基于综合学习策略的多目标分解粒子群算法

Multi-objective Decomposition Particle Swarm Optimization Algorithm Based on Comprehensive Learning Strategy

本文提出了一种基于综合学习策略的多目标分解粒子群算法(D-CLMOPSO),该算法采用综合学习策略对多目标问题进行求解,从而避免早熟收敛;通过分解方法更新主导粒子以增强解的分布;采用存档机制以存储优化过程中的非支配解,并采用多项式变异来避免陷入局部最优.最后将所提出的方法与三种多目标进化算法进行比较,结果表明所提算法在大多数测试问题上具有良好的性能.

In this paper, a multi-objective decomposition particle swarm optimization algorithm （I）-CLMOPSO） based on comprehensive learning strategy is proposed, which uses a comprehensive learning strategy to solve multi- objective problems, so as to avoid premature convergence. The dominant particles are updated by decomposition to enhance the solution Distributiom Archiving mechanism to store the non-dominated solution in the optimization process, and using polynomial variation to avoid falling into the local optimurru Finally, the proposed method is compared with the three multi-objective evolutionary algorithms. The results show that the proposed algorithm has good performance on most of the test problems.