Learnable Threshold Optimization for Massive Dynamic Multi-User Access Detection

SHI Chang-wei; GUO Li-ting; KANG Peng; DU Wei-qing; CHEN Ping-ping; FANG Yi

doi:10.12263/DZXB.20240404

您当前的位置：

首页 >

文章列表页 >

Learnable Threshold Optimization for Massive Dynamic Multi-User Access Detection

PAPERS | 更新时间：2025-08-18

- Learnable Threshold Optimization for Massive Dynamic Multi-User Access Detection
- ACTA ELECTRONICA SINICA Vol. 53, Issue 5, Pages: 1436-1444(2025)
- 作者机构：
  
  1.福州大学物理与信息工程学院，福建福州 350108
  2.广东工业大学信息工程学院，广东广州 510006
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62171135);Natural Science Foundation of Fujian Province(2023J01399);Distinguished Young Scholars Program of Fujian Province, China(2022J06010);Project of Education Department(2023XQ004)
- DOI：10.12263/DZXB.20240404
  CLC： TN914.5;TN929.5
- Received：07 May 2024，
  
  Revised：2024-11-21，
  
  Published：25 May 2025
- 稿件说明：
移动端阅览
石昌伟, 郭里婷, 康芃, 等. 可学习阈值优化的大规模动态多用户接入检测[J]. 电子学报, 2025, 53(05): 1436-1444.

SHI Chang-wei, GUO Li-ting, KANG Peng, et al. Learnable Threshold Optimization for Massive Dynamic Multi-User Access Detection[J]. Acta Electronica Sinica, 2025, 53(05): 1436-1444.
石昌伟, 郭里婷, 康芃, 等. 可学习阈值优化的大规模动态多用户接入检测[J]. 电子学报, 2025, 53(05): 1436-1444. DOI：10.12263/DZXB.20240404

SHI Chang-wei, GUO Li-ting, KANG Peng, et al. Learnable Threshold Optimization for Massive Dynamic Multi-User Access Detection[J]. Acta Electronica Sinica, 2025, 53(05): 1436-1444. DOI：10.12263/DZXB.20240404

摘要

在大规模免授权非正交多址接入（Grant-Free Non-Orthogonal Multiple Access，GF-NOMA）中，多用户检测往往依靠先验信号稀疏度进行活跃用户检测，但在实际应用，特别在动态多用户接入中，用户接入过程变得更加复杂，获取这种先验信息变得更为困难.针对该问题，本文提出一种可学习阈值优化的大规模动态多用户接入检测方案，即阈值改进的自适应交替方向乘子（Threshold-Improved Adaptive Alternating Direction Method of Multipliers，TI-A-ADMM）算法.在该算法中，利用活跃用户连续通信的时间相关性，引入动态相关性度量，对活跃用户检测的噪声阈值进行自适应缩放，提高检测性能.此外，为提升不同信噪比下活跃用户检测的准确度，采用深度学习网络对活跃用户检测初始阈值进行优化，以适应不同的接入环境.仿真结果表明，在未知先验稀疏度信息的动态多用户接入情况下，所提TI-A-ADMM算法相较现有已知稀疏度信息的算法，在误活跃率（Activity Error Rate，AER）和误符号率（Symbol Error Rate，SER）上能得到2.4 dB的性能增益.所提算法对因多用户接入而引起的干扰具有较低的性能衰减和更高的鲁棒性.

Abstract

In massive grant-free non-orthogonal multiple access (GF-NOMA) systems

multi-user detection usually relies on the prior sparsity of signals to detect active users. However

in practical applications

especially in dynamic multi-user access

the user access process becomes more complex and obtaining such prior information becomes more difficult. Therefore

this paper proposes a learnable threshold optimization scheme for massive dynamic multi-user access detection

namely the threshold-improved adaptive alternating direction method of multipliers (TI-A-ADMM) algorithm. In this algorithm

the time correlation of active user communication is utilized to introduce a dynamic correlation measure

which adaptively scales the noise threshold for active user detection

thereby improving detection performances. Moreover

to enhance the accuracy of active user detection across different signal-to-noise ratios

a deep learning network is employed to optimize the initial detection threshold

adapting to various access environments. Simulation results indicate that

in the case of dynamic multi-user access without known prior sparsity information

the proposed TI-A-ADMM algorithm achieves a performance gain of 2.4 dB in terms of active error rate (AER) and symbol error rate (SER) compared to existing algorithms with known sparsity information. The proposed algorithm exhibits lower performance degradation and higher robustness against interference caused by multi-user access.

关键词

Keywords

references

NGUYEN D C , DING M , PATHIRANA P N , et al . 6G Internet of Things: A comprehensive survey [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 1 ): 359 - 383 .

柴蓉 , 陈米铃 , 李锦红 . 基于效用优化的星地融合网络联合用户关联及资源块调度算法 [J ] . 电子学报 , 2023 , 51 ( 12 ): 3483 - 3495 .

CHAI R , CHEN M L , LI J H . Utility optimization-based joint user association and resource allocation algorithm for integrated satellite-terrestrial network [J ] . Acta Electronica Sinica , 2023 , 51 ( 12 ): 3483 - 3495 . (in Chinese)

LIU J A , WANG X D . A grant-based random access scheme with low latency for mMTC in IoT networks [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 20 ): 18211 - 18224 .

LEE W , CHOI S I , JANG Y H , et al . Distributed hybrid NOMA/OMA user allocation for wireless IoT networks [J ] . IEEE Internet of Things Journal , 2023 , 11 ( 3 ): 5316 - 5330 .

丁青锋 , 李怡浩 , 徐梦引 . 去蜂窝大规模MIMO-NOMA系统能效优化算法 [J ] . 电子学报 , 2023 , 51 ( 8 ): 2020 - 2029 .

DING Q F , LI Y H , XU M Y . Energy efficiency optimization algorithm for cell-free massive MIMO-NOMA systems [J ] . Acta Electronica Sinica , 2023 , 51 ( 8 ): 2020 - 2029 . (in Chinese)

LV S , XU X , HAN S , et al . Energy-efficient secure short-packet transmission in NOMA-assisted mMTC networks with relaying [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 2 ): 1699 - 1712 .

LIU J A , WANG X D . A grant-based random access scheme with low latency for mMTC in IoT networks [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 20 ): 18211 - 18224 .

BAI Y , CHEN W , AI B , et al . Prior information aided deep learning method for grant-free NOMA in mMTC [J ] . IEEE Journal on Selected Areas in Communications , 2022 , 40 ( 1 ): 112 - 126 .

HARA T , ISHIBASHI K . Blind multiple measurement vector AMP based on expectation maximization for grant-free NOMA [J ] . IEEE Wireless Communications Letters , 2022 , 11 ( 6 ): 1201 - 1205 .

GAO P , LIU Z , XIAO P , et al . Low-complexity block coordinate descend based multiuser detection for uplink grant-free NOMA [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 9 ): 9532 - 9543 .

KHAN S , DURRANI S , SHAHAB M B , et al . Joint user and data detection in grant-free NOMA with attention-based BiLSTM network [J ] . IEEE Open Journal of the Communications Society , 2023 , 4 : 1499 - 1515 .

陈平平 , 王宣达 , 谢肇鹏 , 等 . 基于稀疏贝叶斯学习的大规模多用户检测算法 [J ] . 通信学报 , 2023 , 44 ( 10 ): 186 - 197 .

CHEN P P , WANG X D , XIE Z P , et al . Sparse Bayesian learning-based massive multi-user detection algorithm [J ] . Journal on Communications , 2023 , 44 ( 10 ): 186 - 197 . (in Chinese)

GAO Z , KE M L , MEI Y K , et al . Compressive-sensing-based grant-free massive access for 6G massive communication [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 5 ): 7411 - 7435 .

BAI Y , CHEN W , SUN F , et al . Data-driven compressed sensing for massive wireless access [J ] . IEEE Communications Magazine , 2022 , 60 ( 11 ): 28 - 34 .

ZHANG Y , GUO Q , WANG Z , et al . Block sparse Bayesian learning based joint user activity detection and channel estimation for grant-free NOMA systems [J ] . IEEE Transactions on Vehicular Technology , 2018 , 67 ( 10 ): 9631 - 9640 .

DU Y , DONG B , ZHU W , et al . Joint channel estimation and multiuser detection for uplink grant-free NOMA [J ] . IEEE Wireless Communications Letters , 2018 , 7 ( 4 ): 682 - 685 .

HASAN S M , MAHATA K , HYDER M M . Uplink grant-free NOMA with sinusoidal spreading sequences [J ] . IEEE Transactions on Communications , 2021 , 69 ( 6 ): 3757 - 3770 .

DAI W , MILENKOVIC O . Subspace pursuit for compressive sensing signal reconstruction [J ] . IEEE Transactions on Information Theory , 2009 , 55 ( 5 ): 2230 - 2249 .

WANG B , DAI L , ZHANG Y , et al . Dynamic compressive sensing-based multi-user detection for uplink grant-free NOMA [J ] . IEEE Communications Letters , 2016 , 20 ( 11 ): 2320 - 2323 .

CUI Y , XU W , WANG Y , et al . Side-information aided compressed multi-user detection for up-link grant-free NOMA [J ] . IEEE Transactions on Wireless Communications , 2020 , 19 ( 11 ): 7720 - 7731 .

LIU Y , YI W , DING Z , et al . Developing NOMA to next generation multiple access: Future vision and research opportunities [J ] . IEEE Wireless Communications , 2022 , 29 ( 6 ): 120 - 127 .

CAMPO A , FABREGAS A G I , BIGLIERI E . Large-system analysis of multiuser detection with an unknown number of users: A high-SNR approach [J ] . IEEE Transactions on Information Theory , 2011 , 57 ( 6 ): 3416 - 3428 .

ZHU W , TAO M , GUAN Y . Double-sided information aided temporal-correlated massive access [J ] . IEEE Wireless Communications Letters , 2022 , 11 ( 9 ): 1860 - 1864 .

BELHABIB A , AMADID J , ZEROUAL A . Large-scale fading coefficients classification-aided power control strategy for mitigating the pilot contamination in massive MIMO systems [J ] . Statistics , Optimization & Information Computing, 2022 , 10 ( 1 ): 107 - 118 .

ZHANG X , FAN P , LIU J , et al . Bayesian learning-based multiuser detection for grant-free NOMA systems [J ] . IEEE Transactions on Wireless Communications , 2022 , 21 ( 8 ): 6317 - 6328 .

LIU H , SONG B , QIN H , et al . An adaptive-ADMM algorithm with support and signal value detection for compressed sensing [J ] . IEEE Signal Processing Letters , 2013 , 20 ( 4 ): 315 - 318 .

TROPP J A , GILBERT A C . Signal recovery from random measurements via orthogonal matching pursuit [J ] . IEEE Transactions on Information Theory , 2007 , 53 ( 12 ): 4655 - 4666 .

DU Y , DONG B , CHEN Z , et al . Efficient multi-user detection for uplink grant-free NOMA: Prior-information aided adaptive compressive sensing perspective [J ] . IEEE Journal on Selected Areas in Communications , 2017 , 35 ( 12 ): 2812 - 2828 .

GHAFOOR U , ALI M , KHAN H Z , et al . NOMA and future 5G & B5G wireless networks: A paradigm [J ] . Journal of Network and Computer Applications , 2022 , 204 : 103413 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Target Recognition Technology Based on a New Joint Sensing Matrix for Compressed Learning

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Differentially Private with Sparse and Smooth Self-Distillation

Operator Fusion Method and Hardware Architecture Design Based on Non-Standard Operators

Related Author

LI Feng

XIN Lei

LIU Yang

XIAO Hua-chao

ZHAN Bang-cheng

LIU Zhi-jia

HUANG Yu-zhe

GUAN Yong-yuan

Related Institution

Qian Xuesen Laboratory of Space Technology

China Academy of Space Technology

Henan Key Laboratory of Big Data Analysis and Processing， Henan University

DFH Satellite Co.， Ltd.

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

⁰