Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2301.10963 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915153031725056 |
|---|---|
| author | Kyaw, Khin Thandar Santipach, Wiroonsak Mamat, Kritsada Kaemarungsi, Kamol Fukawa, Kazuhiko Wuttisittikulkij, Lunchakorn |
| author_facet | Kyaw, Khin Thandar Santipach, Wiroonsak Mamat, Kritsada Kaemarungsi, Kamol Fukawa, Kazuhiko Wuttisittikulkij, Lunchakorn |
| contents | We propose an unsupervised beamforming neural network (BNN) and a supervised reconfigurable intelligent surface (RIS) convolutional neural network (CNN) to optimize transmit beamforming and RIS coefficients of multi-input single-output (MISO) downlink with RIS assistance. To avoid frequent beam updates, the proposed BNN and RIS CNN are based on slow-changing channel covariances and are different from most other neural networks that utilize channel instances. Numerical simulations show that the proposed BNN with RIS CNN can achieve much higher sum rates than zeroforcing beamforming with waterfilling power allocation does, especially for systems with higher load, and reduces computation time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_10963 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink Kyaw, Khin Thandar Santipach, Wiroonsak Mamat, Kritsada Kaemarungsi, Kamol Fukawa, Kazuhiko Wuttisittikulkij, Lunchakorn Information Theory Signal Processing We propose an unsupervised beamforming neural network (BNN) and a supervised reconfigurable intelligent surface (RIS) convolutional neural network (CNN) to optimize transmit beamforming and RIS coefficients of multi-input single-output (MISO) downlink with RIS assistance. To avoid frequent beam updates, the proposed BNN and RIS CNN are based on slow-changing channel covariances and are different from most other neural networks that utilize channel instances. Numerical simulations show that the proposed BNN with RIS CNN can achieve much higher sum rates than zeroforcing beamforming with waterfilling power allocation does, especially for systems with higher load, and reduces computation time. |
| title | Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink |
| topic | Information Theory Signal Processing |
| url | https://arxiv.org/abs/2301.10963 |