect that motivates this paper is the availability of new opportunities that arise from using machine learning, more specifically multi-agent team learning (MATL), to optimize the RAN in a closed-loop where the complexity of disaggregation and virtualization makes well-known Self-Organized Networking (SON) solutions inadequate. In our view, Multi-Agent Systems (MASs) with MATL can play an essential role in the orchestration of O-RAN controllers, i.e., near-real-time and non-real-time RAN Intelligent Controllers (RIC). In this article, we first provide an overview of the landscape in RAN disaggregation, virtualization and O-RAN, then we present the state-of-the-art research in multi-agent systems and team learning as well as their application to O-RAN. We present a case study for team learning where agents are two distinct xApps: power allocation and radio resource allocation. We demonstrate how team learning can enhance network performance when team learning is used instead of individual learning agents. Finally, we identify challenges and open issues to provide a roadmap for researchers in the area of MATL based O-RAN optimization.<\/jats:p>","DOI":"10.3390\/s22145375","type":"journal-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T08:28:25Z","timestamp":1658219305000},"page":"5375","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Multi-Agent Team Learning in Virtualized Open Radio Access Networks (O-RAN)"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8757-2639","authenticated-orcid":false,"given":"Pedro Enrique","family":"Iturria-Rivera","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada"}]},{"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4869-1934","authenticated-orcid":false,"given":"Shahram","family":"Mollahasani","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6787-8457","authenticated-orcid":false,"given":"Melike","family":"Erol-Kantarci","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Trakadas, P., Sarakis, L., Giannopoulos, A., Spantideas, S., Capsalis, N., Gkonis, P., Karkazis, P., Rigazzi, G., Antonopoulos, A., and Cambeiro, M.A. (2021). A Cost-Efficient 5G Non-Public Network Architectural Approach: Key Concepts and Enablers, Building Blocks and Potential Use Cases. Sensors, 21.","DOI":"10.3390\/s21165578"},{"key":"ref_2","first-page":"120","article-title":"Spectrum Sharing for 5G\/6G URLLC: Research Frontiers and Standards","volume":"5","author":"Yang","year":"2021","journal-title":"IEEE Commun. Mag."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MVT.2019.2919236","article-title":"AI-Enabled Future Wireless Networks: Challenges, Opportunities, and Open Issues","volume":"14","author":"Elsayed","year":"2019","journal-title":"IEEE Veh. Technol. Mag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1109\/COMST.2020.2965856","article-title":"Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks","volume":"22","author":"Wang","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/MNET.2020.9277891","article-title":"A perspective of O-RAN integration with MEC, SON, and network slicing in the 5G era","volume":"34","author":"Kuklinski","year":"2020","journal-title":"IEEE Netw."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"28573","DOI":"10.1109\/ACCESS.2018.2831228","article-title":"Multi-Agent Systems: A Survey","volume":"6","author":"Dorri","year":"2018","journal-title":"IEEE Access"},{"key":"ref_7","unstructured":"O-RAN Working Group 1 (2022, April 10). O-RAN Architecture Description 6.00,\u201d O-RAN.WG1.O-RAN-Architecture-Description-v06.00. Available online: https:\/\/orandownloadsweb.azurewebsites.net\/specifications."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Polese, M., Bonati, L., D\u2019Oro, S., Basagni, S., and Melodia, T. (2022). Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research Challenges. arXiv.","DOI":"10.1109\/COMST.2023.3239220"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"39580","DOI":"10.1109\/ACCESS.2022.3166160","article-title":"Supporting Intelligence in Disaggregated Open Radio Access Networks: Architectural Principles, AI\/ML Workflow, and Use Cases","volume":"10","author":"Giannopoulos","year":"2022","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1109\/COMST.2014.2355255","article-title":"Cloud RAN for Mobile Networks\u2014A Technology Overview","volume":"17","author":"Checko","year":"2015","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MCOMSTD.101.2000014","article-title":"O-RAN: Disrupting the Virtualized RAN Ecosystem","volume":"5","year":"2021","journal-title":"IEEE Commun. Stand. Mag."},{"key":"ref_12","unstructured":"O-RAN Working Group 2 (2021, November 05). O-RAN AI\/ML Workflow Description and Requirements\u2013v1.03. Available online: https:\/\/orandownloadsweb.azurewebsites.net\/specifications."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/MIC.2021.3062487","article-title":"RIC: A RAN Intelligent Controller Platform for AI-Enabled Cellular Networks","volume":"25","author":"Balasubramanian","year":"2021","journal-title":"IEEE Internet Comput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCOM.101.2001120","article-title":"Intelligence and Learning in O-RAN for Data-Driven NextG Cellular Networks","volume":"59","author":"Bonati","year":"2021","journal-title":"IEEE Commun. Mag."},{"key":"ref_15","unstructured":"Dryja\u0144ski, M., and Kliks, A. (2022, April 02). The O-RAN Whitepaper 2022 RAN Intelligent Controller, xApps and rApps. Available online: https:\/\/rimedolabs.com\/blog\/the-oran-whitepaper-2022-ran-intelligent-controller."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Dryja\u0144ski, M., Ku\u0142acz, L., and Kliks, A. (2021). Toward Modular and Flexible Open RAN Implementations in 6G Networks: Traffic Steering Use Case and O-RAN xApps. Sensors, 21.","DOI":"10.3390\/s21248173"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cao, Y., Lien, S.Y., Liang, Y.C., and Chen, K.C. (2021, January 14\u201323). Federated Deep Reinforcement Learning for User Access Control in Open Radio Access Networks. Proceedings of the IEEE International Conference on Communications, Montreal, QC, Canada.","DOI":"10.1109\/ICC42927.2021.9500603"},{"key":"ref_18","unstructured":"O-RAN-SC (2021, November 20). RIC Message Router\u2013RMR. Available online: https:\/\/docs.o-ran-sc.org\/projects\/o-ran-sc-ric-plt-lib-rmr\/en\/latest\/rmr.7.html."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107516","DOI":"10.1016\/j.comnet.2020.107516","article-title":"Open, Programmable, and Virtualized 5G Networks: State-of-the-Art and the Road Ahead","volume":"182","author":"Bonati","year":"2020","journal-title":"Comput. Netw."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"154237","DOI":"10.1109\/ACCESS.2020.3018267","article-title":"A Distributed Assignment Method for Dynamic Traffic Assignment Using Heterogeneous-Adviser Based Multi-Agent Reinforcement Learning","volume":"8","author":"Pan","year":"2020","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2014","DOI":"10.1109\/JIOT.2021.3089334","article-title":"BrainIoT: Brain-Like Productive Services Provisioning With Federated Learning in Industrial IoT","volume":"9","author":"Yang","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Elsayed, M., and Erol-Kantarci, M. (2019, January 9\u201313). Reinforcement learning-based joint power and resource allocation for URLLC in 5G. Proceedings of the 2019 IEEE Global Communications Conference, GLOBECOM 2019\u2013Proceedings, Waikoloa, HI, USA.","DOI":"10.1109\/GLOBECOM38437.2019.9014032"},{"key":"ref_23","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yongacoglu, B., Arslan, G., and Yuksel, S. (2019, January 11\u201313). Reinforcement Learning for Decentralized Stochastic Control. Proceedings of the 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France.","DOI":"10.1109\/CDC40024.2019.9030158"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5375\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:53:41Z","timestamp":1760140421000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5375"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,19]]},"references-count":24,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22145375"],"URL":"https:\/\/doi.org\/10.3390\/s22145375","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,19]]}}}