Integrated Communication and Sensing Energy Efficiency Maximization in RSMA-Enabled UAV Networks

Unmanned aerial vehicle (UAV) is widely used to provide integrated sensing and communication (ISAC) services. With its flexible interference management capabilities and robustness to imperfect channel state information, rate splitting multiple access (RSMA) provides effective multiple access support and resource allocation for enabling ISAC in UAV systems. In this article, we tackle the challenge of maximizing the system energy efficiency (EE) while ensuring the quality of communication and sensing through a joint beamforming design, UAV trajectory design, and base station (BS) power optimization problem. As the problem is non-convex, we transform it into a markov decision process (MDP). To address the joint optimization problem involving beamforming design, UAV trajectory design, and power optimization, this paper uses the multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm to solve it. Simulation results demonstrate that the performance of the MATD3 algorithm in this paper is superior to that of other algorithms in maximizing EE.