基于Powell搜索的混沌鸡群优化算法

A Chaotic Chicken Optimization Algorithm Based on Powell Search

针对传统鸡群优化算法(CSO)易陷入局部极值且容易早熟收敛的缺陷,提出了一种混合改进的鸡群优化算法(Powell-LCSO).首先,改进算法利用Logistic混沌映射对种群进行初始化,使得种群较好的分布在解空间中;其次,对鸡群中占据重要地位的母鸡的位置更新方式进行了改进;最后,通过引入Limit阈值判断算法是否陷入局部极值,并利用Powell搜索对全局最优个体进行局部搜索,避免了算法的过早收敛,提高其跳出局部最优的能力.通过实验表明,改进后的鸡群优化算法具有较好寻优精度和收敛效率.

In this paper, a hybrid improved flock optimization algorithm （Powell LCSO） is proposed to overcome the shortcomings of the traditional flock optimization algorithm （CSO） which is easy to fall into the local extremum and easy to premature convergence Firstly, the improved algorithm uses Logistic chaotic map to initialize the population, which makes the population better distributed in the solution space Secondly, the position of the hens in the flocks is improved. Finally, by comparing the Limit threshold to determine whether the algorithm is caught in the local extremum, and using the Powell search to local search for the global optimal individuals, it avoids the premature convergence of the algorithm and improves the accuracy of the algorithm. Its ability to jump out of the local best. Experiments show that the improved flock optimization algorithm has good accuracy and convergence efficiency.