Scholarlink

<p>In complex electromagnetic jamming environments, achieving reliable communication and efficient data collection in UAV swarms requires dynamic and adaptive solutions for distributed deployment optimization and intelligent anti-jamming carrier selection. This paper proposes a game-theoretic optimization framework that simultaneously addresses the above challenges by maximizing data collection volume while minimizing weighted aggregate interference and jamming (WAIJ). This framework comprises two interconnected parts. First, the UAV deployment problem is formulated as a congestion game, where distributed position adjustments are strategically made to increase the swarm’s total data collection capability. This game model is proven to be an exact potential game (EPG) theoretically, guaranteeing the existence of pure-strategy Nash equilibrium. Second, a hierarchical Stackelberg game is constructed for carrier selection, where jammers as leaders employ Q-learning based jamming strategies, while UAVs as followers utilize federated learning for dynamic carrier decision-making. This dual-learning framework enables rapid and robust adaptation to jamming conditions. Simulation results demonstrate that the proposed framework significantly outperforms existing methods in both data collection efficiency and anti-jamming performance, offering an efficient solution for UAV swarm operations in complex electromagnetic environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

UAV Deployment Optimization and Carrier Selection in Jamming Environments: A Game Learning Approach

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Han Liao,
  • Wanyu Xiang,
  • Yusi Zhang,
  • Yifu Sun,
  • Chen Han,
  • Yusheng Li

摘要

In complex electromagnetic jamming environments, achieving reliable communication and efficient data collection in UAV swarms requires dynamic and adaptive solutions for distributed deployment optimization and intelligent anti-jamming carrier selection. This paper proposes a game-theoretic optimization framework that simultaneously addresses the above challenges by maximizing data collection volume while minimizing weighted aggregate interference and jamming (WAIJ). This framework comprises two interconnected parts. First, the UAV deployment problem is formulated as a congestion game, where distributed position adjustments are strategically made to increase the swarm’s total data collection capability. This game model is proven to be an exact potential game (EPG) theoretically, guaranteeing the existence of pure-strategy Nash equilibrium. Second, a hierarchical Stackelberg game is constructed for carrier selection, where jammers as leaders employ Q-learning based jamming strategies, while UAVs as followers utilize federated learning for dynamic carrier decision-making. This dual-learning framework enables rapid and robust adaptation to jamming conditions. Simulation results demonstrate that the proposed framework significantly outperforms existing methods in both data collection efficiency and anti-jamming performance, offering an efficient solution for UAV swarm operations in complex electromagnetic environments.