Anti-jamming Algorithm with Reinforcement Learning in UAV-Aided Internet of Things

The Internet of Things (IoTs) node can transmit messages aided by unmanned aerial vehicle (UAV) who acts as the relay node, which are vulnerable to be attacked, such as the Jammer who can change the interference intensity randomly. A Stackelberg game of attack and defense anti-jammer was proposed in this thesis, the IoTs node, UAV and Jammer were the three players in the game, and the Stackelberg equilibriums (SEs) and its existence condition were derived, the influence of channel gain, distance and other parameters on the utility of IoTs were revealed. The Wolf-PHC was used to dynamically optimize the transmit of the IoTs node and the UAV and the moving trajectory of the UAV unknown the interference model. The simulation results show that the proposed anti-jamming algorithm increases the utility of UAV by 84.8% compared with the algorithm based Q-learning.