一种整数编码的改进遗传算法  

An Ameliorative Integer Coded Genetic Algorithm

作　　者：廖美英[1] 郭荷清[2] 张勇军[3] 

机构地区：[1]广州市信息中心,广州510030 [2]华南理工大学计算机科学与工程学院,广州510640 [3]华南理工大学电力学院,广州510640

出　　处：《计算机工程与应用》2003年第1期103-105,120,共4页Computer Engineering and Applications

摘　　要：遗传算法作为一种优秀的寻优算法,编码策略是其基础。因二进制编码和实数编码均存在一定的不足,该文提出一种整数编码的最优化遗传算法。为了提高收敛效率和避免算法的早熟收敛,该文采用了截断选择机制和混合杂交、邻近变异等操作算子,并引入邻域搜索技术来提高算法的局部搜索能力。仿真计算表明了该算法具有令人满意的全局最优性能和统计稳定性。As an excellent algorithm,genetic algorithm is based on its encoding strategy.This paper presents an ameliorative genetic algorithm based on integer encoding strategy for optimization problems because of the shortages of binary encoding and real encoding.Truncation selection mechanism,hybrid cross and adjacent mutation operators are employed to heighten the convergence efficiency and prevent premature convergence of GA in this paper.Neighbour search technique is introduced to improve the local search capability.The proposed algorithm is proved to have satisfying global optimization performance and statistics stability by the emulation computation.

关 键 词：遗传算法 邻域搜索 最优化 整数编码 

分 类 号：O242.23[理学—计算数学]