UAV-Aided Cellular Communications with Deep Reinforcement Learning Against Jamming

Cellular systems have to resist smart jammers that can optimize their selection of jamming channels and powers based on the estimated ongoing network states. In this article, we present an unmanned aerial vehicle (UAV) aided cellular framework against jamming, in which an UAV uses reinforcement learning to choose the relay policy for a mobile user whose serving base station is attacked by a jammer. More specifically, the UAV applies deep reinforcement learning and transfer learning to help cellular systems resist smart jamming without knowing the cellular topology, the message generation model, the server computation model and the jamming model, based on the previous anti-jamming relay experiences and the observed current communication status. The performance bound in terms of the bit error rate and the UAV energy consumption is derived from the Nash equilibrium of the studied dynamic relay game and verified via simulations. Simulation results show that this scheme can reduce the bit error rate and save the UAV energy consumption in comparison with the benchmark.