RIS partitioning and UAV selection for age-of-information optimization in RIS-assisted UAV communications

Abstract

Reconfigurable intelligent surface (RIS) has been attracted great attention because it can enhance the capacity and coverage of wireless communication systems. However, when applying RIS to an unmanned aerial vehicle (UAV) networks, it is necessary to manage the RIS reflection elements and UAV scheduling in the BS-RIS-UAVs link. This paper proposes a deep reinforcement learning (DRL)-based resource allocation scheme for jointly determining the number of serving UAVs and their partition-based RIS allocation, aiming to minimize the age of information (AoI). Simulation results show that the proposed DRL-based joint UAV selection and partition-based RIS allocation scheme outperforms all the other schemes without joint optimization in terms of the average AoI.