ICINet: ICI-Aware Neural Network Based Channel Estimation for Rapidly Time-Varying OFDM Systems

A novel intercarrier interference (ICI)-aware orthogonal frequency division multiplexing (OFDM) channel estimation network ICINet is presented for rapidly time-varying channels. consists of two components: a preprocessing deep neural subnetwork (PreDNN) and cascaded residual learning-based (CasResNet). By fully taking into account the impact ICI, proposed PreDNN first refines initial estimates in subcarrier-wise fashion. In addition, CasResNet designed to further enhance accuracy. The compatible with any pilot patterns robust against mismatched system configurations. Simulation results verify superiority over existing networks terms better performance much less complexity.