基于多层次信息交互的多目标粒子群优化算法

Multi-objective particle swarm optimization algorithm based on the interaction of multi-level information

为提高多目标优化算法的收敛性和多样性,提出一种基于多层次信息交互的多目标粒子群优化算法.在该算法中,整个优化过程可分为标准粒子群优化层、粒子进化与学习层和档案信息交换层3个层次.粒子进化与学习层保证了每次迭代都能得到更好的粒子位置;档案信息交换层可以提供更好的全局最优.优化算法各个层次之间通过信息交互,共同提高算法的收敛性和多样性.与NSGA-Ⅱ和MOPSO算法的对比分析表明,所提出算法具有良好的性能,能够有效解决多目标优化问题.

In order to improve the convergence and diversity, a multi-objective particle swarm optimization algorithm based on the interaction of multi-level information is proposed. In this algorithm, the optimization is divided into the standard particle optimization layer, the particle evolution and learning layer and the archive information exchange layer. The particle evolution and learning layer ensures that a better particle position can be acquired in each iteration, while the layer of archive information exchange can provide a better global optimization. With the information interaction between different layers in this algorithm, the convergence and diversity are improved. Comparing this algorithm to the NSGA-Ⅱ algorithm and the MOPSO algorithm, the results show that the proposed algorithm has better performance and can effectively solve the multi-objective optimization problem.