基于层级交流机制的混合蛙跳算法  

A Hybrid Frog Leaping Algorithm Based on Interlayer Communication Mechanism

作　　者：张文康 李佳玲 ZHANG Wenkang;LI Jialing(Department of Information,Affiliated Hospital of Jiangsu University,Zhenjiang 212001,Jiangsu,China;School of Computer Science and Communication Engineering,Jiangsu University,Zhenjiang 212013,Jiangsu,China)

机构地区：[1]江苏大学附属医院信息科,江苏镇江212001 [2]江苏大学计算机科学与通信工程学院,江苏镇江212013

出　　处：《实验室研究与探索》2019年第11期21-25,共5页Research and Exploration In Laboratory

基　　金：国家自然科学基金项目(61300228)

摘　　要：针对混合蛙跳算法收敛速度慢,求解精度不高且易于早熟的缺点,提出了一种新的基于层间交流机制的混合蛙跳算法。该算法在原混合蛙跳算法的基础上增加了层间交流机制,使得群中的个体能够进行纵向学习,增强了个体之间信息共享,有利于增强全局搜索能力;并且在对最差青蛙更新的过程中添加了自旋操作,保证了算法后期的多样性,减少了其陷入局部最优的概率。实验结果表明,在6个常用的测试函数上,该算法相比于混合蛙跳算法都取得了较优的结果。A new hybrid frog leaping algorithm based on interlayer communication mechanism is proposed to overcome the shortcomings of slow convergence speed,low accuracy and prematurity of the hybrid frog leaping algorithm.The inter layer communication mechanism is added on the basis of the original hybrid frog leaping algorithm,the new algorithm enables the individual in the group to learn longitudinally,enhances the information sharing among the individuals and enhances the global search ability.The spin operation to the process of the worst frog update ensures the diversity of the algorithm in the later period,and reduces the probability of falling into local optimum.Experimental results show that the proposed algorithm achieves better results than the hybrid frog-hop algorithm on six test functions.

关 键 词：混合蛙跳算法 纵向学习 层级交流 自旋 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]