面向可移动天线安全通感系统的智能天线定位和波束赋形OA

Integrated Sensing and Communication(ISAC)systems,by sharing spectrum and hardware resources,enable wireless networks to perform both communication and sensing functions,significantly improving spectrum efficiency and resource utilization.However,communication signals embedded in sensing signals are also at risk of interception by eavesdroppers.Therefore,resource allocation and interference management for ISAC in various 6G scenarios have drawn significant attention.In response,a secure ISAC architecture enabled by movable antennas is proposed,with antenna positioning and beamforming optimization addressed from both antenna structure and optimization algorithm perspectives.Specifically,a gradient-based meta-learning optimization algorithm is proposed for antenna positioning and beamforming.This algorithm constructs a neural network for each optimization variable,with the gradient of the objective function with respect to the optimization variable as the network input,and the network output as the update step size.The meta-learning strategy allows the algorithm to adapt to various scenarios.Numerical simulations are conducted to compare the proposed optimization algorithm with other baseline algorithms.Results show that the proposed algorithm outperforms the baseline algorithms in both communication and target sensing performance,demonstrating its superiority.