Tupakula Sunayana, Dr.S. Swarnalatha

DOI: https://doi.org/10.5281/zenodo.23672137

5G Wireless Communication Based on Reinforcement Learning Essay 5G wireless communication technologies are predicted to be able to maintain dependable communication while providing the highest possible data rates and minimum delays over time-varying channels. The paper explores the feasibility of employing adaptive modulation as a Markov decision process. The paper trains a Deep Q Network (DQN) controller to make decisions on the most appropriate modulation, out of QPSK, 16-QAM, and 64-QAM options, based on the estimated Signal-to-Noise Ratio (SNR). The communication system has a 20 MHz bandwidth, subject to Rayleigh fading and additive white Gaussian noise. The transmitter modulates binary information data with selected encoding methods. The receiver demodulates and decodes the input data. The BER, latency, throughput, and spectral efficiency are evaluated for the feedback process to the DQN agent. The reward function in the paper’s experiments prioritizes lower BER, lower latency, and higher throughput for the selected action.The results provided by the authors demonstrate that the BER for all three modulation schemes decreases with increasing SNR as expected. The results also confirm that higher-order modulations have higher latency than lower-order ones on average. Most importantly, the experiments have shown that the DQN agent learned to switch between different modulations depending on the conditions and follow the optimal policy of switching from QPSK to 16-QAM and eventually to 64-QAM with rising SNR. The study therefore proves the feasibility of adopting a learning-based approach to modulation control and serves as a valuable basis for future research into the 5G physical layer.

5G wireless communication, reinforcement learning, Deep Q-Network, adaptive modulation, QPSK, 16-QAM, 64-QAM, SNR, BER, Rayleigh fading, AWGN, latency, spectral efficiency.

This paper presents the adaptive modulation framework for 5G-oriented communication based on the DQN RL method. The environment uses the packet BER as the main performance metric under Rayleigh fading and AWGN conditions. The link occupies a 20 MHz spectrum, and the receiver uses the measured BER to estimate the SNR and update the DQN policy. The given setup allows analyzing the reliability-delay trade-off and the decision-making process behind it. The experimental results provided with the project report illustrate the basic principles of the DQN-based adaptive modulation. Figure 4 shows that the BER follows the theoretical predictions for the three modulations but has lower values at most SNR due to the dynamic policy. Figure 5 highlights the reliability-delay trade-off and the corresponding changes in the packet BER and latency. Finally, Figure 7 presents the main finding from the analysis, where the DQN policy follows the three modulations depending on the SNR. In the submitted illustration, the switch from QPSK to 16-QAM occurs near 6 dB, and the transition from 16-QAM to 64-QAM occurs near 16-17 dB. Therefore, the proposed framework provides a baseline for intelligent adaptation in wireless communication. It demonstrates the principles of real-time decision-making and the reliability-delay trade-off while also suggesting the limitations of the current approach.

[1] F. Geiser, D. Wessel, M. Hummert, A. Weber, D. Wübben, and A. Dekorsy, “DRLLA: Deep Reinforcement Learning for Link Adaptation,” Telecom, vol. 3, no. 4, pp. 692-705, 2022.
[2] A. Parsa, N. Moghim, and P. Salavati, “Joint Power Allocation and MCS Selection for Energy-Efficient Link Adaptation: A Deep Reinforcement Learning Approach,” Computer Networks, vol. 218, Art. no. 109386, 2022.
[3] A.-H. Lee, H. Bae, Y.-K. Kim, and C.-K. Kim, “Deep Reinforcement Learning Based MCS Decision Model,” Journal of KIISE, vol. 49, no. 8, pp. 663-668, 2022.
[4] X. Ye, Y. Yu, and L. Fu, “Deep Reinforcement Learning Based Link Adaptation Technique for LTE/NR Systems,” IEEE Transactions on Vehicular Technology, vol. 72, no. 6, pp. 7364-7378, 2023.
[5] X. Cui, Z. Zhang, J. Li, B. Jiang, S. Li, and J. Liu, “Reinforcement Learning-Based Adaptive Modulation Scheme Over Underwater Acoustic OFDM Communication Channels,” Physical Communication, vol. 61, Art. no. 102207, 2023.
[6] A. Parsa, N. Moghim, and S. Shetty, “QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach,” IEEE Open Journal of the Communications Society, vol. 6, pp. 6368-6382, 2025.
[7] B. B. Cebecioglu et al., “Deep Reinforcement Learning Based MCS Selection in Open RAN for Vehicular Communications,” in Proc. IEEE PIMRC, 2025.
[8] G. Liang, J. Hu, Y. Zhao, and K. Yang, “Intelligent Link Adaptation for Integrated Data and Energy Transfer: An Enhanced DRL Approach for Long-Term Constraints,” IEEE Transactions on Communications, vol. 72, no. 11, pp. 6956-6972, 2024.
[9] V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529-533, 2015.
[10] M. Shafi et al., “5G: A Tutorial Overview of Standards, Trials, Challenges, Deployment, and Practice,” IEEE Journal on Selected Areas in Communications, vol. 35, no. 6, pp. 1201-1221, 2017.
[11] M. Agiwal, A. Roy, and N. Saxena, “Next Generation 5G Wireless Networks: A Comprehensive Survey,” IEEE Communications Surveys & Tutorials, vol. 18, no. 3, pp. 1617-1655, 2016.
[12] N. C. Luong et al., “Applications of Deep Reinforcement Learning in Communications and Networking: A Survey,” IEEE Communications Surveys & Tutorials, vol. 21, no. 4, pp. 3133-3174, 2019.

Tupakula Sunayana, Dr.S. Swarnalatha (2026). REINFORCEMENT LEARNING-BASED 5G NETWORK OPTIMIZATION USING BER SIMULATION. International Journal of Engineering and Techniques, 12(5), 373–382. ISSN: 2395-1303. DOI: https://doi.org/10.5281/zenodo.23672137