Design of Intelligent Frequency Hopping Anti Continuous Change Jamming System Based on Migration Learning

This paper proposes a migration learning-based design model for an intelligent FH anti continuous change jamming system. To be able to withstand ongoing changes in linear sweep jamming and random periodic jamming, this model builds on the existing reinforcement learning frequency hopping anti-jamming method and adds the idea of migration learning to it. The core point behind this algorithm model is that the anti-jamming party will restart the learning and training system and continue to optimize the training on the current basis when it notices that the communication quality has decreased as a result of jamming in order to maintain the communication quality at a high level for an extended period of time. The jamming party may also change frequently in the actual situation, thus the anti-jamming party must be able to adjust to these changes. This is the more practical significance of the algorithm model.