Joint Channel Estimation and Mixed-ADCs Allocation for Massive MIMO via Deep Learning

Millimeter wave (mmWave) multi-user massive multi-input multi-output (MIMO) is a promising technique for the next generation communication systems. However, the hardware cost and power consumption grow significantly as the number of radio frequency (RF) components increases, which hampers the deployment of practical massive MIMO systems. To address this issue and further facilitate the commercialization of massive MIMO, mixed analog-to-digital converters (ADCs) architecture has been considered, where parts of conventionally assumed full-resolution ADCs are replaced by one-bit ADCs. In this paper, we first propose a deep learning-based (DL) joint pilot design and channel estimation method for mixed-ADCs mmWave massive MIMO. Specifically, we devise a pilot design neural network whose weights directly represent the optimized pilots, and develop a Runge-Kutta model-driven densely connected network as the channel estimator. Instead of randomly assigning the mixed-ADCs, we then design a novel antenna selection network for mixed-ADCs allocation to further improve the channel estimation accuracy. Moreover, we adopt an autoencoder-inspired end-to-end architecture to jointly optimize the pilot design, channel estimation and mixed-ADCs allocation networks. Simulation results show that the proposed DL-based methods have advantages over the traditional channel estimators as well as the state-of-the-art networks.

I. Introduction

Millimeter wave (mmWave) massive multi-input multi-output (MIMO), one of the promising technology for both 5G and the next generation mobile communication systems, has attracted tremendous attention for its several appealing advantages [1]. By deploying a massive array with hundreds or thousands of antennas at the base station (BS), massive MIMO can improve spectral efficiency and enhance cellular coverage [2]. Meanwhile, with the 30–300GHz mmWave frequency band, the array inter-element spacing can be reduced significantly, which allows to pack a large scale of antenna array into a small area at the BS. Furthermore, with highly directional beamforming, the massive antenna array can concentrate energy on the sparse mmWave channel paths to facilitate spatial multiplex and increase energy efficiency [3].