Model-Driven Deep Learning for Non-Coherent Massive Machine-Type Communications

被引:6
作者
Ma, Zhe [1 ,2 ]
Wu, Wen [3 ]
Gao, Feifei [1 ,2 ]
Shen, Xuemin [4 ]
机构
[1] Tsinghua Univ, Inst Artificial Intelligence, Beijing Natl Res Ctr Informat Sci & Technol, Dept Automat, Beijing, Peoples R China
[2] Tsinghua Univ, State Key Lab Intelligent Technol & Syst, Beijing, Peoples R China
[3] Peng Cheng Lab, Frontier Res Ctr, Shenzhen 518055, Guangdong, Peoples R China
[4] Univ Waterloo, Dept Elect & Comp Engn, Waterloo, ON N2L 3G1, Canada
基金
中国国家自然科学基金;
关键词
Massive machine-type communication (mMTC); non-coherent transmission; grant-free random access; deep learning; model-driven; CHANNEL ESTIMATION; ACCESS; CONNECTIVITY; ALGORITHMS;
D O I
10.1109/TWC.2023.3296218
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, we investigate the joint device activity and data detection in massive machine-type communications (mMTC) with a one-phase non-coherent scheme, where data bits are embedded in the pilot sequences and the base station simultaneously detects active devices and their embedded data bits without explicit channel estimation. Due to the correlated sparsity pattern introduced by the non-coherent transmission scheme, the traditional approximate message passing (AMP) algorithm cannot achieve satisfactory performance. Therefore, we propose a deep learning (DL) modified AMP network (DL-mAMPnet) that enhances the detection performance by effectively exploiting the pilot activity correlation. The DL-mAMPnet is constructed by unfolding the AMP algorithm into a feedforward neural network, which combines the principled mathematical model of the AMP algorithm with the powerful learning capability, thereby benefiting from the advantages of both techniques. Trainable parameters are introduced in the DL-mAMPnet to approximate the correlated sparsity pattern and the large-scale fading coefficient. Moreover, a refinement module is designed to further advance the performance by utilizing the spatial feature caused by the correlated sparsity pattern. Simulation results demonstrate that the proposed DL-mAMPnet can significantly outperform traditional algorithms in terms of the symbol error rate performance.
引用
收藏
页码:2197 / 2211
页数:15
相关论文
共 41 条
[31]   Grant-Free Massive MTC-Enabled Massive MIMO: A Compressive Sensing Approach [J].
Senel, Kamil ;
Larsson, Erik G. .
IEEE TRANSACTIONS ON COMMUNICATIONS, 2018, 66 (12) :6164-6175
[32]   Grant-Free Non-Orthogonal Multiple Access for IoT: A Survey [J].
Shahab, Muhammad Basit ;
Abbas, Rana ;
Shirvanimoghaddam, Mahyar ;
Johnson, Sarah J. .
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2020, 22 (03) :1805-1838
[33]   Holistic Network Virtualization and Pervasive Network Intelligence for 6G [J].
Shen, Xuemin ;
Gao, Jie ;
Wu, Wen ;
Li, Mushu ;
Zhou, Conghao ;
Zhuang, Weihua .
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2022, 24 (01) :1-30
[34]   AI-Assisted Network-Slicing Based Next-Generation Wireless Networks [J].
Shen, Xuemin ;
Gao, Jie ;
Wu, Wen ;
Lyu, Kangjia ;
Li, Mushu ;
Zhuang, Weihua ;
Li, Xu ;
Rao, Jaya .
IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY, 2020, 1 :45-66
[35]   Deep Learning-Based Channel Estimation [J].
Soltani, Mehran ;
Pourahmadi, Vahid ;
Mirzaei, Ali ;
Sheikhzadeh, Hamid .
IEEE COMMUNICATIONS LETTERS, 2019, 23 (04) :652-655
[36]   Algorithms for simultaneous sparse approximation. Part II: Convex relaxation [J].
Tropp, JA .
SIGNAL PROCESSING, 2006, 86 (03) :589-602
[37]   Deep Energy Autoencoder for Noncoherent Multicarrier MU-SIMO Systems [J].
Van Luong, Thien ;
Ko, Youngwook ;
Ngo Anh Vien ;
Matthaiou, Michail ;
Hien Quoc Ngo .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (06) :3952-3962
[38]   AI-Native Network Slicing for 6G Networks [J].
Wu, Wen ;
Zhou, Conghao ;
Li, Mushu ;
Wu, Huaqing ;
Zhou, Haibo ;
Zhang, Ning ;
Shen, Xuemin Sherman ;
Zhuang, Weihua .
IEEE WIRELESS COMMUNICATIONS, 2022, 29 (01) :96-103
[39]   Fast mmwave Beam Alignment via Correlated Bandit Learning [J].
Wu, Wen ;
Cheng, Nan ;
Zhang, Ning ;
Yang, Peng ;
Zhuang, Weihua ;
Shen, Xuemin .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2019, 18 (12) :5894-5908
[40]   End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels [J].
Xue, Songyan ;
Ma, Yi ;
Yi, Na .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2021, 20 (09) :5531-5542