A large-scale multi-antenna channel estimation method based on deep convolutional neural network

Abstract

A large-scale multi-antenna channel estimation method based on a deep convolutional neural network belongs to the field of wireless communication technology. The transmitting antenna sends OFDM data blocks to the receiving antenna, and after the wireless multipath channel propagates, the corresponding normalized pilot signal is received, and a large-scale multi-antenna channel estimation model is stacked by rows; a deep convolutional neural network is constructed and weighted After training, estimate the stacked channel impulse response to obtain the estimated stacked channel impulse response; select the subchannel vector corresponding to the transmitting antenna in the estimated stacking channel impulse response to form an estimated sparse support set; optimize the estimation corresponding to each transmitting antenna The sparse support set is obtained to obtain the joint estimation sparse support set, and further obtain the refined channel estimation of large-scale multi-antenna. In the case of high noise intensity, the large-scale multi-antenna channel can be accurately estimated, the estimation accuracy of the large-scale multi-antenna channel can be effectively improved, and the channel estimation delay can be effectively reduced.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a large-scale multi-antenna channel estimation method based on a deep convolutional neural network. Background technique [0002] Since it can significantly improve the data transmission rate and spectral efficiency, massive multi-antenna technology has been widely used in 5G communication systems. However, with the increasing number of antennas, the difficulty of large-scale multi-antenna channel estimation is also increasing. At the same time, in low-latency communication scenarios, the complex time-varying characteristics of the channel are not conducive to real-time channel estimation using traditional complex methods or iterative channel estimation algorithms. Therefore, it is necessary to design a method that can accurately estimate large-scale multi-antenna channels with low estimation delay to meet the growing communication needs in the future....

AI Technical Summary

Problems solved by technology

The existing channel estimation method based on compressed sensing utilizes the sparse characteristics of the wireless channel, and uses compressed sensing to restore the channel, which can reduce the overhead of the required training sequence and improve the estimation accuracy to a certain extent, such as the Chinese patent application publication number CN104052691A A MIMO-OFDM system channel estimation method based on compressed sensing is proposed. Chinese patent application publication number CN105681232A proposes a MIMO channel estimation method based on shared channel and compressed sensing; however, in the case of strong background noise, lack of sampling data, and In severe and complex scenarios such as high sparsity, the accuracy of the channel estimation method based on compressed sensing is limited, and the high computational complexity of compressed sensing and a large number of iterative processes cause large delays, making it difficult to meet the needs of low-latency scenarios

Images