Joint Antenna Position and Transmit Power Optimization for Pinching Antenna-Assisted ISAC Systems
Yunhui Qin, Yaru Fu, Haijun Zhang
TL;DR
The paper addresses joint optimization of pinching-antenna positions and transmit powers in ISAC systems to maximize total data rate while satisfying sensing SNR and energy constraints. It reformulates the problem as a sequential decision process and introduces a maximum entropy-based reinforcement learning (MERL) algorithm that augments the reward with policy entropy to promote robust exploration. The MERL framework uses a stochastic policy $\pi_{\phi}$, twin critics $Q_{\theta_1}, Q_{\theta_2}$, and soft Bellman updates, trained with experience replay to jointly optimize antenna placement and power allocation. Numerical results show MERL outperforms DDPG, TD3, and random baselines in cumulative reward, total data rate, and sensing SNR, demonstrating robust, scalable optimization for flexible pinching antennas in ISAC; the work also highlights potential extensions to NOMA-enabled ISAC and off-policy learning.
Abstract
This letter explores how pinching antennas, an advanced flexible-antenna system, can enhance the performance of integrated sensing and communication (ISAC) systems by leveraging their adaptability, cost-effectiveness, and ability to facilitate line-of-sight transmission. To achieve this, a joint antenna positioning and transmit power optimization problem is formulated to maximize the total communication data rate while meeting the target sensing requirements and the system energy constraint. To address the complex non-convex optimization problem, we propose a maximum entropy-based reinforcement learning (MERL) solution. By maximizing cumulative reward and policy entropy, this approach effectively balances exploration and exploitation to enhance robustness. Numerical results demonstrate that the proposed MERL algorithm surpasses other benchmark schemes in cumulative reward, total data rate, sensing signal-to-noise ratio, and stability.