（2）本文提出的混合粒子群算法中引入自适应惯性权重和学习因子，使PSO

(2) The hybrid particle swarm algorithm proposed in this paper introduces adaptive inertia weights and learning factors, so that the PSO algorithm can maintain a strong global search ability; at the same time, the simulated annealing strategy is improved to improve the local refinement optimization ability in the later stage of the algorithm. A better solution. Therefore, the inherent advantages of the respective algorithms are combined, and the exploration ability and convergence accuracy of the hybrid algorithm in the solution space are improved, and a satisfactory solution is selected from the pareto feasible solutions through grey relational analysis as the digital twin scheduling scheme.

(2) The hybrid particle swarm optimization algorithm proposed in this paper introduces adaptive inertia weight and learning factor, so that PSO algorithm can maintain strong global search ability; At the same time, the simulated annealing strategy is improved to improve the local refinement optimization ability in the later stage of the algorithm and explore better solutions. Thus, combined with the inherent advantages of each algorithm, the exploration ability and convergence accuracy of the hybrid algorithm in the solution space are improved, and a satisfactory solution is selected as the digital twin scheduling scheme from the Pareto feasible solutions through grey correlation analysis.<br>

(2) Adaptive inertia weight and learning factors are introduced into the hybrid particle swarm optimization algorithm proposed in this paper, so that the PSO algorithm can maintain strong global searching ability; At the same time, the simulated annealing strategy is improved to improve the ability of local refinement and optimization in the later stage of the algorithm, and to explore better solutions. Therefore, combining the inherent advantages of each algorithm, the exploration ability and convergence accuracy of the hybrid algorithm in the solution space are improved, and a satisfactory solution among pareto feasible solutions is selected as the digital twin scheduling scheme through grey relational analysis.