Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces

Integrating large intelligent reflecting surfaces (IRS) into millimeter-wave (mmWave) massive multi-input-multi-ouput (MIMO) has been a promising approach for improved coverage and throughput. Most existing work assumes the ideal channel estimation, which can be challenging due to the high-dimensional cascaded MIMO channels and passive reflecting elements. Therefore, this paper proposes a deep denoising neural network assisted compressive channel estimation for mmWave IRS systems to reduce the training overhead. Specifically, we first introduce a hybrid passive/active IRS architecture, where very few receive chains are employed to estimate the uplink user-to-IRS channels. At the channel training stage, only a small proportion of elements will be successively activated to sound the partial channels. Moreover, the complete channel matrix can be reconstructed from the limited measurements based on compressive sensing, whereby the common sparsity of angular domain mmWave MIMO channels among different subcarriers is leveraged for improved accuracy. Besides, a complex-valued denoising convolution neural network (CV-DnCNN) is further proposed for enhanced performance. Simulation results demonstrate the superiority of the proposed solution over state-of-the-art solutions.

I. Introduction

Millimeter-Wave (mmWave) massive multiple-input multiple-output (MIMO) system with intelligent reflecting surfaces (IRS) is envisioned to be a promising technology for future beyond 5 G/6 G wireless communication networks to substantially improve the link quality and reduce the blockage probability [1], [2]. IRS is a kind of near-passive array whose elements are able to attach independently controllable phase shifts to the incident electromagnetic waves [3]. With very few radio frequency (RF) chains connected and massive near-passive elements, adopting IRS would be an energy-saving and low-cost solution. Leveraging the controllable reflection property of large IRS with passive elements, the mmWave massive MIMO base stations (BS) can serve the user equipments (UEs) whose direct links from the BS are completely blocked by obstacles, so that the effective coverage of mmWave cellular networks can be enhanced by some sophisticated beamforming techniques [1], [2], [4].