Meta-Reinforcement Learning Optimization for Movable Antenna-aided Full-Duplex CF-DFRC Systems with Carrier Frequency Offset

TL;DR

This paper introduces a meta-reinforcement learning approach to optimize movable antennas in a dual-functional radar-communication system, effectively mitigating carrier frequency offset effects and enhancing spectrum efficiency in 6G networks.

Contribution

It proposes a novel MRL-based optimization framework for joint antenna positioning, beamforming, and CFO mitigation in wideband CF-DFRC systems, addressing non-convex challenges.

Findings

MRL outperforms traditional DRL in CFO-robust scenarios

Movable antennas improve spectrum efficiency and sensing accuracy

Proposed method enhances system performance under CFO impairments

Abstract

By enabling spectrum sharing between radar and communication operations, the cell-free dual-functional radar-communication (CF-DFRC) system is a promising candidate to significantly improve spectrum efficiency in future sixth-generation (6G) wireless networks. However, in wideband scenarios, synchronization errors caused by carrier frequency offset (CFO) can severely reduce both communication capacity and sensing accuracy. To address this challenge, this paper integrates movable antennas (MAs) into the CF-DFRC framework, leveraging their spatial flexibility and adaptive beamforming to dynamically mitigate CFO-induced impairments. To fully exploit the advantages of MAs in wideband scenarios with CFO, we aim to maximize the worst-case sum-rate of communication and sensing by jointly optimizing MA positions, {beamforming}, and CFO parameters, subject to transmit power and MA positioning constraints. Due to the non-convex nature of the problem, we propose a robust meta reinforcement learning (MRL)-based two-stage alternating optimization strategy. In the first stage, we employ manifold optimization (MO) with penalty dual decomposition (PDD) to solve the CFO-robust worst-case subproblem. In the second stage, we adopt to jointly optimize {the MA positions and beamforming vectors} in a data-driven manner {for dynamic wireless environments}. Simulation results show that the proposed MRL approach significantly outperforms conventional deep reinforcement learning (DRL) schemes in both communication and sensing performance under CFO impairments. Furthermore, compared to fixed-position antennas (FPAs), the MA-aided CF-DFRC system exhibits