Enhancing Secrecy in UAV RSMA Networks: Deep Unfolding Meets Deep Reinforcement Learning

TL;DR

This paper introduces a novel multiagent deep reinforcement learning framework that combines deep unfolding and DDPG to optimize secrecy rate in UAV RSMA networks through joint beamforming, rate allocation, and trajectory planning.

Contribution

It presents a new DUN-DRL framework integrating deep unfolding and DDPG for joint optimization in UAV RSMA networks, outperforming existing DRL methods.

Findings

DUN-DRL outperforms other DRL-based methods.

The framework effectively maximizes secrecy rate.

Joint optimization improves UAV network security.

Abstract

In this paper, we consider the maximization of the secrecy rate in multiple unmanned aerial vehicles (UAV) rate-splitting multiple access (RSMA) network. A joint beamforming, rate allocation, and UAV trajectory optimization problem is formulated which is nonconvex. Hence, the problem is transformed into a Markov decision problem and a novel multiagent deep reinforcement learning (DRL) framework is designed. The proposed framework (named DUN-DRL) combines deep unfolding to design beamforming and rate allocation, data-driven to design the UAV trajectory, and deep deterministic policy gradient (DDPG) for the learning procedure. The proposed DUN-DRL have shown great performance and outperformed other DRL-based methods in the literature.