Energy-Efficient UAV-Mounted RIS for IoT: A Hybrid Energy Harvesting and DRL Approach

Many future Internet of Things (IoT) applications are expected to rely on reconfigurable intelligent surface (RIS)-aided unmanned aerial vehicles (UAVs). However, their endurance is constrained by limited onboard energy, where frequent recharging or battery replacements disrupt continuous operation and may be impractical in disaster scenarios. To address this, we explore a dual energy harvesting (EH) framework that integrates time-switching (TS), power-splitting (PS), and element-splitting (ES) EH protocols for radio frequency energy, along with solar energy as a renewable source. We first present the system architecture and EH operating protocols, introducing a hybrid ES-TS-PS strategy to extend UAV-mounted RIS endurance. We then outline key application scenarios and design challenges. A deep reinforcement learning-based framework is proposed to maximize EH efficiency by jointly optimizing UAV trajectory, RIS phase shifts, and EH strategies. The framework accounts for dual EH, hardware impairments, and channel state information imperfections to reflect real-world deployment. The optimization problem is modeled as a Markov decision process and solved using an enhanced deep deterministic policy gradient algorithm with clipped double Q-learning and softmax-based Q-value estimation for improved stability and efficiency. Results demonstrate significant performance gains over baseline approaches. Finally, future challenges and research directions are discussed, highlighting the transformative potential of energy-efficient UAV-mounted RIS networks for IoT.