An improved NSGA-II algorithm for multi-sensor scheduling optimization

Abstract In this work, we investigate the issue of inadequate solution quality and insufficient convergence in multi-sensor scheduling algorithms for tracking aerial moving targets, and enhance the traditional Non-dominated Sorting Genetic Algorithm II (NSGA-II) through adaptive parameters for crossover and mutation. Taking tracking error and sensor resource consumption into account, we establish two task metrics for a multi-objective optimization problem. The refined algorithm is employed to solve the multi-sensor scheduling optimization problem. Simulation results indicate that the enhanced algorithm achieves superior solution quality compared to the conventional NSGA-II.