Intelligent Anti-Jamming Decision With Continuous Action and State in Bivariate Frequency Agility Communication System

• DOI: 10.1109/tccn.2023.3306363
• Publication Date: 2023-08-18T17:25:48Z
• Authors: Yupei Zhang; Zhijin Zhao; Shilian Zheng; Fangfang Qiang
• Keywords: Frequency-hopping spread spectrum

The conventional frequency hopping (FH) system is susceptible to malicious jamming due the prearranged table. In this paper, we develop a bivariate agility (BFA) communication improve anti-jamming capability by assigning time-varying characteristics parameters such as fixed interval and rate in FH. Our goal find optimal strategy environment maximize signal-to-noise ratio (SINR). We formulate parameter decision problem Markov process (MDP). Then, propose deep deterministic policy gradient (DDPG) based algorithm for selection setting. addition, overcome shortcomings of DDPG, which prone fall into local optimum unstable convergence, an improved with weighted dual-prioritized experience replay periodically updated learning (IDDPG) proposed. IDDPG, on one hand, model trained replaying more experiences high immediate reward large temporal difference error (TD error) make it accurate. On other decayed so that update network varies periodically, resulting richer diverse exploration. simulation results under different electromagnetic indicates performance proposed two algorithms outperforms PPER-DQN RFH algorithm.