Intelligent Anti-Jamming Relay Communication System Based on Reinforcement Learning
Zixuan Zhang, Qinhao Wu, Bo Zhang, Jinlin Peng · 2019
Frequency hopping communication and spread spectrum communication are the common means of anti-jamming, and these means have their own limitations. In the case of unpredictable jamming, reinforcement learning algorithm can provide good guidance for communication frequency. Firstly, this paper introduces the framework of communication system and the jamming modes commonly used in communication. Then the basic principle of Q-Learning algorithm is briefly introduced. Meanwhile, the meanings of the parameters in the algorithm are explained. In the part of numerical simulation, different jamming modes are used to test the performance of the algorithm. It proves that Q-Learning algorithm has good memory in sweeping, sinusoidal and Gaussian random jamming. It can provide better policy for communication frequency in real time.