Channel estimation is of great importance in realizing practical intelligent reflecting surface-assisted multi-user communication (IRS-MC) systems. However, different from traditional communication systems, an IRS-MC system generally involves a cascaded channel with a sophisticated statistical distribution, which hinders the implementations of the Bayesian estimators. To further improve the channel estimation performance, in this paper, we model the channel estimation as a denoising problem and adopt a data-driven approach to realize the channel estimation. Specifically, we propose a convolutional neural network (CNN)-based deep residual network (CDRN) to implicitly learn the residual noise for recovering the channel coefficients from the noisy pilot-based observations. In the proposed CDRN, a CNN denoising block equipped with an element-wise subtraction structure is designed to exploit both the spatial features of the noisy channel matrices and the additive nature of the noise simultaneously, which further improves the estimation accuracy. Simulation results demonstrate that the proposed method can almost achieve the same estimation accuracy as that of the optimal minimum mean square error (MMSE) estimator requiring the knowledge of the channel distribution.
翻译:然而,与传统的通信系统不同,IRS-MC系统通常涉及一个具有复杂统计分布的级联渠道,这妨碍了Bayesian估计仪的实施。为了进一步改进频道估计性能,我们在本文件中将频道估计作为解译问题进行模拟,并采取数据驱动方法实现频道估计。具体地说,我们提议建立一个基于动态神经网络(CNN)的深层残余网络(CDRN),以隐含地了解从噪音试点观测中恢复频道系数的残余噪音。在拟议的CDRN中,一个配有元素性减色结构的CNN脱色区块,旨在同时利用噪音频道矩阵的空间特征和噪音的添加性,从而进一步提高估计准确性。模拟结果表明,拟议的方法几乎可以达到与最优最低平均平方差(MMSE)估计性,需要了解频道分布的知识。