Machine Learning Based Optimization Techniques for 5G Networks

5G networks promise faster speeds, lower latency, and improved reliability, but achieving these benefits requires overcoming complex challenges related to resource allocation, latency reduction, and network stability. Traditional methods often fall short in adapting to the dynamic and diverse demands of modern wireless communication. This paper presents machine learning-based frameworks designed to enhance 5G network performance by enabling smarter, data-driven optimization. By leveraging real-time data, these frameworks improve traffic prediction, resource management, and fault detection, allowing the network to adapt more efficiently to changing conditions. Simulation results (10 runs on 3GPP-aligned data) demonstrate 22% throughput gain and 60% latency MSE reduction versus Proportional Fair (PF) and Round Robin (RR) baselines, confirming practical ML value for 5G deployments. These findings highlight the strong potential of integrating machine learning into 5G networks to create more responsive and efficient systems. Ultimately, this work offers practical and scalable solutions that contribute to advancing next-generation wireless communication and enhancing user experience.

5G networks, lower latency, optimization Techniques

1. A. Gupta and R. K. Jha, “A Survey of 5G Network: Architecture and Emerging Technologies,” IEEE Access, vol. 3, pp. 1206–1232, 2015. [Google Scholar] [Crossref]

2. K. S. Munasinghe and A. Jamalipour, “Traffic Aware Resource Allocation for 5G Heterogeneous Networks,” IEEE Transactions on Vehicular Technology, vol. 66, no. 10, pp. 9259–9273, 2017. [Google Scholar] [Crossref]

3. M. Elsayed and M. Erol-Kantarci, “AI-Enabled Future Wireless Networks: Challenges, Opportunities, and Open Issues,” IEEE Vehicular Technology Magazine, vol. 14, no. 3, pp. 70–77, 2019. [Google Scholar] [Crossref]

4. F. Tang, B. Mao, and Z. M. Fadlullah, “On the Deep Learning for 5G Traffic Forecasting,” IEEE Network, vol. 32, no. 6, pp. 93–99, 2018. [Google Scholar] [Crossref]

5. ITU-T Recommendation Y.3172, “Architectural Framework for Machine Learning in Future Networks Including IMT-2020,” 2019. [Google Scholar] [Crossref]

6. F. B. Mismar and B. L. Evans, “Deep Reinforcement Learning for 5G Networks: Joint Beamforming, Power Control, and Interference Coordination,” IEEE Transactions on Communications, vol. 68, no. 2, pp. 1150–1162, 2020. [Google Scholar] [Crossref]

7. H. Zhang, N. Liu, X. Chu, K. Long, A. Aghvami, and V. C. M. Leung, “Network Slicing Based 5G and Future Mobile Networks: Mobility, Resource Management, and Challenges,” IEEE Communications Magazine, vol. 55, no. 8, pp. 138–145, 2017. [Google Scholar] [Crossref]

8. X. Chen, Z. Zhao, and H. Zhang, “Reinforcement Learning for Wireless Networks: Techniques, Applications, and Open Issues,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 1572–1607, 2020. [Google Scholar] [Crossref]

9. Z. Gao, “5G Traffic Prediction Based on Deep Learning,” Computational Intelligence and Neuroscience, vol. 2022, 2022. [Google Scholar] [Crossref]

10. P. Rebari and B. Killi, “Deep Learning Based Traffic Prediction for Resource Allocation in Multi-Tenant Virtualized 5G Networks,” in Proc. IEEE TENCON, 2023. [Google Scholar] [Crossref]

11. M. Peng, Y. Sun, X. Li, Z. Mao, and C. Wang, “Self-Configuration and Self-Optimization in LTEAdvanced Heterogeneous Networks,” IEEE Communications Magazine, vol. 51, no. 5, pp. 36–45, 2013. [Google Scholar] [Crossref]

12. H. Zhang, J. Wang, and X. Zhang, “AI-Driven Network Management for 5G and Beyond,” IEEE Wireless Communications, vol. 28, no. 2, pp. 14–21, 2021. [Google Scholar] [Crossref]

13. A. (Author(s)), “A ML-Based Resource Allocation Scheme for Energy Optimization in 5G NR,” Sensors, vol. 25, no. 16, Article 4978, 2025. [Google Scholar] [Crossref]

14. S. Zafar, J. White, P. Legg, “Federated Learning with Adversarial Optimisation for Secure and Efficient 5G Edge Computing Networks,” Big Data and Cognitive Computing, vol. 9, no. 9, Article 238, Sep. 2025. [Google Scholar] [Crossref]

15. M. Rahmati, “Energy-aware Federated Learning for Secure Edge Computing in 5G-enabled IoT Networks,” Journal of Electrical Systems and Information Technology, vol. 12, Article 13, 2025. [Google Scholar] [Crossref]

16. A. Kaur, H. Sadawarti, “Dynamic Resource Allocation Using a DRL Method in 5G Network,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 5s, pp. 501-509, 2023. [Google Scholar] [Crossref]

17. V. Shilpa, R. Ranjan, “Comparative Analysis of RL-Based Resource Allocation Methods for Optimization in 5G mmWave Network,” in IC4S 2024, Springer, 2025. [Google Scholar] [Crossref]

18. A. S. M. Mohammed, A. I. A. Taman, A. M. Hassan, et al., “Deep Learning Channel Estimation for OFDM 5G Systems with Different Channel Models,” Wireless Personal Communications, vol. 128, pp. 2891-2912, 2023. [Google Scholar] [Crossref]

19. Z. Yu, F. Gu, H. Liu, Y. Lai, “5G Multi-Slices Bi-Level Resource Allocation by Reinforcement Learning,” Mathematics, vol. 11, no. 3, Article 760, 2023. [Google Scholar] [Crossref]

20. F. O. Catak, U. Cali, M. Kuzlu, S. Sarp, “Uncertainty Aware Deep Learning Model for Secure and Trustworthy Channel Estimation in 5G Networks,” arXiv:2305.02741, 2023. [Google Scholar] [Crossref]

21. 3GPP TR 37.814 V14.1.0, “User Equipment (UE) radio transmission and reception; Requirements,” 2017. [Google Scholar] [Crossref]

22. Maheshwari, Mukesh Kumar, Raschella, Alessandro, Mackay, Michael, Eiza, Max Hashem, Wetherall, Jon and Laing, Jen “5G High Density Demand (HDD) Dataset in Liverpool City Region,” UK (Supplement), Nature Scientific Data, 2025. [Google Scholar] [Crossref]

23. F. B. Mismar et al., “Deep Reinforcement Learning for 5G Networks: Joint Beamforming, Power Control,” IEEE Trans. Commun., 2020. [Google Scholar] [Crossref]

24. 3GPP TS 38.214 V17.0.0, “NR; Physical layer procedures for data,” 2022. [Google Scholar] [Crossref]

• A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya
• AI-Powered Facial Recognition Attendance System Using Deep Learning and Computer Vision
• A Comprehensive Review on Brain Tumour Segmentation Using Deep Learning Approach
• A Scalable Retrieval-Augmented Generation Pipeline for Domain-Specific Knowledge Applications
• Predictive Maintenance in Semiconductor Manufacturing Using Machine Learning on Imbalanced Dataset