An Optimization Framework for UAV Smoke Screen Coverage Scheduling Using Genetic Algorithm

This paper proposes an effective shielding model and optimization method for drone smoke decoy countermeasures against missiles, focusing on establishing the shielding model based on motion state analysis, single-objective planning optimization, and multi-decoys coordinated scheduling, with a core solution employing genetic algorithms. First, motion state models for both the smoke decoy and the missile are constructed, analyzing pre- and post-detonation movement patterns to define effective shielding geometric criteria and calculate the effective shielding duration per decoy. Second, a single-objective planning model is established to maximize effective shielding duration. Decision variables and constraints are defined, and a genetic algorithm is employed for efficient solution to optimize drone and smoke grenade parameters. Finally, the model is extended to multi-deployments by updating decision variables and objective functions while incorporating release timing constraints. Genetic algorithms determine optimal release sequences and detonation parameters for three smoke grenades, achieving continuous complementary shielding durations. This model precisely describes the relationship between motion and shielding, with genetic algorithms ensuring global optimization and convergence efficiency. It enhances smoke grenade shielding effectiveness against missiles while maintaining practicality and robustness.