模型驱动深度学习增强的马尔可夫链蒙特卡罗MIMO检测器：设计、仿真与原型验证

曹益枭; 周星宇; 张静; 梁乐; 李勇; 金石

doi:10.12263/DZXB.20240798

您当前的位置：

首页 >

文章列表页 >

模型驱动深度学习增强的马尔可夫链蒙特卡罗MIMO检测器：设计、仿真与原型验证

中国电子学会科学技术奖特约专栏 | 更新时间：2025-07-24

- 模型驱动深度学习增强的马尔可夫链蒙特卡罗MIMO检测器：设计、仿真与原型验证
- Model-Driven Deep Learning-Enhanced Markov Chain Monte Carlo MIMO Detector: Design, Simulation and Prototyping
- 电子学报 2025年53卷第4期页码：1142-1152
- 作者机构：
  
  1.东南大学信息科学与工程学院，江苏南京 211189
  2.先进通信网全国重点实验室，河北石家庄 050081
  3.中国电科网络通信研究院，河北石家庄 050081
- 作者简介：
  
  [ "曹益枭男，2024年获得东南大学通信工程专业学士学位.目前正在东南大学信息科学与工程学院攻读硕士学位.主要研究方向为物理层通信、机器学习以及人工智能. E-mail: 220240883@seu.edu.cn" ]
  [ "周星宇男，2021年获得南京邮电大学通信工程专业学士学位.目前正在东南大学信息科学与工程学院攻读博士学位.主要研究方向为基于机器学习的通信信号处理和收发器设计. E-mail: xy_zhou@seu.edu.cn" ]
  [ "张静女，2015年获得中国矿业大学信息与通信工程专业学士学位，并于2018年和2022年分别获得东南大学信息与通信工程专业硕士和博士学位.目前在东南大学信息科学与工程学院担任讲师职务.主要研究方向为物理层通信、人工智能以及收发器设计. E-mail: jingzhang@seu.edu.cn" ]
  [ "梁乐男，2012年获得东南大学信息工程学士学位，2015年获得维多利亚大学电气工程硕士学位，2018年获得乔治亚理工学院电气与计算机工程博士学位.目前在东南大学国家移动通信研究所工作.主要研究方向为无线通信与机器学习.中国电子学会会员编号：E190034275M. E-mail: lliang@seu.edu.cn" ]
  [ "李勇男，分别于2009年、2011年和2014年在哈尔滨工业大学获得学士、硕士和博士学位.目前在中国电子科技集团公司第54研究所先进通信网络国家重点实验室担任教授级高级工程师.主要研究方向为无线人工智能通信、物理层安全和调制理论. E-mail: young_li_54@126.com" ]
  [ "金石男，于1996年在桂林电子科技大学获得通信工程学士学位，2003年在南京邮电大学获得硕士学位，2007年在东南大学获得信息与通信工程博士学位.目前在东南大学国家移动通信研究所任教.主要研究方向为无线通信、随机矩阵理论和信息论." ]
- 基金信息：
  
  国家自然科学基金(62261160576;62301154;623B2019;62231019);先进通信网全国重点实验室基金课题(SCX23641X011)
- DOI：10.12263/DZXB.20240798
  中图分类号： TN929.5;
- 收稿：2024-09-03，
  
  修回：2025-04-23，
  
  纸质出版：2025-04-25
- 稿件说明：
移动端阅览
曹益枭, 周星宇, 张静, 等. 模型驱动深度学习增强的马尔可夫链蒙特卡罗MIMO检测器：设计、仿真与原型验证[J]. 电子学报, 2025, 53(04): 1142-1152.

CAO Yi-xiao, ZHOU Xing-yu, ZHANG Jing, et al. Model-Driven Deep Learning-Enhanced Markov Chain Monte Carlo MIMO Detector: Design, Simulation and Prototyping[J]. Acta Electronica Sinica, 2025, 53(04): 1142-1152.
曹益枭, 周星宇, 张静, 等. 模型驱动深度学习增强的马尔可夫链蒙特卡罗MIMO检测器：设计、仿真与原型验证[J]. 电子学报, 2025, 53(04): 1142-1152. DOI：10.12263/DZXB.20240798

CAO Yi-xiao, ZHOU Xing-yu, ZHANG Jing, et al. Model-Driven Deep Learning-Enhanced Markov Chain Monte Carlo MIMO Detector: Design, Simulation and Prototyping[J]. Acta Electronica Sinica, 2025, 53(04): 1142-1152. DOI：10.12263/DZXB.20240798

摘要

多输入多输出（Multiple-Input Multiple-Output，MIMO）系统规模日益增长，导致接收机信号检测计算复杂度急剧上升，传统检测算法难以在误码性能和复杂度之间取得良好平衡.基于马尔可夫链蒙特卡罗（Markov Chain Monte Carlo，MCMC）的检测算法能以多项式量级的复杂度实现近最优的检测性能，然而该方法在低采样数下性能损失严重.因此，本文引入了基于模型驱动的深度学习技术，将MCMC迭代过程展开为级联网络结构，向网络中引入可训练参数，通过深度学习方法优化参数设置.根据复杂度分析与仿真验证，所提方案在编码场景下的误码性能优于原始算法约1 dB，同时计算复杂度显著低于原始算法.为验证模型驱动深度学习方案在实际传输中的性能，搭建2 × 2 MIMO智能通信原型验证平台，并进行端到端空口传输测试.测试结果表明，模型驱动深度学习增强的MCMC检测算法可以更低的计算复杂度实现误码性能优势，从而证实了所提方案在实际传输环境中的有效性和鲁棒性.

Abstract

The scale of multiple-input multiple-output (MIMO) systems is growing rapidly

leading to a dramatic increase in the computational complexity of receiver signal detection. Traditional detection algorithms struggle to achieve a good balance between bit error rate (BER) performance and computational complexity. Markov chain Monte Carlo (MCMC)-based detection algorithms can achieve near-optimal detection performance with polynomial complexity

but their performance deteriorates significantly with low sampling rates. To address this issue

this paper introduces a model-driven deep learning approach

which transforms the MCMC iterative process into a cascade network structure. Trainable parameters are incorporated into the network

and deep learning techniques are employed to optimize their settings. Based on complexity analysis and simulation results

the proposed method outperforms the original algorithm in terms of BER by approximately 1 dB in coding scenarios

while significantly reducing computational complexity. To validate the performance of the model-driven deep learning approach in real-world transmission

a 2×2 MIMO smart communication prototype is developed

and end-to-end air interface transmission tests are conducted. The test results demonstrate that the MCMC detection algorithm enhanced by the model-driven deep learning approach still achieves a significant BER performance advantage with lower computational complexity

thereby confirming the effectiveness and robustness of the proposed solution in practical transmission environments.

关键词

Keywords

references

YANG S S , HANZO L . Fifty years of MIMO detection: The Road to large-scale MIMOs [J ] . IEEE Communications Surveys & Tutorials , 2015 , 17 ( 4 ): 1941 - 1988 .

YOU X H , WANG C X , HUANG J , et al . Towards 6G wireless communication networks: Vision, enabling technologies, and new paradigm shifts [J ] . Science China Information Sciences , 2020 , 64 ( 1 ): 110301 .

WANG C X , YOU X H , GAO X Q , et al . On the road to 6G: Visions, requirements, key technologies, and testbeds [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 2 ): 905 - 974 .

ALBREEM M A , JUNTTI M , SHAHABUDDIN S . Massive MIMO detection techniques: A survey [J ] . IEEE Communications Surveys & Tutorials , 2019 , 21 ( 4 ): 3109 - 3132 .

HOCHWALD B M , BRINK S TEN . Achieving near-capacity on a multiple-antenna channel [J ] . IEEE Transactions on Communications , 2003 , 51 ( 3 ): 389 - 399 .

HE Y F , ZHANG J , JIN S , et al . Model-driven DNN decoder for turbo codes: Design, simulation, and experimental results [J ] . IEEE Transactions on Communications , 2020 , 68 ( 10 ): 6127 - 6140 .

JIN J J , LIANG X , XU Y H , et al . LDPC decoder based on Markov chain Monte Carlo method [C ] // 2018 IEEE Asia Pacific Conference on Circuits and Systems . Piscataway : IEEE , 2018 : 219 - 222 .

HEDSTROM J C , YUEN C H , CHEN R R , et al . Achieving near MAP performance with an excited Markov chain Monte Carlo MIMO detector [J ] . IEEE Transactions on Wireless Communications , 2017 , 16 ( 12 ): 7718 - 7732 .

HUANG J T , KIM Y H . MCMC decoding of LDPC codes with BP preprocessing [C ] // GLOBECOM 2020 - 2020 IEEE Global Communications Conference . Piscataway : IEEE , 2020 : 1 - 5 .

WELLING M , TEH Y W . Bayesian learning via stochastic gradient Langevin dynamics [C ] // Proceedings of the 28th International Conference on Machine Learning (ICML-11) . New York : ACM , 2011 : 681 - 688 .

ZHOU X Y , LIANG L , ZHANG J , et al . Decentralized massive MIMO detection using mini-batch gradient-based MCMC [C ] // 2024 IEEE 25th International Workshop on Signal Processing Advances in Wireless Communications . Piscataway : IEEE , 2024 : 456 - 460 .

WU Z W , LI H . Stochastic gradient Langevin dynamics for massive MIMO detection [J ] . IEEE Communications Letters , 2022 , 26 ( 5 ): 1062 - 1065 .

ZHOU X Y , LIANG L , ZHANG J , et al . Gradient-based Markov chain Monte Carlo for MIMO detection [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 7 ): 7566 - 7581 .

GOWDA N M , KRISHNAMURTHY S , BELOGOLOVY A . Metropolis-Hastings random walk along the gradient descent direction for MIMO detection [C ] // ICC 2021 - IEEE International Conference on Communications . Piscataway : IEEE , 2021 : 1 - 7 .

QIN Z J , YE H , LI G Y , et al . Deep learning in physical layer communications [J ] . IEEE Wireless Communications , 2019 , 26 ( 2 ): 93 - 99 .

YE H , LIANG L , LI G Y , et al . Deep learning-based end-to-end wireless communication systems with conditional GANs as unknown channels [J ] . IEEE Transactions on Wireless Communications , 2020 , 19 ( 5 ): 3133 - 3143 .

KOSASIH A , ONASIS V , MILOSLAVSKAYA V , et al . Graph neural network aided MU-MIMO detectors [J ] . IEEE Journal on Selected Areas in Communications , 2022 , 40 ( 9 ): 2540 - 2555 .

ZHOU X Y , ZHANG J , SYU C W , et al . Model-driven deep learning-based MIMO-OFDM detector: Design, simulation, and experimental results [J ] . IEEE Transactions on Communications , 2022 , 70 ( 8 ): 5193 - 5207 .

HU Q , GAO F F , ZHANG H , et al . Understanding deep MIMO detection [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 12 ): 9626 - 9639 .

SAMUEL N , DISKIN T , WIESEL A . Deep MIMO detection [C ] // 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications . Piscataway : IEEE , 2017 : 1 - 5 .

HE H T , WEN C K , JIN S , et al . Model-driven deep learning for MIMO detection [J ] . IEEE Transactions on Signal Processing , 2020 , 68 : 1702 - 1715 .

WANG X D , POOR H V . Iterative (turbo) soft interference cancellation and decoding for coded CDMA [J ] . IEEE Transactions on Communications , 1999 , 47 ( 7 ): 1046 - 1061 .

MA Y A , CHEN Y S , JIN C , et al . Sampling can be faster than optimization [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2019 , 116 ( 42 ): 20881 - 20885 .

MA L , DICKSON K , MCALLISTER J , et al . QR decomposition-based matrix inversion for high performance embedded MIMO receivers [J ] . IEEE Transactions on Signal Processing , 2011 , 59 ( 4 ): 1858 - 1867 .

GALLAGER R . Low-density parity-check codes [J ] . IRE Transactions on Information Theory , 1962 , 8 ( 1 ): 21 - 28 .

CÉSPEDES J , OLMOS P M , SÁNCHEZ-FERNÁNDEZ M , et al . Expectation propagation detection for high-order high-dimensional MIMO systems [J ] . IEEE Transactions on Communications , 2014 , 62 ( 8 ): 2840 - 2849 .

GUO Z , NILSSON P . Algorithm and implementation of the K-best sphere decoding for MIMO detection [J ] . IEEE Journal on Selected Areas in Communications , 2006 , 24 ( 3 ): 491 - 503 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向时序异常检测的可变视距多向扫描方法

基于稀疏平滑自蒸馏的差分隐私深度学习方法

基于非一般类算子融合方法及硬件架构设计

基于注意力融合多尺度特征的解压缩点云质量增强方法