Abstract: An improved Genetic Algorithm(GA) based on the kin selection in biology is proposed to avoid the problem of local optimum. The key to this algorithm lies in the construction of a new selection operator, which offers a solution by sacrificing a solution for its kin. By doing so, it ensures an efficiently guided, through search in the neighbourhood of the best solution. This algorithm improves the ability of searching an optimum solution and increases the convergence speed. It has extensive applications for many practical optimization problems. Simulation result proves its effectiveness and better performance.

Key words: kin selection, Genetic Algorithm(GA), premature convergence

摘要： 针对传统遗传算法容易陷入局部最优解的缺陷，借鉴生物中亲缘选择的思想，提出基于亲缘选择的遗传算法。该算法构造新选择算子，通过按亲缘关系放弃一个解而获得另一个解来保证算法在最优解的领域内的有效搜索，提高遗传算法对全局最优解的搜索能力和收敛速度。仿真结果表明，该算法正确有效，性能优于现有的传统算法。

关键词: 亲缘选择, 遗传算法, 早熟收敛

CLC Number: 

• TP18