Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems
We propose a deep learning-based cross-layer power allocation method for asymmetric cell-free massive MIMO video communication systems. The proposed cross-layer approach considers physical layer channel state information (CSI) and the application layer rate distortion (RD) function, and it aims to e...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/15/11/1968 |
| _version_ | 1797457696414236672 |
|---|---|
| author | Wen-Yen Lin Tin-Hao Chang Shu-Ming Tseng |
| author_facet | Wen-Yen Lin Tin-Hao Chang Shu-Ming Tseng |
| author_sort | Wen-Yen Lin |
| collection | DOAJ |
| description | We propose a deep learning-based cross-layer power allocation method for asymmetric cell-free massive MIMO video communication systems. The proposed cross-layer approach considers physical layer channel state information (CSI) and the application layer rate distortion (RD) function, and it aims to enhance video quality in terms of peak signal-to-noise ratio (PSNR). Our study develops a decentralized deep neural network (DNN) model to capture intricate system patterns, enabling accurate and efficient power allocation decisions. The proposed cross-layer approach includes unsupervised and hybrid (supervised/unsupervised) learning models. The numerical results show that the hybrid method achieves convergence with just 50% of the iterations required by the unsupervised learning model and that it achieves a 1 dB gain in PSNR over the baseline physical layer scheme. |
| first_indexed | 2024-03-09T16:25:42Z |
| format | Article |
| id | doaj.art-8784aedeccdd4dbfaca73f015901a655 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T16:25:42Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-8784aedeccdd4dbfaca73f015901a6552023-11-24T15:08:34ZengMDPI AGSymmetry2073-89942023-10-011511196810.3390/sym15111968Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication SystemsWen-Yen Lin0Tin-Hao Chang1Shu-Ming Tseng2Department of Information Management, National Taichung University of Science and Technology, Taichung 404, TaiwanFun Learn Tech Enterprise, Taipei 100, TaiwanDepartment of Electronic Engineering, National Taipei University of Technology, Taipei 106, TaiwanWe propose a deep learning-based cross-layer power allocation method for asymmetric cell-free massive MIMO video communication systems. The proposed cross-layer approach considers physical layer channel state information (CSI) and the application layer rate distortion (RD) function, and it aims to enhance video quality in terms of peak signal-to-noise ratio (PSNR). Our study develops a decentralized deep neural network (DNN) model to capture intricate system patterns, enabling accurate and efficient power allocation decisions. The proposed cross-layer approach includes unsupervised and hybrid (supervised/unsupervised) learning models. The numerical results show that the hybrid method achieves convergence with just 50% of the iterations required by the unsupervised learning model and that it achieves a 1 dB gain in PSNR over the baseline physical layer scheme.https://www.mdpi.com/2073-8994/15/11/1968cell-freemassive MIMOpower allocationdeep neural networkpeak signal-to-noise ratio (PSNR)video quality |
| spellingShingle | Wen-Yen Lin Tin-Hao Chang Shu-Ming Tseng Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems Symmetry cell-free massive MIMO power allocation deep neural network peak signal-to-noise ratio (PSNR) video quality |
| title | Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems |
| title_full | Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems |
| title_fullStr | Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems |
| title_full_unstemmed | Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems |
| title_short | Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems |
| title_sort | deep learning based cross layer power allocation for downlink cell free massive multiple input multiple output video communication systems |
| topic | cell-free massive MIMO power allocation deep neural network peak signal-to-noise ratio (PSNR) video quality |
| url | https://www.mdpi.com/2073-8994/15/11/1968 |
| work_keys_str_mv | AT wenyenlin deeplearningbasedcrosslayerpowerallocationfordownlinkcellfreemassivemultipleinputmultipleoutputvideocommunicationsystems AT tinhaochang deeplearningbasedcrosslayerpowerallocationfordownlinkcellfreemassivemultipleinputmultipleoutputvideocommunicationsystems AT shumingtseng deeplearningbasedcrosslayerpowerallocationfordownlinkcellfreemassivemultipleinputmultipleoutputvideocommunicationsystems |