具有记忆的果蝇优化算法

摘要

针对基本的果蝇优化算法(FOA)在寻优进化过程中,极易陷入局部极值区域致使算法的收敛精度和收敛速度下降的缺点,提出了一种改进的果蝇优化算法PFOA.从微粒群算法(PSO)更新粒子的方法中得到启发,在果蝇优化算法中加入了个体经验信息和群体经验信息.PFOA使果蝇个体在寻优进化过程中充分地利用了种群历史信息来增加种群的多样性,从而使果蝇个体能够跳出局部最优解区域,提高算法收敛精度和速度.经过对标准测试函数的仿真实验,表明PFOA在收敛精度、收敛速度上比其他FOA具有明显的提高.%In order to overcome the problems of low convergence precision and easily relapsing into local optimum in the optimization process of the fruit fly algorithm (FOA),this paper presents an improved algorithm PFOA.Inspired by the Particle Swarm Optimization (PSO),the memory of each individual and the memory of the best individual are added into the new algorithm PFOA.In the optimization process,PFOA increases the diversity of fruit fly population and makes fruit fly escape from local optimum,thus improving the algorithm convergence accuracy and speed.The experiment results of standard test functions show that PFOA is better than the other FOAs in convergence accuracy and convergence speed,and the global convergence ability of population has been improved.