Optimizing Age of Information Through Aerial Reconfigurable Intelligent Surfaces: A Deep Reinforcement Learning Approach

We investigate the benefits of integrating unmanned aerial vehicles (UAVs) with reconfigurable intelligent surface (RIS) elements to passively relay information sampled by Internet Things devices (IoTDs) base station (BS). In order maintain freshness relayed information, an optimization problem objective minimizing expected sum Age-of-Information (AoI) is formulated optimize altitude UAV, communication schedule, and phases-shift RIS elements. absence prior knowledge activation pattern IoTDs, proximal policy algorithm developed solve this mixed-integer non-convex problem. Numerical results show that our proposed outperforms all others in terms AoI.