求解TSP的学习记忆果蝇算法

Novel Fruit Fly Algorithm Based on Learning and Memory for Solving Traveling Salmesman Problem

提出一种解决TSP的学习记忆果蝇算法.为克服传统果蝇算法易于陷入局部极值的缺点,该算法引入了果蝇的学习记忆机制,通过设置种群记忆区指导果蝇个体的搜索方向,以提高算法的全局寻优能力.同时,为增强算法求解TSP的局部搜索能力,结合λ-opt算法设计了一种离散型嗅觉搜索过程.实验结果分析表明,本文所提出的算法能够有效地求解TSP,具有可靠的全局收敛性,较快的收敛速度.

A novel fruit fly algorithm based on learning and memory for solving traveling salesman problem （ TSP ） is proposed. In or- der to overcome the premature convergence drawback of traditional fruit fly algorithm, a learning and memory mechanism of drosophi- la is introduced. With the aim of improving its global optimization ability,the algorithm sets a population memory area so as to guide the search direction of drosophila individuals, which improves its global optimization ability. For enhancing its local search ability for TSP, the λ-opt algorithm is integrated into the algorithm to design a new discrete osphresis foraging phase. The result of TSP examples shows that the algorithm can solve the TSP effectively and it has an excellent search performance no matter in convergence speed or precision.