Deep Reinforcement Learning Based Hopping Strategy for Wideband Anti-Jamming Wireless Communications

Abstract

Frequency hopping has been proved to be effective against radio jamming attacks in wireless communications. In this article, deep reinforcement learning algorithm is applied for providing frequency hopping strategies against jamming attacks in wideband communication systems. We first model the frequency hopping communication system in a dynamic jamming environment, where a two-dimensional pattern with a certain number of time slots and channels are formulated. In particular, a jammer using multi-channel blocking jamming is considered, where the some frequency bands are attacked via probabilistic jamming patterns. In this case, an intelligent frequency hopping strategy is desired, especially when perfect knowledge of the jamming patterns is not known at the transmitter and receiver sides. In order to tackle this issue, the interaction between the users and the jammer are modeled as a Markov decision process and a deep Q-learning algorithm is proposed to solve the frequency hopping decision making problem. Finally, the system performance is evaluated by simulations. Our simulation results have shown that in comparison to Q-learning assisted frequency hopping strategy, the proposed deep Q-learning assisted frequency hopping strategy is capable of attaining a better anti-jamming performance, especially for a large number of frequency bands and long transmission time. Furthermore, the proposed deep Q-learning assisted frequency hopping strategy is able to provide robust anti-jamming performance when jamming patterns are unknown.