Self-supervised Contrastive Learning for 6G UM-MIMO THz Communications: Improving Robustness Under Imperfect CSI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910523486896128 |
|---|---|
| author | Murshed, Rafid Umayer Ullah, Md Saheed Saquib, Mohammad Win, Moe Z. |
| author_facet | Murshed, Rafid Umayer Ullah, Md Saheed Saquib, Mohammad Win, Moe Z. |
| contents | This paper investigates the potential of contrastive learning in 6G ultra-massive multiple-input multiple-output (UM-MIMO) communication systems, specifically focusing on hybrid beamforming under imperfect channel state information (CSI) conditions at THz. UM-MIMO systems are promising for future 6G wireless communication networks due to their high spectral efficiency and capacity. The accuracy of CSI significantly influences the performance of UM-MIMO systems. However, acquiring perfect CSI is challenging due to various practical constraints such as channel estimation errors, feedback delays, and hardware imperfections. To address this issue, we propose a novel self-supervised contrastive learning-based approach for hybrid beamforming, which is robust against imperfect CSI. We demonstrate the power of contrastive learning to tackle the challenges posed by imperfect CSI and show that our proposed method results in improved system performance in terms of achievable rate compared to traditional methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11376 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised Contrastive Learning for 6G UM-MIMO THz Communications: Improving Robustness Under Imperfect CSI Murshed, Rafid Umayer Ullah, Md Saheed Saquib, Mohammad Win, Moe Z. Signal Processing This paper investigates the potential of contrastive learning in 6G ultra-massive multiple-input multiple-output (UM-MIMO) communication systems, specifically focusing on hybrid beamforming under imperfect channel state information (CSI) conditions at THz. UM-MIMO systems are promising for future 6G wireless communication networks due to their high spectral efficiency and capacity. The accuracy of CSI significantly influences the performance of UM-MIMO systems. However, acquiring perfect CSI is challenging due to various practical constraints such as channel estimation errors, feedback delays, and hardware imperfections. To address this issue, we propose a novel self-supervised contrastive learning-based approach for hybrid beamforming, which is robust against imperfect CSI. We demonstrate the power of contrastive learning to tackle the challenges posed by imperfect CSI and show that our proposed method results in improved system performance in terms of achievable rate compared to traditional methods. |
| title | Self-supervised Contrastive Learning for 6G UM-MIMO THz Communications: Improving Robustness Under Imperfect CSI |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2401.11376 |