基于动态多策略差分进化模型的MOEA/D算法

MOEA/D based on dynamic multi-strategy differential evolution model

在基于分解技术的多目标进化算法的框架中,引入一种动态多策略差分进化模型。该模型在分析不同差分进化策略的特点基础上,选择了三种差分进化策略,并对每种策略分配一子种群。在进化过程中,依据每种策略对邻域更新的贡献度,动态地调整其子种群的大小。对比分析采用不同差分进化算法的性能,结果表明运用多个策略之间相互协同进化,有利于提高算法性能。将新算法同NSGA-Ⅱ与MOEA/D算法在LZ09系列基准函数上进行性能对比,实验结果显示该算法的收敛性和多样性均优于对比算法。将新应用于Ⅰ型梁多目标优化设计问题中,获得的Pareto前沿均匀,且解集域较宽广,对比分析表明了算法的工程实用性。

In the framework of multi-objective evolutionary algorithm based on decomposition （MOEA/D）, this paper intro- duced a dynamic multi-strategy differential evolution model （MOEA/D-DMDE）. The model chose three differential evolution strategies and each sub-population was corresponding to a differential evolution strategy based on the analysis of the characteri- stics of different strategies. In order to improve the performance of the algorithm, it adjusted the size of sub-population dynami- cally on the basis of a differential evolution strategy contribution for updated of neighborhood. It adopted each strategy to partic- ipate in coordination during the evolution process. Via the comparative analysis of different schemes of differential strategy, MOEA/D-DMDE also performed well. Comparing with NSGA-1I and MOEA/D on the LZ09 benchmarks, the experimental results indicate that MOEA/D-DMDE has a better performance in terms of convergence and diversity. To validate its perfor- mance on constraint multi-objective optimization problems, the proposed MOEA/D-DMDE is applied for solving the I -Beam. The uniformly distributed Pareto sets obtained by MOEA/D-DMDE show its practicability for engineering problems.