Reconfigurable Intelligent Surface-assisted Multi-UAV Networks: Efficient Resource Allocation with Deep Reinforcement Learning

TL;DR

This paper introduces RIS-assisted UAV networks and employs deep reinforcement learning to optimize energy efficiency through joint power and phase-shift control, enabling real-time adaptive network management.

Contribution

It presents a novel DRL-based framework for joint resource optimization in RIS-assisted UAV networks, including a parallel learning approach to reduce communication overhead.

Findings

Significant EE improvement over conventional methods

Enhanced network flexibility and adaptability

Reduced processing time with proposed DRL schemes

Abstract

In this paper, we propose reconfigurable intelligent surface (RIS)-assisted unmanned aerial vehicles (UAVs) networks that can utilise both advantages of UAV's agility and RIS's reflection for enhancing the network's performance. To aim at maximising the energy efficiency (EE) of the considered networks, we jointly optimise the power allocation of the UAVs and the phase-shift matrix of the RIS. A deep reinforcement learning (DRL) approach is proposed for solving the continuous optimisation problem with time-varying channels in a centralised fashion. Moreover, a parallel learning approach is also proposed for reducing the information transmission requirement of the centralised approach. Numerical results show a significant improvement of our proposed schemes compared with the conventional approaches in terms of EE, flexibility, and processing time. Our proposed DRL methods for RIS-assisted UAV networks can be used for real-time applications due to their capability of instant decision-making and handling the time-varying channel with the dynamic environmental setting.