Learning-Based Channel Estimation and Phase Noise Compensation in Doubly-Selective Channels

In this letter, we propose a learning based channel estimation scheme for orthogonal frequency division multiplexing (OFDM) systems in the presence of phase noise doubly-selective fading channels. Two-dimensional (2D) convolutional neural networks (CNNs) are employed effective training and tracking variation both as well time domain. The proposed network learns estimates coefficients entire time-frequency (TF) grid on pilots sparsely populated TF grid. order to make robust (PN) impairment, novel where data is rotated by random phases before being fed employed. Further, using estimated coefficients, simple PN compensation devised. Numerical results demonstrate that achieve OFDM performance noise.