Full Cascaded Channel Estimation for RIS-Aided Cognitive Radio Systems by Deep Neural Networks

In reconfigurable intelligent surfaces (RIS)-aided cognitive radio (CR) systems, the estimation of high-dimensional channel state information (CSI) with the interferences for all the cascaded channels between the RIS and any pair of the transceivers is challenging. To solve this problem, we propose a three-stage scheme of the full cascaded channel estimation based on the deep neural network (DNN). At the beginning, the protocol of the two-step pilot transmissions is designed for generating the labeled channel dataset in data preparation stage. Specifically, we propose dual-output parameter estimation (DOPE) architecture to establish and train the DNN model for full cascaded channel estimation simultaneously with a low pilot overhead in model construction and training stage. Notably, our proposed DNNbased DOPE architecture can accomplish the estimation of both the near-field and far-field cascaded channels in the RIS-aided CR system. Besides, the protocol of only one pilot transmission is introduced for online channel estimation in the model deployment stage. The simulation results show that our proposed scheme outperforms the compared benchmark estimation algorithms at the aspects of both the normalized mean square error (NMSE) performance and the cost of the pilot overhead.