Federated Deep Reinforcement Learning for Adaptive Spectrum Allocation in Dense 5G-A Wireless Networks
Keywords:
Federated learning, deep reinforcement learning, adaptive spectrum allocation, 5G-Advanced, dense wireless networks, edge intelligence, spectrum management, network orchestration, distributed AI, wireless infrastructure resilienceAbstract
The evolution of fifth-generation advanced wireless systems has intensified the complexity of spectrum allocation in dense heterogeneous communication environments characterized by massive device connectivity, ultra-low latency requirements, network slicing, edge intelligence, and highly dynamic traffic behavior. Traditional spectrum management approaches based on static assignment, centralized optimization, or isolated learning architectures have demonstrated limited scalability under rapidly changing radio conditions and geographically distributed service demands. This paper investigates the integration of federated deep reinforcement learning as a distributed intelligence paradigm for adaptive spectrum allocation in dense 5G-A wireless networks. The study explores how federated collaborative learning mechanisms enable decentralized base stations, edge nodes, and network controllers to jointly optimize spectrum utilization while preserving local operational autonomy and minimizing raw data exchange. The paper develops a system-level analytical framework examining the interaction between spectrum scarcity, edge orchestration, interference management, mobility-aware optimization, and trust-aware policy coordination across heterogeneous radio access infrastructures. Particular attention is given to governance challenges associated with fairness, privacy preservation, model drift, communication overhead, and energy sustainability within large-scale wireless ecosystems. The analysis further evaluates the architectural implications of integrating deep reinforcement learning with federated coordination under high-density urban deployments, industrial communication systems, vehicular networking environments, and critical infrastructure services. Beyond performance optimization, the paper emphasizes the broader socio-technical implications of intelligent spectrum orchestration, including regulatory adaptation, infrastructure inequality, environmental efficiency, and operational resilience. The findings indicate that federated deep reinforcement learning provides a viable pathway toward scalable, adaptive, and resilient spectrum governance for next-generation wireless ecosystems, particularly when supported by cross-layer coordination, policy-aware deployment strategies, and robust edge intelligence frameworks.
References
[1] Andrews, J. G., Buzzi, S., Choi, W., Hanly, S. V., Lozano, A., Soong, A. C., & Zhang, J. C. (2014). What will 5G be? IEEE Journal on Selected Areas in Communications, 32(6), 1065–1082.
[2] Akyildiz, I. F., Nie, S., Lin, S. C., & Chandrasekaran, M. (2016). 5G roadmap: 10 key enabling technologies. Computer Networks, 106, 17–48.
[3] Zhang, Y., Wang, H., Zheng, T., & Yang, Q. (2018). Deep reinforcement learning for resource management in network slicing. IEEE Access, 6, 74429–74441.
[4] Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 19(4), 2322–2358.
[5] Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.
[6] Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T., & Chan, K. (2019). Adaptive federated learning in resource constrained edge computing systems. IEEE Journal on Selected Areas in Communications, 37(6), 1205–1221.
[7] McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Aguera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings of AISTATS, 1273–1282.
[8] Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., Niyato, D., & Poor, H. V. (2020). Federated learning for wireless communications: Motivation, opportunities, and challenges. IEEE Communications Surveys & Tutorials, 22(4), 2642–2683.
[9] Ziegeldorf, J. H., Morchon, O. G., & Wehrle, K. (2014). Privacy in the Internet of Things: Threats and challenges. Security and Communication Networks, 7(12), 2728–2742.
[10] Haykin, S. (2005). Cognitive radio: Brain-empowered wireless communications. IEEE Journal on Selected Areas in Communications, 23(2), 201–220.
[11] Dahlman, E., Parkvall, S., & Skold, J. (2018). 5G NR: The next generation wireless access technology. Academic Press.
[12] Shafi, M., Molisch, A. F., Smith, P. J., Haustein, T., Zhu, P., Silva, P. D., & Wunder, G. (2017). 5G: A tutorial overview of standards, trials, challenges, deployment, and practice. IEEE Journal on Selected Areas in Communications, 35(6), 1201–1221.
[13] Boccardi, F., Heath, R. W., Lozano, A., Marzetta, T. L., & Popovski, P. (2014). Five disruptive technology directions for 5G. IEEE Communications Magazine, 52(2), 74–80.
[14] Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT Press.
[15] Li, Y. (2018). Deep reinforcement learning: An overview. arXiv preprint arXiv:1810.06339.
[16] Chen, M., Challita, U., Saad, W., Yin, C., & Debbah, M. (2017). Artificial neural networks-based machine learning for wireless networks: A tutorial. IEEE Communications Surveys & Tutorials, 21(4), 3039–3071.
[17] Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y. C., Yang, Q., & Miao, C. (2020). Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(3), 2031–2063.
[18] Ye, H., Li, G. Y., & Juang, B. H. (2019). Deep reinforcement learning based resource allocation for V2V communications. IEEE Transactions on Vehicular Technology, 68(4), 3163–3173.
[19] Park, J., Samarakoon, S., Bennis, M., & Debbah, M. (2019). Wireless network intelligence at the edge. Proceedings of the IEEE, 107(11), 2204–2239.
[20] Saad, W., Bennis, M., & Chen, M. (2020). A vision of 6G wireless systems: Applications, trends, technologies, and open research problems. IEEE Network, 34(3), 134–142.
[21] Nasir, A. A., Guo, S., & Wang, J. (2021). Multi-agent deep reinforcement learning for dynamic spectrum access in multichannel wireless networks. IEEE Transactions on Cognitive Communications and Networking, 7(1), 33–45.
[22] Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., & Zhao, S. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210.
[23] Mach, P., & Becvar, Z. (2017). Mobile edge computing: A survey on architecture and computation offloading. IEEE Communications Surveys & Tutorials, 19(3), 1628–1656.
[24] Abbas, N., Zhang, Y., Taherkordi, A., & Skeie, T. (2018). Mobile edge computing: A survey. IEEE Internet of Things Journal, 5(1), 450–465.
[25] Roman, R., Lopez, J., & Mambo, M. (2018). Mobile edge computing, fog et al.: A survey and analysis of security threats and challenges. Future Generation Computer Systems, 78, 680–698.
[26] Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018). Federated learning with non-IID data. arXiv preprint arXiv:1806.00582.
[27] Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., & Van Overveldt, T. (2019). Towards federated learning at scale: System design. Proceedings of MLSys, 374–388.
[28] Samarakoon, S., Bennis, M., Saad, W., & Debbah, M. (2019). Distributed federated learning for ultra-reliable low-latency vehicular communications. IEEE Transactions on Communications, 68(2), 1146–1159.
[29] Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2020). How to backdoor federated learning. Proceedings of AISTATS, 2938–2948.
[30] Foukas, X., Patounas, G., Elmokashfi, A., & Marina, M. K. (2017). Network slicing in 5G: Survey and challenges. IEEE Communications Magazine, 55(5), 94–100.
[31] Wang, X., Han, Y., Wang, V. C. M., Zhao, Q., Chen, X., & Chen, M. (2020). In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning. IEEE Network, 33(5), 156–165.
[32] Challita, U., Ferdowsi, A., Chen, M., & Saad, W. (2019). Machine learning for wireless connectivity and security of cellular-connected UAVs. IEEE Wireless Communications, 26(1), 28–35.
[33] Luong, N. C., Hoang, D. T., Gong, S., Niyato, D., Wang, P., Liang, Y. C., & Kim, D. I. (2019). Applications of deep reinforcement learning in communications and networking. IEEE Communications Surveys & Tutorials, 21(4), 3133–3174.
[34] Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738–1762.
[35] Li, Q. (2026). QoS Assurance Mechanism for 5G Network Slicing Based on the Deep Reinforcement Learning PPO Algorithm. arXiv preprint arXiv:2605.03345.
[36] Sun, Y., Peng, M., Mao, S., Wang, Y., & Liu, C. (2018). Application of machine learning in wireless networks: Key techniques and open issues. IEEE Communications Surveys & Tutorials, 21(4), 3072–3108.
[37] Campolo, C., Molinaro, A., Araniti, G., & Berthet, A. O. (2017). Better platooning control toward autonomous driving: An LTE device-to-device communications strategy. Vehicular Communications, 16, 1–10.
[38] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646.
[39] Wang, C., Wang, C., Liang, Y. C., Chen, F. R., & Cheng, H. (2020). Learning-driven resource allocation for wireless communication systems. IEEE Wireless Communications, 27(4), 10–16.
[40] Rawls, J. (1971). A theory of justice. Harvard University Press.
[41] Nishio, T., & Yonetani, R. (2019). Client selection for federated learning with heterogeneous resources in mobile edge. Proceedings of ICC, 1–7.
[42] Zhu, L., Liu, Z., & Han, S. (2019). Deep leakage from gradients. Advances in Neural Information Processing Systems, 32, 14774–14784.
[43] Wang, J., Liu, Q., Liang, H., Joshi, G., & Poor, H. V. (2020). Tackling the objective inconsistency problem in heterogeneous federated optimization. Advances in Neural Information Processing Systems, 33, 7611–7623.
[44] Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2019). Edge artificial intelligence for 6G: Vision, enabling technologies, and applications. IEEE Journal on Selected Areas in Communications, 40(1), 5–36.
[45] Deng, Y., Lyu, F., Ren, J., Yang, H., Zhou, Y., Zhang, Y., & Shen, X. (2020). FAIR: Quality-aware federated learning for green mobile edge networks. Proceedings of ICC, 1–6.
[46] Hsieh, K., Phanishayee, A., Mutlu, O., & Gibbons, P. B. (2020). The non-IID data quagmire of decentralized machine learning. Proceedings of ICML, 4387–4398.
[47] Tran, N. H., Bao, W., Zomaya, A., Nguyen, M. N. H., & Hong, C. S. (2019). Federated learning over wireless networks: Optimization model design and analysis. Proceedings of INFOCOM, 1387–1395.
[48] Yu, W., Liang, F., He, X., Hatcher, W. G., Lu, C., Lin, J., & Yang, X. (2018). A survey on the edge computing for the Internet of Things. IEEE Access, 6, 6900–6919.
[49] Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2020). The limitations of federated learning in sybil settings. Proceedings of RAID, 301–316.
[50] Shi, Y., Sagduyu, Y. E., Davaslioglu, K., Li, J. H., & Erpek, T. (2021). Adversarial deep learning for cognitive radio security. IEEE Wireless Communications, 28(3), 64–71.
[51] Sutton, R. S. (1990). Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. Proceedings of ICML, 216–224.
[52] van Dijk, J. (2020). The digital divide. Polity Press.
[53] Eubanks, V. (2018). Automating inequality. St. Martin’s Press.
[54] Helou, M. E., Ibrahim, S., & Machanavajjhala, A. (2020). The price of fairness in federated learning. Proceedings of ICML Workshops.
[55] Barocas, S., Hardt, M., & Narayanan, A. (2019). Fairness and machine learning. fairmlbook.org.
[56] Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of ACL, 3645–3650.
[57] Bianzino, A. P., Chaudet, C., Rossi, D., & Rougier, J. L. (2012). A survey of green networking research. IEEE Communications Surveys & Tutorials, 14(1), 3–20.
[58] Jones, N. (2018). How to stop data centres from gobbling up the world’s electricity. Nature, 561(7722), 163–166.
[59] Henderson, P., Hu, J., Romoff, J., Brunskill, E., Jurafsky, D., & Pineau, J. (2018). Deep reinforcement learning that matters. Proceedings of AAAI, 3207–3214.
[60] Ismail, M., Zhuang, W., Serpedin, E., & Qaraqe, K. (2015). A survey on green mobile networking: From the perspectives of network operators and mobile users. IEEE Communications Surveys & Tutorials, 17(3), 1535–1556.
[61] Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60.
[62] Xu, D., Li, P., Guo, S., & Wu, S. (2021). Deep reinforcement learning enabled green heterogeneous networks. IEEE Transactions on Green Communications and Networking, 5(3), 1109–1121.
[63] Han, T., & Ansari, N. (2018). Green mobile edge computing for 5G and beyond. IEEE Communications Magazine, 56(8), 123–129.
[64] Chien, S. Y., Hsiang, H. P., Hsu, C. Y., & Wang, K. C. (2020). Deep learning-based energy-efficient resource allocation for future wireless networks. IEEE Access, 8, 56813–56827.
[65] Parajuly, K., Kuehr, R., Awasthi, A. K., Fitzpatrick, C., Lepawsky, J., Smith, E., & Zeng, X. (2019). Future e-waste scenarios. United Nations University.
[66] Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S., & Zomaya, A. Y. (2020). Edge intelligence: The confluence of edge computing and artificial intelligence. IEEE Internet of Things Journal, 7(8), 7457–7469.
[67] IPCC. (2022). Climate change 2022: Impacts, adaptation and vulnerability. Cambridge University Press.
[68] Sen, A. (2009). The idea of justice. Harvard University Press.
[69] European Commission. (2020). A new circular economy action plan. Brussels.
[70] Cave, M., & Webb, W. (2015). Spectrum management: Using the airwaves for maximum social and economic benefit. Cambridge University Press.
[71] Floridi, L., & Cowls, J. (2019). A unified framework of five principles for AI in society. Harvard Data Science Review, 1(1), 1–15.
[72] Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608.
[73] Shokri, R., & Shmatikov, V. (2015). Privacy-preserving deep learning. Proceedings of CCS, 1310–1321.
[74] Nye, J. S. (2011). The future of power. Public Affairs.
[75] Weiss, M. B., Lehr, W. H., & Cui, Y. (2015). Technological change and spectrum governance. Telecommunications Policy, 39(10–11), 824–836.
[76] 3GPP. (2022). Study on AI/ML for NR air interface. Technical Specification Group Radio Access Network.
[77] Noble, S. U. (2018). Algorithms of oppression. NYU Press.
[78] ENISA. (2021). Threat landscape for 5G networks. European Union Agency for Cybersecurity.
[79] Winner, L. (1980). Do artifacts have politics? Daedalus, 109(1), 121–136.
[80] OECD. (2019). OECD principles on artificial intelligence. OECD Publishing.
[81] Cisco. (2023). Annual internet report. Cisco Systems.
[82] Batty, M. (2018). Inventing future cities. MIT Press.
[83] Zanella, A., Bui, N., Castellani, A., Vangelista, L., & Zorzi, M. (2014). Internet of Things for smart cities. IEEE Internet of Things Journal, 1(1), 22–32.
[84] Lu, Y. (2017). Industry 4.0: A survey on technologies, applications and open research issues. Journal of Industrial Information Integration, 6, 1–10.
[85] Xu, X., Lu, Y., Vogel-Heuser, B., & Wang, L. (2021). Industry 4.0 and Industry 5.0: Inception, conception and perception. Journal of Manufacturing Systems, 61, 530–535.
[86] Gerla, M., Lee, E. K., Pau, G., & Lee, U. (2014). Internet of vehicles: From intelligent grid to autonomous cars and vehicular clouds. Proceedings of WF-IoT, 241–246.
[87] Hartenstein, H., & Laberteaux, K. P. (2010). VANET: Vehicular applications and inter-networking technologies. Wiley.
[88] Islam, S. M. R., Kwak, D., Kabir, M. H., Hossain, M., & Kwak, K. S. (2015). The Internet of Things for health care: A comprehensive survey. IEEE Access, 3, 678–708.
[89] Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H. R., Albarqouni, S., & Cardoso, M. J. (2020). The future of digital health with federated learning. NPJ Digital Medicine, 3(119), 1–7.
[90] Townsend, A. M. (2013). Smart cities. W. W. Norton & Company.
[91] Graham, M. (2019). Digital economies at global margins. MIT Press.
[92] Taddeo, M., & Floridi, L. (2018). How AI can be a force for good. Science, 361(6404), 751–752.
[93] Scharre, P. (2018). Army of none: Autonomous weapons and the future of war. W. W. Norton & Company.
[94] Comfort, L. K. (2007). Crisis management in hindsight. Public Administration Review, 67, 189–197.
[95] Latva-aho, M., & Leppanen, K. (2019). Key drivers and research challenges for 6G ubiquitous wireless intelligence. University of Oulu.
[96] Strinati, E. C., Barbarossa, S., Gonzalez-Jimenez, J. L., Ktenas, D., Cassau, J., Maret, L., & Dehos, C. (2021). 6G: The next frontier. arXiv preprint arXiv:1901.03239.
[97] Dang, S., Amin, O., Shihada, B., & Alouini, M. S. (2020). What should 6G be? Nature Electronics, 3(1), 20–29.
[98] Zhang, N., Yang, P., Ren, J., Shen, X., & Mark, J. W. (2019). Software defined space-air-ground integrated vehicular networks. IEEE Communications Magazine, 57(7), 50–56.
[99] Tao, F., Zhang, H., Liu, A., & Nee, A. Y. C. (2019). Digital twin in industry: State-of-the-art. IEEE Transactions on Industrial Informatics, 15(4), 2405–2415.
[100] Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1–38.
[101] Lu, Y., Huang, X., Dai, Y., Maharjan, S., & Zhang, Y. (2020). Blockchain and federated learning for privacy-preserved data sharing in industrial IoT. IEEE Transactions on Industrial Informatics, 16(6), 4177–4186.
[102] Gyongyosi, L., & Imre, S. (2019). A survey on quantum computing technology. Computer Science Review, 31, 51–71.
[103] Wu, Y., Khisti, A., Xiao, C., Caire, G., Wong, K. K., & Gao, X. (2018). A survey of physical layer security techniques for 5G wireless networks. IEEE Journal on Selected Areas in Communications, 36(4), 679–695.
[104] Couldry, N., & Mejias, U. A. (2019). The costs of connection. Stanford University Press.
[105] Jasanoff, S. (2016). The ethics of invention. W. W. Norton & Company.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Computational Intelligence Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
