Neural network channel estimator for time‐variant frequency‐selective fading channels

The next generations of wireless communications systems are pushing the limits of the channel estimation methods utilized in the orthogonal frequency division multiplexing receptors. This letter proposes a novel channel estimation method using a densely connected neural network considering the time‐variant frequency‐selective fading channel model. A fully connected deep neural network for the AWGN channel case is also proposed. The comparative complexity of the estimation for different channel models is also discussed. The simulation results demonstrate that the densely connected neural network method surpasses the minimum mean‐square error method performance for a signal‐to‐noise ratio ranging from 0 to 25 dB in the frequency‐selective channel. This letter proposes a novel channel estimation method using a densely connected neural network considering the time‐variant frequency‐selective fading channel model. A fully connected deep neural network for the AWGN channel case is also proposed. The comparative complexity of the estimation for different channel models is also discussed.