DRL-Enhanced QoS-Aware NOMA for Ambient IoT: Resource Allocation Optimization With RIS and RF Energy Harvesting Diversity

In the emerging field of ambient Internet-of-things (A-IoT), a new frontier driven by the need for sustainable, low-power, and energy-efficient communication solutions is paramount. This evolution is embodied in A-IoT, where innovative approaches are essential to meet the growing demands of interconnected devices. One such transformative technique is the integration of quality-of-service (QoS)–aware non-orthogonal multiple access (NOMA) schemes with deep reinforcement learning (DRL), reconfigurable intelligent surfaces (RIS), and radio-frequency energy harvesting (RF-EH) diversity. In this article, we propose how these combined technologies can maximize through-put for low-power IoT devices. Beginning with an overview of the foundational concepts of NOMA, DRL, RIS, and RF-EH, we demonstrate how their synergy can dynamically optimize resource allocation while maximizing throughput. Through illustrative use cases and extensive simulations, we reveal that our proposed scheme significantly enhances both data rate and EH compared to traditional methods. The article also discusses the potential applications and practical implications of this approach, paving the way for the future of near-zero energy IoT networks. Finally, we identify key research challenges and opportunities for realizing scalable and efficient A-IoT systems that leverage these advanced technologies.