具有野草行为的萤火虫算法及仿真应用

Glowworm Swarm Optimization with Invasive Weed Behavior and its Applications in Simulation

萤火虫算法特有的局部决策域机制使其具有较强的多峰搜索能力,但也容易造成算法鲁棒性差和收敛速度慢的缺点。针对这一问题,将野草的繁殖和侵占行为引入到萤火虫算法的优化之中,提出一种具有野草行为的萤火虫算法。该算法相对基本萤火虫算法改变较小,但能有效解决吸引邻居集合为空萤火虫个体陷入搜索停滞以及由此造成的鲁棒性差,并可有效提高算法的搜索速度。在4个标准测试函数和PID参数整定上进行仿真应用,结果证明了所提出的算法相对与基本萤火虫算法具有更快的收敛速度和更强的鲁棒性。

The mechanism with local-decision domain in Glowworm swarm optimization makes it strong in searching multiple optima,whereas it may lead to poor robustness and slow convergence speed.To deal with this problem,the invasion and colonial behavior of invasive weed is introduced to the algorithm.The proposed algorithm avoids glowworm agents with empty neighbor stalled,and makes more use of best individuals to speed up the search.Simulations with four benchmark functions and PID parameters tuning demonstrate that the proposed algorithm has faster convergence speed and stronger robustness than standard glowworm swarm optimization.