Abstract
Accurate wireless channel estimation is essential for optimizing communication systems, particularly in 5G and future wireless networks. This study explores a deep learning-based approach to estimate the received power in a wireless channel, using distance, fading effects, and noise characteristics as input features. The deep neural network is designed with multiple hidden layers, incorporating batch normalization, dropout regularization, and L2 weight decay to enhance generalization and stability. The model is trained on synthetically generated channel data, simulating path loss, Rayleigh fading, and additive noise to represent realistic propagation conditions. The proposed deep learning model is trained using Mean Squared Error (MSE) loss and optimized with the Adam optimizer, along with a learning rate scheduler to improve convergence. Evaluation shows that the model achieves a low Mean Absolute Error (MAE), indicating strong predictive accuracy. The simulated and predicted power curves demonstrate minimal deviation, confirming the model's capability to generalize well across different channel conditions. Results suggest that this deep learning-based channel estimation approach effectively captures complex propagation characteristics, making it suitable for real-time applications in wireless communication systems. The model can aid in beamforming, resource allocation, and interference management, contributing to enhanced network efficiency.
References
- Ye, H., Li, G. Y., &Juang, B.-H. (2018). Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communications Letters, 7(1), 114-117.
- Samuel, N., Diskin, T., & Wiesel, A. (2019). Learning to detect. IEEE Transactions on Signal Processing, 67(10), 2554-2564.
- He, H., Wen, C.-K., Jin, S., & Li, G. Y. (2018). Deep learning-based channel estimation for beamspace mmWave massive MIMO systems. IEEE Wireless Communications Letters, 7(5), 852-855.
- Gao, Xinyu, Linglong Dai, Ying Sun, Shuangfeng Han, and I. Chih-Lin. "Machine learning inspired energy-efficient hybrid precoding for mmWave massive MIMO systems." In 2017 IEEE International Conference on Communications (ICC), pp. 1-6. IEEE, 2017.
- Wen, C.-K., Shih, W.-T., & Jin, S. (2018). Deep learning for massive MIMO CSI feedback. IEEE Wireless Communications Letters, 7(5), 748-751.
- Jiang, Rongkun, Xuetian Wang, Shan Cao, Jiafei Zhao, and Xiaoran Li. "Deep neural networks for channel estimation in underwater acoustic OFDM systems." IEEE access 7 (2019): 23579-23594.
- Huang, H., Song, Y., Yang, J., Huang, G., &Gui, G. (2018). Deep learning for super- resolution channel estimation and DOA estimation based massive MIMO system. IEEE Transactions on Vehicular Technology, 67(9), 8549-8560.
- Zhong, Shida, Haogang Feng, Peichang Zhang, Jiajun Xu, Huancong Luo, Jihong Zhang, Tao Yuan, and Lei Huang. "Deep learning based antenna selection for MIMO SDR system." Sensors 20, no. 23 (2020): 6987.
- Chen, M., Zhao, N., &Alouini, M.-S. (2019). Artificial neural networks-based machine learning for wireless networks: A tutorial. IEEE Communications Surveys & Tutorials, 21(4), 3039-3071.
- Dong, P., Wang, H., Gao, J., Chen, J., & Wang, J. (2019). Deep CNN-based channel estimation for mmWave massive MIMO systems. IEEE Journal of Selected Topics in Signal Processing, 13(5), 989-1000.
- Gao, Shen, Peihao Dong, Zhiwen Pan, and Geoffrey Ye Li. "Deep learning based channel estimation for massive MIMO with mixed-resolution ADCs." IEEE Communications Letters 23, no. 11 (2019): 1989-1993.
- Wang, T., Wen, C.-K., Jin, S., & Li, G. Y. (2019). Deep learning-based CSI feedback approach for time-varying massive MIMO channels. IEEE Wireless Communications Letters, 8(2), 416-419.
- Guo, Jiajia, Xi Yang, Chao-Kai Wen, Shi Jin, and Geoffrey Ye Li. "DL-based CSI feedback and cooperative recovery in massive MIMO." arXiv preprint arXiv:2003.03303 (2020).
- https://www.kaggle.com/datasets/programmer3/5g6g-multipath-fading-equalization-dataset