As a large of parameter space and correlation between parameters of ant colony algorithm, it is difficult to determine the optimal combination of parameters with which the ant colony algorithm for optimal performance. There has yet to complete the theoretical basis, so the parameters are obtained by trial in most cases. Based on these issues, objective function of algorithm performance evaluation is established by balancing exploration and exploitation capabilities of ant colony algorithm, and the ant parameters are solved using genetic algorithm to get a better performance of combination parameters. It verified the feasibility of this model based on simulation of classical TSP problems. The simulation results show that the model can effectively determine the parameters of ant colony algorithm. So it presented a feasible option of determining combination parameters of ant colony algorithm.%由于蚁群算法参数取值范围的不确定性和参数之间的相互影响性,如何确定待解决问题蚁群算法的最优组合参数使得其求解性能最优成为一个难题,至今对该问题还没有完善的理论依据,大多数情况下是通过反复试验试凑得到.根据这些问题,通过平衡蚁群算法探索和开发能力,建立算法性能评价目标函数,采用遗传算法对蚁群参数进行求解,从而得到一组性能较佳的组合参数.基于经典TSP问题进行试验模拟,仿真实验结果表明,该模型能够有效地确定蚁群算法参数,为蚁群算法组合参数的选择提供了一种可行方案.
展开▼
