Deep Reinforcement Learning Based Intelligent Reflecting Surface Optimization for MISO Communication Systems
Top Cited Papers
- 24 January 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 9 (5), 745-749
- https://doi.org/10.1109/lwc.2020.2969167
Abstract
This letter investigates the intelligent reflecting surface (IRS)-aided multiple-input single-output wireless transmission system. Particularly, the optimization of the passive phase shift of each element at IRS to maximize the downlink received signal-to-noise ratio is considered. Inspired by the huge success of deep reinforcement learning (DRL) on resolving complicated control problems, we develop a DRL based framework to solve this non-convex optimization problem. Numerical results reveal that the proposed DRL based framework can achieve almost the upper bound of the received SNR with relatively low time consumption.Keywords
Funding Information
- National Natural Science Foundation of China (61971126, 61831013)
- Ministry of Science and Technology of Taiwan (MOST 108-2628-E-110-001-MY3)
This publication has 9 references indexed in Scilit:
- Towards Smart and Reconfigurable Environment: Intelligent Reflecting Surface Aided Wireless NetworkIEEE Communications Magazine, 2019
- Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent SurfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Large Intelligent Surface-Assisted Wireless Communication Exploiting Statistical CSIIEEE Transactions on Vehicular Technology, 2019
- Beamforming Optimization for Intelligent Reflecting Surface with Discrete Phase ShiftsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Programmable metasurface‐based RF chain‐free 8PSK wireless transmitterElectronics Letters, 2019
- Intelligent Reflecting Surface Enhanced Wireless Network: Joint Active and Passive Beamforming DesignPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Statistical 3-D Beamforming for Large-Scale MIMO Downlink Systems Over Rician Fading ChannelsIEEE Transactions on Communications, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Affective Learning — A ManifestoBT Technology Journal, 2004