Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems
Hybrid analog-digital signal processing (HSP) is an enabling technology to harvest the potential of millimeter-wave (mmWave) massive-MIMO communications. In this paper, we present a general deep learning (DL) framework for efficient design and implementation of HSP-based massive-MIMO systems. Exploi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9815247/ |
| _version_ | 1818163880310865920 |
|---|---|
| author | Alireza Morsali Afshin Haghighat Benoit Champagne |
| author_facet | Alireza Morsali Afshin Haghighat Benoit Champagne |
| author_sort | Alireza Morsali |
| collection | DOAJ |
| description | Hybrid analog-digital signal processing (HSP) is an enabling technology to harvest the potential of millimeter-wave (mmWave) massive-MIMO communications. In this paper, we present a general deep learning (DL) framework for efficient design and implementation of HSP-based massive-MIMO systems. Exploiting the fact that any complex matrix can be written as a scaled sum of two matrices with unit-modulus entries, a novel <italic>analog</italic> deep neural network (ADNN) structure is first developed which can be implemented with common radio frequency (RF) components. This structure is then embedded into an extended hybrid analog-digital deep neural network (HDNN) architecture which facilitates the implementation of mmWave massive-MIMO systems while improving their performance. In particular, the proposed HDNN architecture enables HSP-based massive-MIMO transceivers to approximate any desired transmitter and receiver mapping with arbitrary precision. To demonstrate the capabilities of the proposed DL framework, we present a new HDNN-based beamformer design that can achieve the same performance as fully-digital beamforming, with reduced number of RF chains. Finally, simulation results are presented confirming the advantages of the proposed HDNN design over existing hybrid beamforming schemes. |
| first_indexed | 2024-12-11T16:56:35Z |
| format | Article |
| id | doaj.art-2214eddc66c548b188b0ddc790ca8297 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-11T16:56:35Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2214eddc66c548b188b0ddc790ca82972022-12-22T00:57:57ZengIEEEIEEE Access2169-35362022-01-0110723487236210.1109/ACCESS.2022.31886449815247Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO SystemsAlireza Morsali0https://orcid.org/0000-0002-8760-5218Afshin Haghighat1Benoit Champagne2https://orcid.org/0000-0002-0022-6072Department of Electrical and Computer Engineering, McGill University, Montreal, QC, CanadaInterDigital Canada, Montreal, QC, CanadaDepartment of Electrical and Computer Engineering, McGill University, Montreal, QC, CanadaHybrid analog-digital signal processing (HSP) is an enabling technology to harvest the potential of millimeter-wave (mmWave) massive-MIMO communications. In this paper, we present a general deep learning (DL) framework for efficient design and implementation of HSP-based massive-MIMO systems. Exploiting the fact that any complex matrix can be written as a scaled sum of two matrices with unit-modulus entries, a novel <italic>analog</italic> deep neural network (ADNN) structure is first developed which can be implemented with common radio frequency (RF) components. This structure is then embedded into an extended hybrid analog-digital deep neural network (HDNN) architecture which facilitates the implementation of mmWave massive-MIMO systems while improving their performance. In particular, the proposed HDNN architecture enables HSP-based massive-MIMO transceivers to approximate any desired transmitter and receiver mapping with arbitrary precision. To demonstrate the capabilities of the proposed DL framework, we present a new HDNN-based beamformer design that can achieve the same performance as fully-digital beamforming, with reduced number of RF chains. Finally, simulation results are presented confirming the advantages of the proposed HDNN design over existing hybrid beamforming schemes.https://ieeexplore.ieee.org/document/9815247/Hybrid beamformingdeep learningdeep neural networkshybrid analog-digital beamformingmassive-MIMOmmWave |
| spellingShingle | Alireza Morsali Afshin Haghighat Benoit Champagne Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems IEEE Access Hybrid beamforming deep learning deep neural networks hybrid analog-digital beamforming massive-MIMO mmWave |
| title | Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems |
| title_full | Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems |
| title_fullStr | Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems |
| title_full_unstemmed | Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems |
| title_short | Deep Learning-Based Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems |
| title_sort | deep learning based hybrid analog digital signal processing in mmwave massive mimo systems |
| topic | Hybrid beamforming deep learning deep neural networks hybrid analog-digital beamforming massive-MIMO mmWave |
| url | https://ieeexplore.ieee.org/document/9815247/ |
| work_keys_str_mv | AT alirezamorsali deeplearningbasedhybridanalogdigitalsignalprocessinginmmwavemassivemimosystems AT afshinhaghighat deeplearningbasedhybridanalogdigitalsignalprocessinginmmwavemassivemimosystems AT benoitchampagne deeplearningbasedhybridanalogdigitalsignalprocessinginmmwavemassivemimosystems |