智能感知辅助的快速动态频谱抗干扰方法

Intelligent Sensing Aided Fast Dynamic Spectrum Anti-Jamming Method

机器学习赋能的动态频谱抗干扰方法能够通过频谱感知学习干扰规律,自主优化抗干扰策略,适应动态复杂的频谱环境。然而,现有大部分研究假设环境中仅有恶意干扰而不考虑其他通信系统的存在,且所提算法复杂度和算力要求较高。针对以上问题,考虑主用户和恶意干扰同时存在且用频规律未知的场景,设计了基于并行学习的智能感知算法和基于预先学习的动态频谱接入算法,无须通过随机探索频谱环境即可学习可用信道变化规律。仿真结果表明,所提算法在动态干扰攻击下能在线快速找到最优信道选择策略,在完美避开动态干扰的同时不对主用户造成无意干扰。

Machine learning empowered dynamic spectrum anti-jamming method can learn jamming patterns through spectrum sensing and autonomously optimize anti-jamming strategies to adapt to dynamic and complex spectrum environments.However,most existing works assume that there is only malicious jamming and no other communication system exists,and the complexity and computing power requirement of the proposed algorithms are high.To address the above problems,this paper considers the scenario where primary users and jammers coexist with their spectrum use patterns unknown.Concurrent learningbased intelligent spectrum sensing algorithm and pre-learning-based dynamic spectrum access algorithm are designed to learn the changing patterns of available channels without randomly exploring the spectrum environment.Simulation results indicate that the proposed algorithm can find the optimal channel access strategy in a fast and online manner under dynamic jamming attacks,and avoid dynamic jamming perfectly without causing unintentional jamming to the primary users.