DRL下UAV辅助认知无线电网络资源优化研究

Resource Optimization in UAV-Assisted Cognitive Ratio Network Under DRL

认知无线电和能量收集技术为解决频谱利用率低和电池受限的问题提供了思路。为解决来自窃听者的安全威胁所导致的信息泄露问题,本文研究应用无人机协同干扰来增强多用户的物理层安全,以最大化安全速率。在底层模式下UAV辅助的能量采集认知无线电系统中,采用多智能体近端策略优化算法,结合长短期记忆网络增强序列样本数据的学习能力,提高算法的训练效率和有效性。仿真结果验证了所提方法的有效性和扩展性。

Cognitive radio and energy harvesting technologies provide ideas for solving the problems of low spectrum utilization and battery limitations.To address the issue of information leakage caused by security threats from eavesdroppers,this paper studies the application of drone collaborative interference to enhance the physical layer security of multiple users,in order to maximize security rate.In the energy harvesting cognitive radio system assisted by UAV in the underlying mode,a multi-agent proximal strategy optimization algorithm is adopted,combined with a long short-term memory network to enhance the learning ability of sequence sample data and improve the training efficiency and effectiveness of the algorithm.The simulation results have verified the effectiveness and scalability of the proposed method.