A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming
In the sixth-generation (6G) cellular networks, hybrid beamforming would be a real-time optimization problem that is becoming progressively more challenging. Although numerical computation-based iterative methods such as the minimal mean square error (MMSE) and the alternative manifold optimization...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10098778/ |
| _version_ | 1827960468736573440 |
|---|---|
| author | Rafid Umayer Murshed Zulqarnain Bin Ashraf Abu Horaira Hridhon Kumudu Munasinghe Abbas Jamalipour Md. Farhad Hossain |
| author_facet | Rafid Umayer Murshed Zulqarnain Bin Ashraf Abu Horaira Hridhon Kumudu Munasinghe Abbas Jamalipour Md. Farhad Hossain |
| author_sort | Rafid Umayer Murshed |
| collection | DOAJ |
| description | In the sixth-generation (6G) cellular networks, hybrid beamforming would be a real-time optimization problem that is becoming progressively more challenging. Although numerical computation-based iterative methods such as the minimal mean square error (MMSE) and the alternative manifold optimization (Alt-Min) can already attain near-optimal performance, their computational cost renders them unsuitable for real-time applications. However, recent studies have demonstrated that machine learning techniques like deep neural networks (DNN) can learn the mapping done by those algorithms between channel state information (CSI) and near-optimal resource allocation and then approximate this mapping in near real-time. In light of this, we investigate various DNN architectures for beamforming challenges in the terahertz (THz) band for ultra-massive multiple-input multiple-output (UM-MIMO) and explore their contextual mathematical modelling. Specifically, we design a sophisticated 1D convolutional neural network and long short-term memory (1D CNN-LSTM) based fusion-separation scheme, which can approach the performance of the Alt-Min algorithm in terms of spectral efficiency (SE) for fully connected structures and, at the same time, use significantly less computational effort. Simulation results indicate that the proposed system can attain almost the same level of SE as that of the numerical iterative algorithms while incurring a substantial reduction in computational cost. Our DNN-based approach also exhibits exceptional adaptability to diverse network setups and high scalability. Although the current model only addresses the fully connected hybrid architecture, our approach can also be expanded to address a variety of other beamforming topologies. |
| first_indexed | 2024-04-09T16:09:04Z |
| format | Article |
| id | doaj.art-c393af29954c4089aedf8b7246f3a5bb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T16:09:04Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c393af29954c4089aedf8b7246f3a5bb2023-04-24T23:00:32ZengIEEEIEEE Access2169-35362023-01-0111386143863010.1109/ACCESS.2023.326635510098778A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid BeamformingRafid Umayer Murshed0https://orcid.org/0000-0002-9030-4336Zulqarnain Bin Ashraf1https://orcid.org/0000-0002-8602-346XAbu Horaira Hridhon2https://orcid.org/0009-0004-4465-3932Kumudu Munasinghe3https://orcid.org/0000-0002-0141-8973Abbas Jamalipour4https://orcid.org/0000-0002-1807-7220Md. Farhad Hossain5https://orcid.org/0000-0001-5632-7633Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshSchool of IT and Systems, University of Canberra, Canberra, ACT, AustraliaDepartment of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshSchool of IT and Systems, University of Canberra, Canberra, ACT, AustraliaSchool of Electrical and Information Engineering, The University of Sydney, Camperdown, NSW, AustraliaDepartment of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshIn the sixth-generation (6G) cellular networks, hybrid beamforming would be a real-time optimization problem that is becoming progressively more challenging. Although numerical computation-based iterative methods such as the minimal mean square error (MMSE) and the alternative manifold optimization (Alt-Min) can already attain near-optimal performance, their computational cost renders them unsuitable for real-time applications. However, recent studies have demonstrated that machine learning techniques like deep neural networks (DNN) can learn the mapping done by those algorithms between channel state information (CSI) and near-optimal resource allocation and then approximate this mapping in near real-time. In light of this, we investigate various DNN architectures for beamforming challenges in the terahertz (THz) band for ultra-massive multiple-input multiple-output (UM-MIMO) and explore their contextual mathematical modelling. Specifically, we design a sophisticated 1D convolutional neural network and long short-term memory (1D CNN-LSTM) based fusion-separation scheme, which can approach the performance of the Alt-Min algorithm in terms of spectral efficiency (SE) for fully connected structures and, at the same time, use significantly less computational effort. Simulation results indicate that the proposed system can attain almost the same level of SE as that of the numerical iterative algorithms while incurring a substantial reduction in computational cost. Our DNN-based approach also exhibits exceptional adaptability to diverse network setups and high scalability. Although the current model only addresses the fully connected hybrid architecture, our approach can also be expanded to address a variety of other beamforming topologies.https://ieeexplore.ieee.org/document/10098778/6GCNNhybrid beamformingLSTMUM-MIMO |
| spellingShingle | Rafid Umayer Murshed Zulqarnain Bin Ashraf Abu Horaira Hridhon Kumudu Munasinghe Abbas Jamalipour Md. Farhad Hossain A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming IEEE Access 6G CNN hybrid beamforming LSTM UM-MIMO |
| title | A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming |
| title_full | A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming |
| title_fullStr | A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming |
| title_full_unstemmed | A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming |
| title_short | A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming |
| title_sort | cnn lstm based fusion separation deep neural network for 6g ultra massive mimo hybrid beamforming |
| topic | 6G CNN hybrid beamforming LSTM UM-MIMO |
| url | https://ieeexplore.ieee.org/document/10098778/ |
| work_keys_str_mv | AT rafidumayermurshed acnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT zulqarnainbinashraf acnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT abuhorairahridhon acnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT kumudumunasinghe acnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT abbasjamalipour acnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT mdfarhadhossain acnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT rafidumayermurshed cnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT zulqarnainbinashraf cnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT abuhorairahridhon cnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT kumudumunasinghe cnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT abbasjamalipour cnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming AT mdfarhadhossain cnnlstmbasedfusionseparationdeepneuralnetworkfor6gultramassivemimohybridbeamforming |