Improved Spectral Efficiency of RIS-aided 6G Communication using Deep Learning
Authors:
- 17 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 175-179
Abstract
Due to uncontrollable interactions of the transmitted signal with the adjacent objects, which diminish the quality of the received signal, wireless signal designers have adopted Reconfigurable Intelligent Surface (RIS) to overcome this challenge. The possibility of suitably designing phase shifts applied by each reflecting element, has made the RIS attractive technology. This capability conduces to gainful combination of each reflected signal and thus higher spectral efficiency, without any power amplifier. Motivated by the potential of deep learning (DL), the present article is aimed to propose a neural network for passive beamforming design of RIS-assisted systems in 6G wireless communication. DL-based beamformer indeed try to maximize the spectral efficiency(SE). Simulation results signify the superb SE enhancement in low signal to noise ratio (SNR) with the use of DL-based approach.Keywords
This publication has 22 references indexed in Scilit:
- Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive BeamformingIEEE Transactions on Wireless Communications, 2019
- Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless CommunicationIEEE Transactions on Wireless Communications, 2019
- Beamforming Optimization for Intelligent Reflecting Surface with Discrete Phase Shifts2019
- Mobile Encrypted Traffic Classification Using Deep Learning: Experimental Evaluation, Lessons Learned, and ChallengesIEEE Transactions on Network and Service Management, 2019
- Intelligent Reflecting Surface Enhanced Wireless Network: Joint Active and Passive Beamforming Design2018
- Achievable Rate Maximization by Passive Intelligent Mirrors2018
- Deep Learning for Massive MIMO CSI FeedbackIEEE Wireless Communications Letters, 2018
- Deep Learning Based Communication Over the AirIEEE Journal of Selected Topics in Signal Processing, 2017
- Power of Deep Learning for Channel Estimation and Signal Detection in OFDM SystemsIEEE Wireless Communications Letters, 2017
- Learning to optimize: Training deep neural networks for wireless resource management2017