摘要
围绕空天地一体化战场信息采集场景,建立优化目标为最大化系统效率和性能的信道分配和设备匹配模型。针对信道分配和设备匹配决策变量具有相关和耦合性的特点,提出一种基于遗传算法和深度强化学习的两阶段资源分配(GD2A)算法。通过仿真验证,分析超参数对GD2A算法的性能和收敛速度的影响。对比实验表明,GD2A算法能在6G空天地异构网络中保障军事通信的可靠性和安全性,最大化系统效用。
Oriented to the space-air-ground integration battlefield information collection scenario,a channel allocation and device matching model with the optimixation objective of maximizing system fficiency and performance is established.There are correlation and coupling between channel allocation and device matching decision variables.In view of the characterstics,a two-stage resource allocation algorithm based on genetie algorithm and deep reinforcement learning algorithm(GD2A)is proposed.The flect of hyper-parameters on the performance and convergence rate of the GD2A algorithm is analyzed through simulation validation.Comparative experiments show that the GD2A algorithm ensures the reliability and security of military communications and maximizes the system utility in a 6G space-air-ground heterogeneous network.
作者
王易杰
陈昕
焦立博
朱文武
WANG Yijie;CHEN Xin;JIAO Libo;ZHU Wenwu(Beijing Information Science&Technology University,Beijing 100000,China)
出处
《电光与控制》
CSCD
北大核心
2024年第3期17-24,共8页
Electronics Optics & Control
基金
国家自然科学基金(62202059)。
关键词
战场信息采集
无人机
空天地一体化
深度强化学习
遗传算法
battlefield information collection
UAV
space-air-ground integration
deep reinforcement learning
genetic algorithm