In this paper, we combine the network-assisted full-duplex (NAFD) technology and distributed radar sensing to implement integrated sensing and communication (ISAC). The ISAC system features both uplink and downlink remote radio units (RRUs) equipped with communication and sensing capabilities. We evaluate the communication and sensing performance of the system using the sum communication rates and the Cramer-Rao lower bound (CRLB), respectively. We compare the performance of the proposed scheme with other ISAC schemes, the result shows that the proposed scheme can provide more stable sensing and better communication performance. Furthermore, we propose two power allocation algorithms to optimize the communication and sensing performance jointly. One algorithm is based on the deep Q-network (DQN) and the other one is based on the non-dominated sorting genetic algorithm II (NSGA-II). The proposed algorithms provide more feasible solutions and achieve better system performance than the equal power allocation algorithm.

翻译：本文融合网络辅助全双工（NAFD）技术与分布式雷达感知，实现了集成感知与通信（ISAC）。该ISAC系统的上下行远端射频单元（RRU）均具备通信与感知能力。我们分别利用通信总速率和克拉美-罗下界（CRLB）评估系统的通信与感知性能。将所提方案与其他ISAC方案进行对比，结果表明所提方案能提供更稳定的感知性能与更优的通信性能。此外，我们提出两种功率分配算法以联合优化通信与感知性能：一种基于深度Q网络（DQN），另一种基于非支配排序遗传算法II（NSGA-II）。与等功率分配算法相比，所提算法可实现更多可行解并取得更优的系统性能。