Enhancing channel estimation accuracy in polar-coded MIMO–OFDM systems via CNN with 5G channel models

Abstract

In this paper, a novel channel estimation technique for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO–OFDM) systems in fifth generation (5G) networks is proposed, which leverages the power of convolutional neural networks (CNNs) along with the application of polar coding. By employing polar encoding at the transmitter and polar decoding at the receiver, the proposed system enhances error correction performance, reliability, and data transmission rate in 5G networks. A novel optimized CNN-based channel estimation technique, named CNN-CENet, has been integrated into the polar-coded MIMO–OFDM receiver. This integration aims to address the interference and noise challenges in 5G systems. The proposed channel estimation method utilizes multiple layers of CNN to accurately characterize the properties of the real channel by incorporating least squares (LS) estimations. Hence, the proposed CNN-CENet provides an accurate estimation of the channel coefficients, enabling efficient signal detection at the receiver. The MATLAB simulation has been conducted using deep learning and 5G toolboxes to obtain results for various channel parameters. These results are then compared with the LS and minimum mean square error (MMSE) methods for performance evaluation. The proposed model surpasses the performance of the LS and MMSE methods, achieving a significant 95.6% reduction in mean square error (MSE) compared to LS and a substantial 59.7% reduction compared to MMSE. Additionally, it delivers notable bit error rate (BER) reductions of 59.8% and 53.2% for LS and MMSE, respectively, in low mobility scenarios, and 57.4% and 48.5% reductions in high mobility scenarios. This improvement leads to enhanced reliability and overall system efficiency.