首页 | 官方网站   微博 | 高级检索  
     


An efficient and robust artificial bee colony algorithm for numerical optimization
Authors:Wan-li Xiang  Mei-qing An
Affiliation:1. School of Traffic & Transportation, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, PR China;2. Institute of Systems Engineering, Tianjin University, Tianjin 300072, PR China
Abstract:Artificial bee colony (ABC) algorithm has already shown more effective than other population-based algorithms. However, ABC is good at exploration but poor at exploitation, which results in an issue on convergence performance in some cases. To improve the convergence performance of ABC, an efficient and robust artificial bee colony (ERABC) algorithm is proposed. In ERABC, a combinatorial solution search equation is introduced to accelerate the search process. And in order to avoid being trapped in local minima, chaotic search technique is employed on scout bee phase. Meanwhile, to reach a kind of sustainable evolutionary ability, reverse selection based on roulette wheel is applied to keep the population diversity. In addition, to enhance the global convergence, chaotic initialization is used to produce initial population. Finally, experimental results tested on 23 benchmark functions show that ERABC has a very good performance when compared with two ABC-based algorithms.
Keywords:Artificial bee colony algorithm  Initialization based on chaos  Reverse selection based on roulette wheel  Solution search equation  Chaotic search
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号