Data collection in deep reinforcement learning-enhanced reconfigurable intelligent surface-assisted wireless networks

In the evolving sixth generation (6G) landscape, the integration of reconfigurable intelligent surfaces (RIS) with unmanned aerial vehicles (UAVs) offers a revolutionary opportunity to optimize data collection in the Internet of things (IoT) through deep reinforcement learning (DRL) and improve energy efficiency and network performance. This paper aims to study how reconfigurable intelligent surfaces and deep reinforcement learning can help increase throughput and energy efficiency in unmanned aerial vehicle-controlled Internet of things networks. The focus is on improving the capabilities of unmanned aerial vehicles to efficiently collect data in different regions and ensure safe landings. Divided into two phases, the study first improves the directional capacity and flexibility of unmanned aerial vehicles and then evaluates the integration of reconfigurable intelligent surface technology. We introduce two deep reinforcement learning models, namely the directional capacity and flexible reconnaissance (DCFR) model and the reconfigurable intelligent surface model, and compare them with a benchmark model. We found significant improvements in communication and data collection efficiency. The simulation results show an 8.18% increase in data collection performance and a 6.92% increase in collected data per unit energy when using reconfigurable intelligent surfaces, with a 10.59% increase in collection performance and a 22.64% increase in energy efficiency. Furthermore, an unmanned aerial vehicle optimized with the double deep Q-network algorithm effectively identified optimal trajectories for data collection, confirming the significant benefits of reconfigurable intelligent surfaces in unmanned aerial vehicle-controlled Internet of things networks.