Deep Reinforcement Learning-Based Anti-Jamming Approach for Fast Frequency Hopping Systems

Abstract

Increasing the hopping frequency speed and integrating artificial intelligence (AI) technologies are currently two of the most effective strategies for enhancing the anti-jamming performance of frequency hopping (FH) systems. However, due to the complexity of the decision-making process in intelligent agents, the system cannot complete decisions within the intervals between hops in fast frequency hopping (FFH) systems. As a result, there is no existing strategy for directly applying AI technologies to FFH systems. In this work, we introduce the concept of the available frequency set (AFS) and apply deep reinforcement learning (DRL) methods to FFH systems, enabling them to retain their inherent advantages while also gaining adaptability to dynamic environments. Building on this, we propose an improved multi-action deep recurrent Q-network (MA-DRQN) algorithm to determine the AFS for hopping sequence generation. Finally, the proposed method is shown to outperform both traditional FFH systems and advanced intelligent FH systems in handling passive and active jammers. Moreover, the hopping sequences generated based on AFS exhibit strong unpredictability.