Abstract
This research investigates how deep learning might be used to optimize beamforming in wireless communication systems that are helped by Reconfigurable Intelligent Surfaces (RIS). Our goal is to increase the possible data rates by dynamically forecasting the best phase shifts for RIS elements by utilizing Convolutional Neural Networks (CNN) and hybrid CNN-Long Short-Term Memory (CNN-LSTM) models. We assess the performance of these deep learning models against conventional genie-aided techniques by simulating real-world wireless settings using the DeepMIMO dataset. The findings demonstrate that beamforming based on deep learning can reach near-optimal performance, greatly lowering the overhead associated with channel estimation while improving communication efficiency. In order to support the development of next-generation wireless networks like 5G and 6G, this study shows how deep learning approaches can be used to increase the effectiveness of RIS-assisted systems.
Recommended Citation
Jassim, Mohammed Firas; Mohammed, Alhamzah Taher; and Abdullah, Osamah
(2025)
"Deep Learning-Based Beamforming Optimization for Reconfigurable Intelligent Surface-Assisted Wireless Communication Systems,"
Iraqi Journal for Computer Science and Mathematics: Vol. 6:
Iss.
1, Article 7.
DOI: https://doi.org/10.52866/2788-7421.1233
Available at:
https://ijcsm.researchcommons.org/ijcsm/vol6/iss1/7
