A novel intelligent anti-jamming communication algorithm based on proximal policy optimization

With the increasing complexity of the electromagnetic environment, the traditional communication anti-jamming technology has been difficult to effectively resist various high-dynamic intelligent jamming threats. However, this paper addresses the emerging threat issues posed by high-dynamic intelligent jamming and proposes an intelligent anti-jamming communication algorithm based on proximal policy optimization (PPO). First, the communication immunity problem under high-dynamic jamming is modeled as a multi-parameter markov decision process (MDP). Then, the optimal joint anti-jamming strategy for the system's channel, time slot, transmission rate, and transmit power is obtained by solving with the proximal policy optimization algorithm. This approach enhances the convergence speed of the algorithm and reduces the time required to reach an optimal strategy. The simulation results demonstrate that the proposed algorithm effectively adjusts multiple communication parameters simultaneously, exhibiting superior statistical average packet receive ratio and convergence speed compared to existing anti-jamming communication methods based on Q-learning and DQN, and has remarkable anti-jamming performance.