共 50 条
Deep Learning Methods for Universal MISO Beamforming
被引:45
作者:
Kim, Junbeom
[1
]
Lee, Hoon
[2
]
Hong, Seung-Eun
[3
]
Park, Seok-Hwan
[1
]
机构:
[1] Jeonbuk Natl Univ, Div Elect Engn, Jeonju 54896, South Korea
[2] Pukyong Natl Univ, Dept Informat & Commun Engn, Busan 48513, South Korea
[3] Elect & Telecommun Res Inst, Future Mobile Commun Res Div, Daejeon 34129, South Korea
基金:
新加坡国家研究基金会;
关键词:
Array signal processing;
Optimization;
Downlink;
Training;
Deep learning;
MISO communication;
Neural networks;
Multi-user MISO downlink;
deep learning;
beamforming;
interference management;
unsupervised learning;
OPTIMIZATION;
D O I:
10.1109/LWC.2020.3007198
中图分类号:
TP [自动化技术、计算机技术];
学科分类号:
0812 ;
摘要:
This letter studies deep learning (DL) approaches to optimize beamforming vectors in downlink multi-user multi-antenna systems that can be universally applied to arbitrarily given transmit power limitation at a base station. We exploit the sum power budget as side information so that deep neural networks (DNNs) can effectively learn the impact of the power constraint in the beamforming optimization. Consequently, a single training process is sufficient for the proposed universal DL approach, whereas conventional methods need to train multiple DNNs for all possible power budget levels. Numerical results demonstrate the effectiveness of the proposed DL methods over existing schemes.
引用
收藏
页码:1894 / 1898
页数:5
相关论文