Deep Learning-Based Adaptive Modulation Scheme for Enhancing Data Throughput in Fading Wireless Channels
DOI:
https://doi.org/10.31838/NJAP/07.02.29Keywords:
Adaptive Modulation, Deep Learning, Fading Channels, Spectral Efficiency, Recurrent Neural Networks, Wireless CommunicationAbstract
Dynamic channel impairments of systems with wireless communication systems working under faulty channel conditions can cause a considerable deterioration of throughput and signal quality. The adapted modulation approach in the system stemmed from the fact that the traditional adaptive modulation approaches are somewhat limited; although their use has been very common either due to static evaluation metrics based on SNR thresholds or lack of responsiveness to real-time channel conditions in practical applications. Here the proposed Deep Learning-Based Adaptive Modulation Scheme (DL-AMS) utilizes Long Short-Term Memory (LSTM) networks to dynamically choose the modulation orders in real-time according to the Channel State Information (CSI). The developed framework is verified and evaluated by MATLAB-based simulations (Rayleigh and Rician fading models) with improved up to 38 percent throughput performance and up to 25 percent lower bit error rate (BER) than the conventional SNR-threshold-based schemes. Moreover, besides the baseband flexibility DL-AMS can be easily combined with propagation-sensitive RF systems such as beamforming arrays and reconfigurable antennas in order to implement spatially selective modulation control. The approach offers a dexterous, smart solution to the quest of next-generation wireless networking (5G, vehicular networks, and cognitive radio systems)
References
1. Giji Kiruba, D., Benita, J., & Rajesh, D. (2023). A proficient obtrusion recognition clustered mechanism for malicious sensor nodes in a mobile wireless sensor network. Indian Journal of Information Sources and Services, 13(2), 53–63. https://doi.org/10.51983/ijiss-2023.13.2.3793
2. Alouini, M. S., & Goldsmith, A. J. (2000). Adaptive modulation over Nakagami fading channels. Wireless Personal Communications, 13(1–2), 119–143.
3. Tandon, B., & Thakur, M. (2025). An overview of adaptive signal processing methods for 6G wireless communication networks. International Academic Journal of Science and Engineering, 12(1), 12–15. https://doi.org/10.71086/IAJSE/V12I1/IAJSE1203
4. Chen, J. & Lin, S. LSTM-aided CSI prediction for adaptive modulation in OFDM Systems. IEEE Access, 9(8876488774), 2021.
5. Ibrahim, M. S., & Shanmugaraja, P. (2023). Mobility based routing protocol performance oriented comparative analysis in the ADHOC networks FANET, MANET and VANET using OPNET modeler for FTP and web applications. International Academic Journal of Innovative Research, 10(1), 14–24. https://doi.org/10.9756/IAJIR/V10I1/IAJIR1003
6. Iserte, A. P., Pérez-Neira, A. I., & Hernández, M. A. L. (2002, May). Joint beamforming strategies in OFDM MIMO systems. In 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing (Vol. 3, pp. III 2845). IEEE.
7. Wang, Z, & Giannakis, G. B. (May 2000). Wireless multicarrier communications. IEEE Signal Processing Magazine, 17(3), 29–48,.
8. Van, C., Trinh, M. H., & Shimada, T. (2023). Next generation semiconductor-based fundamental computation module implementation. Journal of VLSI Circuits and Systems, 5(2), 50–55. https://doi.org/10.31838/jvcs/05.02.08
9. Patel, A., & Natarajan, K. (2020). Reconfigurable antenna design for adaptive modulation in low-power IoT Devices. IEEE Access, 8, 19874–19883.
10. Tamm, J. A., Laanemets, E. K., & Siim, A. P. (2025). Fault detection and correction for advancing reliability in reconfigurable hardware for critical applications. SCCTS Transactions on Reconfigurable Computing, 2(3), 27–36. https://doi.org/10.31838/RCC/02.03.04
11. Ali, W., Ashour, H., & Murshid, N. (2025). Photonic integrated circuits: Key concepts and applications. Progress in Electronics and Communication Engineering, 2(2), 1–9. https://doi.org/10.31838/PECE/02.02.01
12. Mohammed, S. S., & Chockalingam, A. (Jun. 2013). A unified view of MIMO precoding and beamforming. EEE Communications Magazine, vol. 51, no. 6, pp. 128–137.
13. Sun, Y. et al. (Oct. 2019). Deep learning for physical layer: Opportunities and challenges. IEEE Wireless Communications, 26(5), 94–101.
14. Kim, B. et al. (Jan. 2020). Convolutional neural networks for modulation classification. IEEE Transactions on Communications, 68(1), 17–25.
15. Gupta, A. K., & Sharma, S. (2020).Deep neural network modulation prediction in LTE systems. Springer Telecommunication Systems, 75, 1–13.
16. O’Shea, T., & Hoydis, J. (Dec. 2017). An introduction to deep learning for the physical layer. IEEE Transactions on Cognitive Communications and Networking, 3(4), 563–575.
17. Singh, J. S. P. (2022). APC: Adaptive power control technique for multi-radio multi-channel cognitive radio networks. Wireless Personal Communications, 122(4), 3603-3632.
18. Mehmood, R. et al. (Mar. 2020). Smart modulation techniques for IoT. IEEE Internet of Things Journal, 7(3), 1849–1863,.
19. James, A., Elizabeth, C., Henry, W., & Rose, I. (2025). Energy-efficient communication protocols for long-range IoT sensor networks. Journal of Wireless Sensor Networks and Internet of Things, 2(1), 62–68.
20. Aravindh, G., & Sridhar, K. P. (2024). Resilient and adaptive secure routing protocol for wireless sensor networks using a grey wolf optimizer and lightning search algorithm. Journal of Internet Services and Information Security, 14(4), 331–346. https://doi.org/10.58346/JISIS.2024.I4.020
21. Uvarajan, K. P. (2024). Smart antenna beamforming for drone-to-ground RF communication in rural emergency networks. National Journal of RF Circuits and Wireless Systems, 1(2), 37–46.
22. Alkasassbeh, J. S., Al-Taweel, F. M., Alawneh, T. A., Al-Qaisi, A., Makableh, Y. F., & El-Mezieni, T. (2024). Advancements in wireless communication technology: A comprehensive analysis of 4G to 7G systems. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 15(3), 73–91. https://doi.org/10.58346/JOWUA.2024.I3.006
23. Nayak, A., & Rahman, F. (2024). A deep learning-based intelligent automatic detection and classification of fish species in marine environment. Natural and Engineering Sciences, 9(3), 144–153. https://doi.org/10.28978/nesciences.160662
24. Dorner, S. et al. (Feb. 2018). Deep learning based communication over the air. IEEE Journal of Selected Topics in Signal Processing, 12(1), 132–143.
