并行多种群模糊遗传算法参数

为改善标准遗传算法的求解效率,提出了一种基于6模糊控制器(6FLC-MDPFGA:6 Fuxy Logic Controllers-Multi-Deme Parallel Fuxxy Genetic Algorithm)的并行多种群自适应遗传算法,并利用MPI(Message PassingInterface)技术建立了一个COW(Cluster Of Workstation)集群,将算法在该硬件平台上进行了实现.通过对该算法的迁移率、迁移间隔等并行参数的试验研究,得出了在特定条件下参数选择的经验值和规律,定性分析了不同参数选择对于求解结果的不同影响.在演示算法组合优化实时应用可行性的同时,试验结果可为算法实际应用参数选择提供参考.

Parameter of Parallel Multi-Deme Fuzzy Genetic Algorithm

In order to improve efficiency of standard genetic algorithms,a novel parallel multi-deme adaptive Genetic algorithm is proposed based on 6FLC-MDPFGA(6 Fuxy Logic Controllers-Multi-Deme Parallel Fuxxy Genetic Algorithm).One PC-based COW(Cluster Of Workstation) with MPI(Message Passing Interface) is built.Furthermore,the proposed 6FLC-MDPFGA is run on the hardware platform.The experiments put emphasis on important parallel parameters of the algorithm,such as migration rates and the frequency of individual migration.Empirical values and rules of parameter selection are determined conditionally.Moreover,qualitative analysis is made for different parameters with respect to the different effects on solving results.While illustrating the feasibility of the proposed algorithm in real-time applications of combinational optimization,simulation results obtained will help select algorithm parameters of other practical applications.