Modeling and Optimization of Deploying Anti-UAV Swarm Detection Systems Based on the Mixed Genetic and Monte Carlo Algorithm

Focusing on detecting anti-UAV swarms, the study on the optimal deployment of detection systems is conducted in this paper. Firstly, it analyzes the problem of detecting anti-UAV swarms to decide feasible detection systems, to rasterizes the deployment space, and then select the deployment strategies. Secondly, based on typical early warning models and using segmented modeling methods, a detection model based on radar/photoelectric detection system is established. The optimization sub-objectives of each stage are sorted and quantified to meet the requirement of different detection stages, and an effectiveness evaluation model of detection system deployment for anti-UAV swarms is proposed. Thirdly, a mixed Genetic Algorithm and Monte Carlo algorithm (hereinafter “GA-MCA”) is put forward to solve the optimization problem of deploying the anti-UAV swarm detection system and then try to find out the best deployment plan of the detection system. Finally, a typical deployment case is designed, and the detection effectiveness of the mixed GA-MCA in different drone scales is evaluated. The simulation results show that compared with the traditional algorithm driven by mathematical models, the detection effectiveness of the deployment plan, which is based on the data-driven mixed GA-MCA, is increased by about 38.2%, which verifies the effectiveness of the mixed algorithm applied to the deployment optimization of the anti-UAV swarm detection systems.