基于混沌理论的动态种群萤火虫算法

Chaos-based dynamic population firefly algorithm

针对萤火虫算法在全局寻优搜索中收敛速度慢、求解精度低,易陷入局部极值区域等缺陷,提出一种基于混沌理论的动态种群萤火虫算法。首先,该算法采用立方映射产生的混沌序列对萤火虫位置进行初始化,为全局搜索的多样性奠定基础;其次,通过对种群的动态监测,每当算法满足预设条件时,基于混沌序列生成部分新的个体,以提高算法的收敛速度;最后,对每一代产生的全局最优解,适时采用高斯扰动进行变异操作,使算法更具有跳出局部极小的能力。通过对6个复杂Benchmark函数进行测试,实验结果表明,该算法提高了全局搜索能力、收敛速度和解的精度。

The Firefly Algorithm （FA） has a few disadvantages in the global searching, including slow convergence speed, low solving precision and high possibility of being trapped in local optimum. A FA based on chaotic dynamic population was proposed. Firstly, chaotic sequence generated by cube map was used to initiate individual position, which strengthened the diversity of global searching; secondly, through dynamic monitoring of population, whenever the algorithm meets the preset condition, the new population individuals were generated using chaotic sequences, thus effectively improving convergence speed; thirdly, a Gaussian disturbance would be given on the global optimum of each generation, thus the algorithm could effectively jump out of local minima. Based on six complex test functions, the test results show that chaos- based dynamic population FA improves the capacity of global searching optimal solution, convergence speed and computational precision of solution.