Optimized CNN-based channel estimation for zero-padded uplink OFDMA in 5G new radio over fast-fading channels

This paper addresses a pilot-assisted channel estimation applicable to the uplink orthogonal frequency-division multiple-access with zero-padding in a 5G new radio. The adjacent uplink subchannels in the frequency domain are allocated separately for each user, and each subchannel assigns the pilot signal independently. This paper proposes a convolutional neural network-based channel estimation, including one-dimensional and two-dimensional architectures, designed to optimize the handling of rapid fading channel variations encountered in high-mobility scenarios. The estimation process leverages the subchannels of each user to enhance accuracy. Simulation results demonstrate the effectiveness of the proposed method in offering a better bit-error rate and a higher transmission data rate than the conventional channel estimation methods under challenging conditions. Finally, this paper discusses the considerable computational complexity of aspects of the lightweight two convolutional neural network architectures.