期刊
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
卷 70, 期 7, 页码 7255-7260出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TVT.2021.3087132
关键词
Antennas; Antenna arrays; Neural networks; Massive MIMO; Signal processing algorithms; Feature extraction; Computational complexity; Antenna selection; deep neural network; massive MIMO; multi-label learning
资金
- National Natural Science Foundation of China [61801208, 61931023, U1936202]
This paper proposes a low-complexity antenna selection algorithm based on multi-label learning, using a deep neural network to extract low-dimensional features of the channel matrix for accurate prediction of selected antenna sets. Compared to traditional methods, the new algorithm achieves comparable capacity while reducing computation time.
Antenna selection (AS) is a signal processing technology that can greatly reduce the hardware complexity of multi-antenna systems. Specifically, AS can decrease the number of required radio frequency chains by activating only a subset of the available antennas in each transmission slot. However, optimal AS suffers from a high computational complexity that increases exponentially with the scale of the antenna array. In this paper, we propose a low-complexity AS algorithm based on multi-label learning (MLL), where a deep neural network is employed to determine the set of selected antennas for a given channel matrix. Specifically, the MLL network combines deep canonical correlation analysis and an autoencoder in a unified network structure, which can extract the low dimensional features of channel matrix as well as the interdependency among selected antennas, so as to achieve an accurate prediction of the set of selected antennas with a relatively small-scale learning model. Simulation results show that, in comparison with the convex relaxation based method, our proposed MLL-based method can achieve comparable capacity with significantly reduced computation time.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据