Inspired by the remarkable learning and prediction performance of deep neural networks (DNNs), we apply one special type of DNN framework, known as model-driven deep unfolding neural network, to reconfigurable intelligent surface (RIS)-aided millimeter wave (mmWave) single-input multiple-output (SIMO) systems. We focus on uplink cascaded channel estimation, where known and fixed base station combining and RIS phase control matrices are considered for collecting observations. To boost the estimation performance and reduce the training overhead, the inherent channel sparsity of mmWave channels is leveraged in the deep unfolding method. It is verified that the proposed deep unfolding network architecture can outperform the least squares (LS) method with a relatively smaller training overhead and online computational complexity.
翻译:在深神经网络的杰出学习和预测表现的启发下,我们采用了一种特殊类型的DNN框架,称为模型驱动的深潜神经网络,用于重新配置智能表面(RIS)辅助的单输入量多输出量(MSIMO)系统。我们侧重于上链式频道估算,即考虑将已知和固定的连接和RIS阶段控制矩阵基站用于收集观测。为了提高估计性能并减少培训间接费用,在深演方法中利用了毫米瓦夫频道的内在广度。可以证实,拟议的深演网络结构可以比最小方(LS)方法更小的间接培训和在线计算复杂性。