Deep Learning-Based Transmit Power Control for Device Activity Detection and Channel Estimation in Massive Access

被引：4

作者：

Sun, Zhuo ^{[1
]}

Yang, Nan ^{[2
]}

Li, Chunhui ^{[2
]}

Yuan, Jinhong ^{[3
]}

Quek, Tony Q. S. ^{[4
]}

机构：

[1] Northwestern Polytech Univ, Sch Comp Sci, Xian, Peoples R China

[2] Australian Natl Univ, Coll Engn & Comp Sci, Canberra, ACT 2600, Australia

[3] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia

[4] Singapore Univ Technol & Design, Dept Informat Syst Technol & Design, Singapore, Singapore

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2022年 / 11卷 / 01期

基金：

澳大利亚研究理事会; 中国国家自然科学基金;

关键词：

Deep learning; Channel estimation; Performance evaluation; Power control; Approximation algorithms; Sparse matrices; Rayleigh channels; Massive access; transmit power control; compressed sensing; deep learning; CONNECTIVITY; INTERNET; DESIGN;

D O I：

10.1109/LWC.2021.3123579

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We propose a transmit power control (TPC) scheme for grant-free multiple access, where each device is able to determine its transmit power based on a TPC function. For the proposed scheme, we design a novel deep learning framework to jointly design the TPC functions and the parametric Stein's unbiased risk estimate (SURE) approximate message passing (AMP) algorithm, which significantly improves the accuracy of active device detection and channel estimation, particularly for short pilot sequences. Simulations are conducted to demonstrate the advantages of our proposed deep learning framework on massive device activity detection and channel estimation compared to existing schemes.

引用

页码：183 / 187

页数：5

共 18 条

[1]

[Anonymous], 2021, IoT Connected Devices Worldwide 2019-2030

[2] Approximate Message-Passing Decoder and Capacity Achieving Sparse Superposition Codes [J].

Barbier, Jean ;

Krzakala, Florent .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2017, 63 (08) :4894-4927

[3] AMP-Inspired Deep Networks for Sparse Linear Inverse Problems [J].

Borgerding, Mark ;

Schniter, Philip ;

Rangan, Sundeep .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (16) :4293-4308

[4] Massive Access for 5G and Beyond [J].

Chen, Xiaoming ;

Ng, Derrick Wing Kwan ;

Yu, Wei ;

Larsson, Erik G. ;

Al-Dhahir, Naofal ;

Schober, Robert .

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2021, 39 (03) :615-637

[5] Sparse Activity Detection for Massive Connectivity [J].

Chen, Zhilin ;

Sohrabi, Foad ;

Yu, Wei .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, 66 (07) :1890-1904

[6] Message-passing algorithms for compressed sensing [J].

Donoho, David L. ;

Maleki, Arian ;

Montanari, Andrea .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2009, 106 (45) :18914-18919

[7] Techniques for Improving the Finite Length Performance of Sparse Superposition Codes [J].

Greig, Adam ;

Venkataramanan, Ramji .

IEEE TRANSACTIONS ON COMMUNICATIONS, 2018, 66 (03) :905-917

[8] Near Optimal Compressed Sensing Without Priors: Parametric SURE Approximate Message Passing [J].

Guo, Chunli ;

Davies, Mike E. .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2015, 63 (08) :2130-2141

[9] Deep Learning-Based Power Control for Non-Orthogonal Random Access [J].

Jang, Han Seung ;

Lee, Hoon ;

Quek, Tony Q. S. .

IEEE COMMUNICATIONS LETTERS, 2019, 23 (11) :2004-2007

[10] Joint Design of Measurement Matrix and Sparse Support Recovery Method via Deep Auto-Encoder [J].

Li, Shuaichao ;

Zhang, Wanqing ;

Cui, Ying ;

Cheng, Hei Victor ;

Yu, Wei .

IEEE SIGNAL PROCESSING LETTERS, 2019, 26 (12) :1778-1782

← 1 2 →