Channel Estimation Capacity Enhancement for Multigroup Multicasting Multimedia Networks With DnCNN

Abstract

In Time Domain Duplex (TDD) massive MIMO systems, multi-group multi-casting becomes a promising technology since it supports services of mass content distribution. Based on the nature of transmitting common message to groups of users simultaneously, there exists a rich literature discussing the resource allocation under various constraints. However, the practical acquisition of CSI has not been fully explored when the number of multi-groups is large and the band is narrow. The insufficient sounding reference signal resources lead to the limited Channel Estimation Capacity (CEC). Under this case, even with Multi-User (MU) channel estimation techniques, some users still cannot be estimated in-timely, which introduces degradation. Aiming at this problem, in this paper we provide a preliminary exploration on CEC enhancement. Based on Denoising Convolutional Neuron Network (DnCNN), which is recently proposed and has succeeded in image denoising, we propose MU-DnCNN Channel Estimation (M-DnCNN CE). M-DnCNN CE includes three parts. First, we modify the utilization of SRS sequences. Then we establish the feature maps and propose M-DnCNN to denoise the signals. Finally, a matched channel restoration method is provided. The practical 3-D MIMO channel model is utilized to evaluate the performance. Compared with DFT-based and conjugated separation methods, results show that the performance of M-DnCNN CE is robust and superior, and the CEC is remarkably improved on the premise of satisfying latency constraint.

Keywords

• Multi-user channel estimation
• multi-group multi-casting
• DnCNN
• 3-D MIMO
• mobile intelligence