ARIS for Safeguarding MISO Wireless Communications: A Deep Reinforcement Learning Approach
Abstract
This paper discusses the problem of securing the transmissions of a ground user against aerial eavesdropping attacks. We propose and optimize the deployment of an aerial reconfigurable intelligent surface (ARIS) mounted on an unmanned aerial vehicle (UAV). The focus is on maximizing the average secrecy rate of the cellular multi-user downlink by jointly optimizing the position and phase shifts of the ARIS. The joint optimization problem is non-convex; therefore we propose an artificial intelligence algorithm based on deep reinforcement learning to solve it. Simulation results demonstrate that the proposed ARIS can effectively safeguard legitimate transmissions in the presence of an aerial eavesdropper.
Metrics
Citation History
Topics
Related Documents
RIS-Assisted ABS for Mobile Multi-User MISO Wireless Communications: A Deep Reinforcement Learning Approach
Walaa AlQwiderAly Sabri AbdallaVuk Marojevic
Three-Dimensional Trajectory Design for Multi-User MISO UAV Communications: A Deep Reinforcement Learning Approach
Resource Allocation for Multi-Active-RIS assisted MISO Communications via Deep Reinforcement Learning
An Overview of Intelligent Wireless Communications using Deep Reinforcement Learning
Yongming HuangChunmei XuCheng ZhangMeng HuaZhengming Zhang