• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

强化学习和深度学习在多输入多输出(MIMO)系统中的应用。

Application of Reinforcement Learning and Deep Learning in Multiple-Input and Multiple-Output (MIMO) Systems.

机构信息

Institute of High Performance Computing and Networking, National Research Council of Italy, 80131 Napoli, Italy.

出版信息

Sensors (Basel). 2021 Dec 31;22(1):309. doi: 10.3390/s22010309.

DOI:10.3390/s22010309
PMID:35009848
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8749942/
Abstract

The current wireless communication infrastructure has to face exponential development in mobile traffic size, which demands high data rate, reliability, and low latency. MIMO systems and their variants (i.e., Multi-User MIMO and Massive MIMO) are the most promising 5G wireless communication systems technology due to their high system throughput and data rate. However, the most significant challenges in MIMO communication are substantial problems in exploiting the multiple-antenna and computational complexity. The recent success of RL and DL introduces novel and powerful tools that mitigate issues in MIMO communication systems. This article focuses on RL and DL techniques for MIMO systems by presenting a comprehensive review on the integration between the two areas. We first briefly provide the necessary background to RL, DL, and MIMO. Second, potential RL and DL applications for different MIMO issues, such as detection, classification, and compression; channel estimation; positioning, sensing, and localization; CSI acquisition and feedback, security, and robustness; mmWave communication and resource allocation, are presented.

摘要

当前的无线通信基础设施必须面对移动流量规模的指数级增长,这需要高数据速率、可靠性和低延迟。MIMO 系统及其变体(即多用户 MIMO 和大规模 MIMO)是最有前途的 5G 无线通信系统技术,因为它们具有高系统吞吐量和数据速率。然而,MIMO 通信中最显著的挑战是在利用多天线和计算复杂性方面存在重大问题。RL 和 DL 的最新成功引入了新的强大工具,可以缓解 MIMO 通信系统中的问题。本文通过对这两个领域的综合回顾,重点介绍了用于 MIMO 系统的 RL 和 DL 技术。我们首先简要介绍了 RL、DL 和 MIMO 的必要背景。其次,介绍了 RL 和 DL 在不同 MIMO 问题(如检测、分类和压缩;信道估计;定位、感知和定位;CSI 获取和反馈、安全性和鲁棒性;mmWave 通信和资源分配)中的潜在应用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/c70723716fd8/sensors-22-00309-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/2865bf28ff46/sensors-22-00309-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/b69a0004815b/sensors-22-00309-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/a093a0f8f6e5/sensors-22-00309-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/7cdba38eff54/sensors-22-00309-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/64b20ffc095d/sensors-22-00309-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/b107d3394c04/sensors-22-00309-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/afe7076af2a5/sensors-22-00309-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/c70723716fd8/sensors-22-00309-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/2865bf28ff46/sensors-22-00309-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/b69a0004815b/sensors-22-00309-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/a093a0f8f6e5/sensors-22-00309-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/7cdba38eff54/sensors-22-00309-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/64b20ffc095d/sensors-22-00309-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/b107d3394c04/sensors-22-00309-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/afe7076af2a5/sensors-22-00309-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a1ff/8749942/c70723716fd8/sensors-22-00309-g008.jpg

相似文献

1
Application of Reinforcement Learning and Deep Learning in Multiple-Input and Multiple-Output (MIMO) Systems.强化学习和深度学习在多输入多输出(MIMO)系统中的应用。
Sensors (Basel). 2021 Dec 31;22(1):309. doi: 10.3390/s22010309.
2
Deep Reinforcement Learning-Based Coordinated Beamforming for mmWave Massive MIMO Vehicular Networks.基于深度强化学习的毫米波大规模 MIMO 车联网协同波束成形。
Sensors (Basel). 2023 Mar 3;23(5):2772. doi: 10.3390/s23052772.
3
Deep Learning for Massive MIMO Channel State Acquisition and Feedback.用于大规模多输入多输出(Massive MIMO)信道状态获取与反馈的深度学习
J Indian Inst Sci. 2020;100(2):369-382. doi: 10.1007/s41745-020-00169-2. Epub 2020 May 3.
4
Massive MIMO Systems for 5G and Beyond Networks-Overview, Recent Trends, Challenges, and Future Research Direction.面向5G及未来网络的大规模MIMO系统——概述、最新趋势、挑战及未来研究方向
Sensors (Basel). 2020 May 12;20(10):2753. doi: 10.3390/s20102753.
5
Deep Learning-Based Channel Estimation for mmWave Massive MIMO Systems in Mixed-ADC Architecture.混合模数转换器架构下毫米波大规模多输入多输出系统基于深度学习的信道估计
Sensors (Basel). 2022 May 23;22(10):3938. doi: 10.3390/s22103938.
6
A Deep Learning Approach for MIMO-NOMA Downlink Signal Detection.一种用于MIMO-NOMA下行链路信号检测的深度学习方法。
Sensors (Basel). 2019 Jun 2;19(11):2526. doi: 10.3390/s19112526.
7
Reinforcement Learning-Based Joint User Pairing and Power Allocation in MIMO-NOMA Systems.基于强化学习的MIMO-NOMA系统联合用户配对与功率分配
Sensors (Basel). 2020 Dec 11;20(24):7094. doi: 10.3390/s20247094.
8
Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems.基于深度强化学习的毫米波大规模MIMO-NOMA系统频谱高效用户分组与资源分配
Sci Rep. 2024 Apr 17;14(1):8884. doi: 10.1038/s41598-024-59241-x.
9
Energy Efficiency and Spectral Efficiency Tradeoff in Massive MIMO Multicast Transmission with Statistical CSI.基于统计信道状态信息的大规模多输入多输出组播传输中的能量效率与频谱效率权衡
Entropy (Basel). 2020 Sep 18;22(9):1045. doi: 10.3390/e22091045.
10
Design, Challenges and Developments for 5G Massive MIMO Antenna Systems at Sub 6-GHz Band: A Review.6GHz以下频段5G大规模多输入多输出(MIMO)天线系统的设计、挑战与发展:综述
Nanomaterials (Basel). 2023 Jan 28;13(3):520. doi: 10.3390/nano13030520.

引用本文的文献

1
Spectral efficiency and BER analysis of RNN based hybrid precoding for cell free massive MIMO under terahertz communication.太赫兹通信下基于循环神经网络的无小区大规模多输入多输出混合预编码的频谱效率与误码率分析
PLoS One. 2025 Aug 14;20(8):e0328499. doi: 10.1371/journal.pone.0328499. eCollection 2025.
2
An enhanced performance analysis of load based resource sharing framework for MIMO systems in 5G communication systems.5G通信系统中基于负载的MIMO系统资源共享框架的性能增强分析
Sci Rep. 2025 Jul 2;15(1):23327. doi: 10.1038/s41598-025-06441-8.
3
Reinforcement Learning-Aided Channel Estimator in Time-Varying MIMO Systems.

本文引用的文献

1
Reinforcement learning for intelligent healthcare applications: A survey.强化学习在智能医疗保健应用中的研究进展:综述
Artif Intell Med. 2020 Sep;109:101964. doi: 10.1016/j.artmed.2020.101964. Epub 2020 Sep 28.
2
Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions.深度学习:关于技术、分类法、应用及研究方向的全面综述
SN Comput Sci. 2021;2(6):420. doi: 10.1007/s42979-021-00815-1. Epub 2021 Aug 18.
3
Machine Learning-Based 5G-and-Beyond Channel Estimation for MIMO-OFDM Communication Systems.
基于强化学习的时变 MIMO 系统信道估计器。
Sensors (Basel). 2023 Jun 18;23(12):5689. doi: 10.3390/s23125689.
4
A Literature Survey on AI-Aided Beamforming and Beam Management for 5G and 6G Systems.人工智能辅助的 5G 和 6G 系统波束成形和波束管理的文献综述。
Sensors (Basel). 2023 Apr 28;23(9):4359. doi: 10.3390/s23094359.
5
A Study on the Impact of Integrating Reinforcement Learning for Channel Prediction and Power Allocation Scheme in MISO-NOMA System.基于强化学习的 MISO-NOMA 系统信道预测与功率分配方案的研究。
Sensors (Basel). 2023 Jan 26;23(3):1383. doi: 10.3390/s23031383.
6
Optimal User Scheduling in Multi Antenna System Using Multi Agent Reinforcement Learning.多智能体强化学习在多天线系统中的最优用户调度。
Sensors (Basel). 2022 Oct 28;22(21):8278. doi: 10.3390/s22218278.
7
A Low-Complexity Algorithm for a Reinforcement Learning-Based Channel Estimator for MIMO Systems.基于强化学习的 MIMO 系统信道估计器的低复杂度算法。
Sensors (Basel). 2022 Jun 9;22(12):4379. doi: 10.3390/s22124379.
基于机器学习的 5G 及未来通信系统中 MIMO-OFDM 信道估计
Sensors (Basel). 2021 Jul 16;21(14):4861. doi: 10.3390/s21144861.
4
Generalization aspect of accurate machine learning models for CSI-based localization.基于信道状态信息(CSI)定位的精确机器学习模型的泛化方面。
Ann Telecommun. 2022;77(5-6):345-357. doi: 10.1007/s12243-021-00853-z. Epub 2021 Jun 14.
5
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects.卷积神经网络综述:分析、应用与展望
IEEE Trans Neural Netw Learn Syst. 2022 Dec;33(12):6999-7019. doi: 10.1109/TNNLS.2021.3084827. Epub 2022 Nov 30.
6
Deep Learning for Massive MIMO Channel State Acquisition and Feedback.用于大规模多输入多输出(Massive MIMO)信道状态获取与反馈的深度学习
J Indian Inst Sci. 2020;100(2):369-382. doi: 10.1007/s41745-020-00169-2. Epub 2020 May 3.
7
Massive MIMO Systems for 5G and Beyond Networks-Overview, Recent Trends, Challenges, and Future Research Direction.面向5G及未来网络的大规模MIMO系统——概述、最新趋势、挑战及未来研究方向
Sensors (Basel). 2020 May 12;20(10):2753. doi: 10.3390/s20102753.
8
Deep Learning-Based Secure MIMO Communications with Imperfect CSI for Heterogeneous Networks.基于深度学习的异构网络不完美信道状态信息安全多输入多输出通信
Sensors (Basel). 2020 Mar 20;20(6):1730. doi: 10.3390/s20061730.
9
Convolutional neural networks: an overview and application in radiology.卷积神经网络:概述及其在放射学中的应用。
Insights Imaging. 2018 Aug;9(4):611-629. doi: 10.1007/s13244-018-0639-9. Epub 2018 Jun 22.
10
Adaptive Neural Control of Uncertain Nonlinear Systems Using Disturbance Observer.基于干扰观测器的不确定非线性系统自适应神经控制
IEEE Trans Cybern. 2017 Oct;47(10):3110-3123. doi: 10.1109/TCYB.2017.2667680. Epub 2017 Mar 10.