https://github.com/khinthandarkyaw98/optimization-of-transmit-beamforming-and-ris-coefficients-using-channel-covariances-in-miso-downlink

Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink
https://github.com/khinthandarkyaw98/optimization-of-transmit-beamforming-and-ris-coefficients-using-channel-covariances-in-miso-downlink

cvxpy neural-networks numpy optimization pydot python reconfigurable-intelligent-surfaces scipy semidefinite-programming tensorflow wireless-communication

Last synced: about 2 months ago
JSON representation

Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink

• Host: GitHub
• URL: https://github.com/khinthandarkyaw98/optimization-of-transmit-beamforming-and-ris-coefficients-using-channel-covariances-in-miso-downlink
• Owner: khinthandarkyaw98
• Created: 2024-09-18T14:44:55.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2025-01-04T14:37:30.000Z (about 2 months ago)
• Last Synced: 2025-01-04T15:25:17.271Z (about 2 months ago)
• Topics: cvxpy, neural-networks, numpy, optimization, pydot, python, reconfigurable-intelligent-surfaces, scipy, semidefinite-programming, tensorflow, wireless-communication
• Language: Python
• Homepage:
• Size: 3.54 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# [Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink](https://doi.org/10.1016/j.aeue.2024.155656)

Authors: Khin Thandar Kyaw, Wiroonsak Santipacha, Kritsada Mamat, Kamol Kaemarungsi, Kazuhiko Fukawa, Lunchakorn Wuttisittikulkij

## Citation

```

@article{KYAW2025155656,

title = {Neural network based optimization of transmit beamforming and RIS coefficients using channel covariances in MISO downlink},

journal = {AEU - International Journal of Electronics and Communications},

volume = {191},

pages = {155656},

year = {2025},

issn = {1434-8411},

doi = {https://doi.org/10.1016/j.aeue.2024.155656},

url = {https://www.sciencedirect.com/science/article/pii/S1434841124005429},

author = {Khin Thandar Kyaw and Wiroonsak Santipach and Kritsada Mamat and Kamol Kaemarungsi and Kazuhiko Fukawa and Lunchakorn Wuttisittikulkij},

keywords = {Beamforming, Optimization, Downlink, RIS, Channel covariance, MISO, Neural network, Unsupervised learning, Supervised learning},

}

```

---



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 for a small or moderate signal-to-noise ratio (SNR), the proposed BNN with RIS CNN can achieve a sum rate close to that of a system with optimal beams and RIS coefficients. Furthermore, the proposed scheme significantly reduces the computation time.



---

## System Model



    



## Implementation

Please refer the [paper](https://doi.org/10.1016/j.aeue.2024.155656) for implementation details.

## Numerical Results