Force Demand Planning of UAV Cluster Adversarial via Hybrid Group Swarm Optimization

A force demand planning method based on Hybrid Group Swarm Optimization (HGSO) is proposed for unmanned aerial vehicle (UAV) swarm confrontation. Firstly, according to the information on UAVs' maneuverability and load performance, the mathematical model of UAV cluster force demand planning is constructed. Then, a hybrid group swarm optimization algorithm is proposed. During the evolution, all particles are randomly divided into two groups. The two groups conduct competitive learning respectively. All the loser particles are gathered together for another competitive learning. Successful particles only evolve once in two evolutions. Compared with other algorithms, successful particles can be less disturbed. It is conducive to protecting the information of high-quality particles and improving the convergence of clusters. HGSO fully exploits the potential of the particle swarm and improves cluster diversity. It improves the quality of solving the UAV cluster force demand planning problem. Results show that this method can effectively solve the problem of UAV group force demand planning. The fitness is 180.7636, the total running time is 0.41 times of the other algorithms, and the solution quality is high. Compared with other algorithms, HGSO is optimal in convergence speed. It has obvious advantages in optimization accuracy and stability.