一种基于动态参数调整的改进人工鱼群算法

A Modified Artificial Fish-swarm Algorithm Based on the Dynamic Regulation of Configuring Parameters

针对经典鱼群算法收敛速度慢、寻优精度低的缺陷,提出了一种基于参数动态调整的改进人工鱼群算法.动态调整视野和拥挤度因子以提高算法的搜索效率;改进去交叉算子以消除交叉路径;引入了再寻优算子确保再次搜索去交叉后路径能够快速找到最优值.求解TSP问题的实验结果表明:改进的人工鱼群算法提高了收敛速度、增强了搜索最优解的能力.

Abstract.A modified AFSA （artificial fish swarm algorithm） with parameters dynamic adjusting was proposed to solve the problem of standard AFSA algorithm trapped in local optimal solution and low con- vergence precision. The advanced algorithm was modified with the following strategies： adiusting the pa- rameters dynamically in the visual field and the congestion factor to improve the searching efficiency, modi- fying the removing crossover operator to find the crossing point and eliminate it, and designing a further optimizing operator to find the current optimal value again in the current path. The improved AFSA was applied to the TSP problem, and the experiment result has shown that the proposed algorithm has better convergence effect and can improve search performance.