A Multi-Parameter Intelligent Communication Anti-Jamming Method Based on Three-Dimensional Q-Learning

Abstract

Aiming at the deficiency of the traditional intelligent communication anti-jamming algorithms, a multi-parameter intelligent anti-jamming method for wireless communication based on three-dimensional Q-learning (3DQL) is proposed. In the case of multi-channel random jamming, the wireless communication system guides the transmitter to choose the optimal channel and power for communication or keep silent in each timeslot by learning the random variation law of channel, timeslot and power of jamming, achieving the anti-jamming effect of optimal decision accuracy and timeslot utilization. Simulation results show that the 3DQL algorithm is better than the traditional two-dimensional Q-learning (2DQL) algorithm in decision accuracy and slot utilization.