Joint Optimization of Resource Utilization and Jamming Method Selection for Cluster Asymmetrical Multifunction Radars Based on Deep Reinforcement Learning

Multifunction radar (MFR) can be probabilistically transferred to different operating modes according to the surrounding environment, and multiradar is often the case in reality. Compared with one-to-one jamming, multiradar jamming involves the selection of the jamming action for each radar and the scheduling of the whole resource. Therefore, the development of intelligent jamming methods for cluster asymmetric countermeasures has become an important task in electronic warfare. In this article, we propose a solution to address the problem of formulating jamming schemes under conditions of asymmetrical countermeasures within a cluster with limited resources. Specifically, we have investigated a joint optimization of resource utilization and jamming method selection for cluster asymmetrical MFRs. Considering the threat level of the overall MFR operating states and the variations in jamming power across different alignment states, we have meticulously designed the reward function, radar state space, and action space. Furthermore, for the asymmetrical tasks of the cluster, we have proposed a set of evaluation criteria for the jamming scheme, which takes into account the overall threat level and the power expenditure. Ultimately, the simulation results demonstrate that the proposed algorithm is capable of learning highly adaptive strategies within asymmetrical cluster jamming and has achieved commendable performance in terms of jamming. The model proposed in this article not only has a good performance in the field of electronic countermeasures but also has a certain universality to other cluster nonpeer environments.