一种多群竞争进化规划算法

易早熟收敛是传统进化规划算法的致命缺点.本文在分析了导致进化规划算法早熟原因的基础上,提出了一种改进的多群进化规划算法.在该算法中,进化在多个不同的子群间并行进行,子群间的竞争决定个体的变异能力,子群间的信息交流通过子群重组实现.对典型算例的数值仿真表明,该算法能够改善传统的进化规划算法易早熟收敛的弱点,同时具有良好的快速收敛性和参数鲁棒性.

A Multi-Subgroup Competition Evolutionary Programming Algorithm

Premature convergence is the fatal shortcoming of traditional evolutionary programming.Based on the analysis of premature convergence of traditional evolutionary programming,a novel Multi-subgroup Competition Evolutionary Programming (MCEP) algorithm is proposed.In the algorithm,evolutions of subgroups are parallely performed with the different mutation strategies.The mutation capability of an individual is determined by the competition among subgroups.The individual,together with information,is exchanged while subgroup is reorganized.The simulations based on benchmarks confirm that this algorithm is better than classical evolutionary programming algorithm in the aspects of global optimization,convergence speed and the robustness.