Mobility-aware Hybrid EH for Self-Sustaining IoT Devices: A DRL-driven Opportunistic NOMA Framework

This paper presents a novel approach to maximizing the throughput of self-sustaining mobile IoT devices using a quality-of-service (QoS)-aware non-orthogonal multiple access (NOMA) technique. The proposed method enables transmissions within the timeslots of licensed users in IoT networks through a deep reinforcement learning (DRL)-driven strategy. By integrating hybrid energy harvesting (EH) from radio frequency (RF) and solar sources, the proposed framework is designed to optimize the energy usage and data transmission rates of a mobile sensing node (MSN) operating in a dynamic wireless environment. Our model incorporates non-linear RF and solar EH characteristics and accounts for mobility-induced variations in channel conditions. The throughput maximization problem is decomposed into a two-layer optimization framework, where the first layer utilizes convex optimization for power and time-sharing coefficients, while the second layer employs DRL to adapt to one-dimensional state-action spaces. Our results show that the Prioritized Experience Replay (PER)-DDPG algorithm achieves the best performance among the evaluated DRL approaches by enabling hybrid EH to achieve 7.83% higher data rates compared to RF-only scenarios. The results underscore the effectiveness of the DRL-based approach in enabling continuous operation and enhanced data rates for mobile IoT applications in QoS-aware NOMA IoT networks.