DNN-based Detectors for Massive MIMO Systems with Low-Resolution ADCs
DNN-based Detectors for Massive MIMO Systems with Low-Resolution ADCs
复制标题
DOI：
10.1109/icc42927.2021.9501054
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Ly V. Nguyen;D. Nguyen;A. L. Swindlehurst
中科院分区：
文献类型：
--
作者：
Ly V. Nguyen;D. Nguyen;A. L. Swindlehurst
低分辨率模数转换器（ADC）被认为是大规模多输入多输出（MIMO）系统中降低成本和功耗的实用且有前途的解决方案。不幸的是，低分辨率ADC会使接收信号严重失真，从而使数据检测更具挑战性。在本文中，我们开发了一种新的深度神经网络（DNN）框架，用于低分辨率大规模MIMO系统中的高效和低复杂度数据检测。基于重新定义的最大似然检测问题，我们提出了两个模型驱动的DNN为基础的检测器，即OBMNet和FBMNet，分别为一位和几位大规模MIMO系统。所提出的OBMNet和FBMNet检测器具有为低分辨率MIMO接收器设计的独特而简单的结构，因此可以有效地训练和实现。数值结果还表明，OBMNet和FBMNet显着优于现有的检测方法。
Low-resolution analog-to-digital converters (ADCs) have been considered as a practical and promising solution for reducing cost and power consumption in massive Multiple-Input-Multiple-Output (MIMO) systems. Unfortunately, low-resolution ADCs significantly distort the received signals, and thus make data detection much more challenging. In this paper, we develop a new deep neural network (DNN) framework for efficient and low-complexity data detection in low-resolution massive MIMO systems. Based on reformulated maximum likelihood detection problems, we propose two model-driven DNN-based detectors, namely OBMNet and FBMNet, for one-bit and few-bit massive MIMO systems, respectively. The proposed OBMNet and FBMNet detectors have unique and simple structures designed for low-resolution MIMO receivers and thus can be efficiently trained and implemented. Numerical results also show that OBMNet and FBMNet significantly outperform existing detection methods.