TechRxiv
IEEE_Letter_V5_Adversarial Bandit Approach for Stand Alone RIS operation.pdf (444.31 kB)

Adversarial Bandit Approach for Stand Alone RIS Operation

Download (444.31 kB)
preprint
posted on 13.09.2021, 17:17 by messaoud Ahmed Ouameurmessaoud Ahmed Ouameur, Dương Tuấn Anh Lê, Gwanggil Jeon, Felipe A.P. De Figueiredo, Daniel Massicotte
Abstract— Even though, reconfigurable intelligent surfaces (RISs) are adopted in various scenarios to enable the implementation of a smart radio environment, there are still challenging issues for its real-time operation due to the need for a costly full dimensional channel estimation with offline exhaustive search or online exhaustive beamtraining. The application of the deep learning (DL) tools is favored to enable feasible solutions. In this work, we propose two low training overhead and energy efficient adversarial bandit-based schemes with outstanding performance gains compared to reference DL based reflection beamforming methods. The resulting deep learning models are also discussed using state of-the art model quality prediction trends.

History

Email Address of Submitting Author

messaoud.ahmed.ouameur@uqtr.ca

Submitting Author's Institution

Université du Québec à Trois-Rivières

Submitting Author's Country

Canada