Scholarlink

To address the challenge of balancing low observability, communication quality, and anti-surveillance capabilities in unmanned aerial vehicle (UAV)-assisted low observable Communication under dynamic game environments, this study proposes a dynamic co-optimization framework integrating game theory and an improved genetic algorithm (IGA). A non-cooperative game model is first established between the communication party and the surveillance party, where Nash equilibrium is employed to update the probability distributions of surveillance strategies. Subsequently, an IGA is designed with an adaptive weighting mechanism based on fuzzy cognitive maps and the entropy weight method. This mechanism dynamically adjusts optimization objective weights according to threat levels, channel quality, and data priority. Finally, the path planning is iteratively optimized through alternating interactions between the Game Theory (GT) and the IGA. Experimental results demonstrate that the proposed method achieves superior performance in median observability probability (0.15) and stability (IQR = 0.08) compared to baseline approaches (GA + GT: 0.24, IQR = 0.12; IGA-StaticOP:0.33, IQR = 0.14;GA:0.47, IQR = 0.15; GT-StaticPath:0.45, IQR = 0.12), validating the effectiveness of the dynamic coupling mechanism in resolving multi-objective conflicts while enhancing adaptability and security in UAV path planning.

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

Optimization for Low-Observability UAV-Assisted Communications Based on Game-Evolution Coupling

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Li Tianyu,
  • Liu Jintao,
  • Liu Weihua

摘要

To address the challenge of balancing low observability, communication quality, and anti-surveillance capabilities in unmanned aerial vehicle (UAV)-assisted low observable Communication under dynamic game environments, this study proposes a dynamic co-optimization framework integrating game theory and an improved genetic algorithm (IGA). A non-cooperative game model is first established between the communication party and the surveillance party, where Nash equilibrium is employed to update the probability distributions of surveillance strategies. Subsequently, an IGA is designed with an adaptive weighting mechanism based on fuzzy cognitive maps and the entropy weight method. This mechanism dynamically adjusts optimization objective weights according to threat levels, channel quality, and data priority. Finally, the path planning is iteratively optimized through alternating interactions between the Game Theory (GT) and the IGA. Experimental results demonstrate that the proposed method achieves superior performance in median observability probability (0.15) and stability (IQR = 0.08) compared to baseline approaches (GA + GT: 0.24, IQR = 0.12; IGA-StaticOP:0.33, IQR = 0.14;GA:0.47, IQR = 0.15; GT-StaticPath:0.45, IQR = 0.12), validating the effectiveness of the dynamic coupling mechanism in resolving multi-objective conflicts while enhancing adaptability and security in UAV path planning.