一种求解动态优化问题的免疫文化基因算法

Immune-based memetic algorithm for dynamic optimization problems

针对传统免疫网络动态优化算法局部寻优能力弱、寻优精度低及易早熟收敛的缺点,提出一种求解动态优化问题的免疫文化基因算法。基于文化基因算法基本框架,将人工免疫网络算法作为全局搜索算法,采用禁忌搜索算法作为局部搜索算子;同时引入柯西变异加强算法的全局搜索能力,并有效防止早熟收敛。通过对经典动态优化函数测试集在相同条件下的实验表明,该免疫文化基因算法相较于其他同类算法具有较好的搜索精度和收敛速度。

The traditional immune network optimization algorithm had the shortcomings of weak local searching ability, low precision and premature convergence. In order to improve the algorithm performance, this paper proposed an artificial-immune-network-based memetic algorithm for dynamic optimization problems. Based on the framework of memetic algorithm, an artificial immune network algorithm served as the global search algorithm, and a tabu search algorithm served as the local search operator. At the same time, the algorithm introduced the Cauchy variation to improve global searching ability and prevent premature convergence. The experimental results show that the improved algorithm has better search precision and convergence speed compared with other algorithms.