Opponent’s Dynamic Prediction Model-Based Power Control Scheme in Secure Transmission and Smart Jamming Game
Haozhi Wang, Qing Wang, Qi Chen · IEEE Internet of Things Journal · 2023
In this article, we propose a novel power control scheme for secure transmission and smart jamming game to solve the problem of the decline of anti-jamming performance due to the unknown behavior of the opponent. By exploring recursive reasoning principles and reinforcement learning approaches, we design a high-performance framework for predicting the opponent’s power strategies in dynamic wireless environments. The proposed framework consists of two parts: 1) we develop a game model considering the opponent’s dynamic to characterize the jamming/anti-jamming confrontation and 2) we propose a jamming and anti-jamming policy recursive reasoning (JPR2) algorithm for power control based on reinforcement learning, where the opponent’s dynamic prediction model is learned through variational inference from the transmitter and jammer’s observation history. In addition, we optimize the policy considering the opponent’s dynamic prediction to maximize both parties’ utility functions and achieve their optimal power control strategies. More elaborately, we theoretically guarantee the algorithm’s convergence to the Nash equilibrium of the game. Our experiments show that the proposed algorithm significantly improves the performance of both parties.