ACE-PPO and MDE-IDS: a novel approach for efficiency and security in 5G optical networks
-
Piyush Kulshreshtha
Abstract
This paper proposes a novel dual-strategy intelligent framework to enhance the efficiency and security of high-speed 5G optical networks. The framework, labeled as attention and curriculum learning enhanced proximal policy optimization (ACE-PPO), is introduced for efficiency optimization. It manages optical signal processing beamforming and power control by focusing on key features like user locations and channel conditions, improving spectral efficiency and signal quality without requiring the overheads of explicit channel state information (CSI). For security, an intrusion detection system (MDE-IDS) based on a mutual distillation ensemble model is proposed. It synergistically combines a temporal convolutional network, a convolutional neural network, and a transformer, using a cross-attention gate and mutual distillation to boost robustness against sophisticated cyber threats in a 5G optical network. Simulations show ACE-PPO outperforms baselines, achieving a 14 % higher signal to interference plus noise ratio (SINR) and 5 % lower power consumption, while MDE-IDS provides higher detection accuracy. The framework forms a holistic approach for intelligent and resilient 5G optical networks.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The author states no conflict of interest.
-
Research funding: None declared.
-
Data availability: Not Applicable.
References
1. Caroline, BE, Xavier, SC, Kabilan, AP, William, J. Performance analysis and comparison of optical signal processing beamforming networks: a survey. Photonic Netw Commun 2019;37:38–52. https://doi.org/10.1007/s11107-018-0802-8.Search in Google Scholar
2. Hojatian, H, Nadal, J, Frigon, JF, Leduc-Primeau, F. Decentralized beamforming for cell-free massive MIMO with unsupervised learning. IEEE Commun Lett 2022;26:1042–6. https://doi.org/10.1109/lcomm.2022.3157161.Search in Google Scholar
3. Elrashidy, M, Masood, M, Nasir, AA. Unsupervised learning approach for distributed beamforming in cell-free integrated sensing and communication with dynamic balancing method. Phys Commun 2025;69:102591. https://doi.org/10.1016/j.phycom.2024.102591.Search in Google Scholar
4. Geranmayeh, P, Grass, E. Machine learning based beam selection for maximizing wireless network capacity. IEEE Access 2024;12:45176–86. https://doi.org/10.1109/access.2024.3381542.Search in Google Scholar
5. Shlezinger, N, Ma, M, Lavi, O, Nguyen, NT, Eldar, YC, Juntti, M. Artificial intelligence-empowered hybrid multiple-input/multiple-output beamforming: Learning to optimize for high-throughput scalable MIMO. IEEE Veh Technol Mag 2024;19:58–67.10.1109/MVT.2024.3396927Search in Google Scholar
6. Murshed, RU, Ashraf, ZB, Hridhon, AH, Munasinghe, K, Jamalipour, A, Hossain, MF. A CNN-LSTM-based fusion separation deep neural network for 6G ultra-massive MIMO hybrid beamforming. IEEE Access 2023;11:38614–30. https://doi.org/10.1109/access.2023.3266355.Search in Google Scholar
7. Mismar, FB, Evans, BL, Alkhateeb, A. Deep reinforcement learning for 5G networks: joint beamforming, power control, and interference coordination. IEEE Trans Commun 2020;68:1581–92. https://doi.org/10.1109/tcomm.2019.2961332.Search in Google Scholar
8. Wang, Q, Feng, K, Li, X, Jin, S. PrecoderNet: hybrid beamforming for millimeter wave systems with deep reinforcement learning. IEEE Wireless Communications Letters 2020;9:1677–81. https://doi.org/10.1109/lwc.2020.3001121.Search in Google Scholar
9. Li, W, Ni, W, Tian, H, Hua, M. Deep reinforcement learning for energy-efficient beamforming design in cell-free networks. In:IEEE Wireless Communications and Networking Conference Workshops (WCNCW). IEEE, Nanjing, China; 2021:1–6 pp.10.1109/WCNCW49093.2021.9420002Search in Google Scholar
10. Fredj, F, Al-Eryani, S, Maghsudi, S, Akrout, M, Hossain, E. Distributed beamforming techniques for cell-free wireless networks using deep reinforcement learning. IEEE Transactions on Cognitive Communications and Networking 2022;8:1186–201. https://doi.org/10.1109/tccn.2022.3165810.Search in Google Scholar
11. Tarafder, P, Choi, W. Deep reinforcement learning-based coordinated beamforming for mm-Wave massive MIMO vehicular networks. Sensors 2023;23:2772. https://doi.org/10.3390/s23052772.Search in Google Scholar PubMed PubMed Central
12. Li, B, Liu, W, Xie, W. Joint resource allocation and beamforming design for RIS-Aided symbiotic radio networks: a DRL approach. Digital Communications and Networks 2024;10:1566–75. https://doi.org/10.1016/j.dcan.2024.03.002.Search in Google Scholar
13. Li, Y, Lu, Y, Ai, B, Dobre, OA, Ding, Z, Niyato, D. GNN-based beamforming for sum-rate maximization in MU-MISO networks. IEEE Trans Wireless Commun 2024;23:9251–64. https://doi.org/10.1109/twc.2024.3361174.Search in Google Scholar
14. Yan, Y, Zhang, B, Li, C, Bai, J, Yao, Z. A novel model-assisted de-multi-agent reinforcement learning for joint optimization of hybrid beamforming in massive MIMO mm-Wave systems. IEEE Trans Veh Technol 2023;72:14743–55.10.1109/TVT.2023.3280910Search in Google Scholar
15. Liang, K, Zheng, G, Li, Z, Wong, KK, Chae, CB. A data and model-driven deep learning approach to robust downlink beamforming optimization. IEEE J Sel Area Commun 2024;42:3278–92. https://doi.org/10.1109/jsac.2024.3431583.Search in Google Scholar
16. Jiang, L, Wang, X, Yang, A, Wang, X, Jin, X, Wang, W, et al.. An efficient multi-agent optimization approach for coordinated massive MIMO beamforming. In: 2023 IEEE International Conference on Communications (ICC). IEEE, Rome, Italy; 2023:5632–8 pp.10.1109/ICC45041.2023.10279724Search in Google Scholar
17. Sadhwani, S, Mathur, A, Muthalagu, R, Pawar, PM. 5G-SIID: an intelligent hybrid DDoS intrusion detector for 5G IoT networks. International Journal of Machine Learning and Cybernetics 2024:1–21. https://doi.org/10.1007/s13042-024-02332-y.Search in Google Scholar
18. Ghubaish, A, Yang, Z, Jain, R.: a hybrid deep reinforcement learning intrusion detection system for enhancing the security of medical applications in 5G networks. In: 2024 International Conference on Smart Applications, Communications and Networking (Smart Nets). IEEE, Harrisonburg, VA, USA; 2024:1–6 pp.10.1109/SmartNets61466.2024.10577692Search in Google Scholar
19. Moubayed, A. Comparing boosting-based and GAN-based models for intrusion detection in 5G networks. In: 2024 International Symposium on Networks, Computers and Communications (ISNCC). IEEE, Washington, DC, USA; 2024:1–6 pp.10.1109/ISNCC62547.2024.10759066Search in Google Scholar
20. Kouchaki, M, Zhang, M, Abdalla, AS, Lan, G, Brinton, CG, Marojevic, V. Enhanced real-time threat detection in 5G networks: a self-attention RNN autoencoder approach for spectral intrusion analysis. In: 2024 22nd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt). IEEE, Seoul, Republic of Korea; 2024:249–56 pp.Search in Google Scholar
21. Moustafa, N, Slay, J. UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: 2015 Military Communications and Information Systems Conference (MilCIS). IEEE, Canberra, ACT, Australia; 2015:1–6 pp.10.1109/MilCIS.2015.7348942Search in Google Scholar
22. Bengio, Y, Louradour, J, Collobert, R, Weston, J. Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09). ACM, Montreal, Quebec, Canada; 2009:41–8 pp.10.1145/1553374.1553380Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
