一种排序变异的改进蝙蝠算法

Improved Bat Algorithm with Ranking-based Mutation

针对蝙蝠算法易陷入局部最小值等不足,提出一种改进的蝙蝠算法,局部搜索采用指数交叉变异,提高局部搜索能力的同时又保持种群多样性;受自然界启发,优良的品种总是包含有好的信息,采用排序策略选择较优质的个体进行变异来产生优质的候选解。在典型测试函数上对新算法进行了仿真,结果表明改进的蝙蝠算法能够有效提高算法的收敛速度并改善解的质量,与其它改进蝙蝠算法和改进群智能算法的比较表明,改进算法在求解多维函数优化问题上是具有竞争力的。

Aiming at the shortages that bat algorithm is easy falling into local minimum, an improved bat algorithm is proposed. Exponential crossover mutation is employed in the local search, which improve searching capabilities while maintaining the diversity of popula- tion on the process of iterations. Inspired by nature, good species always contain good information, and hence, they have more chance to be utilized. So some of the parents in the mutation operators are proportionally selected according their rankings in the current population. The higher ranking a parent obtains, the more opportunity it will be selected. The simulation experiments on typical test functions show the proposed method can improve the convergence speed and the quality of the solution effectively. Meanwhile, the results also reveal the pro- posed algorithm is competitive for solving multi-dimensional function optimization compared with other improved bat algorithm and swarm intelligence algorithms.