计算机科学与探索 ›› 2019, Vol. 13 ›› Issue (12): 2103-2116.DOI: 10.3778/j.issn.1673-9418.1812019

• 人工智能 • 上一篇    下一篇

结合JADE和CoDE差分算子的人工蜂群算法

耿璐,李艳娟   

  1. 东北林业大学 信息与计算机工程学院,哈尔滨 150040
  • 出版日期:2019-12-01 发布日期:2019-12-10

Artificial Bee Colony Algorithm Combining JADE and CoDE Difference Operators

GENG Lu, LI Yanjuan   

  1. School of Information and Computer Engineering,  Northeast Forestry University, Harbin 150040, China
  • Online:2019-12-01 Published:2019-12-10

摘要: 人工蜂群算法(ABC)具有良好的全局探索能力,但局部利用能力较弱。与此相反,差分进化(DE)具有良好的局部利用能力,但全局探索能力较弱。鉴于此,提出了ABC和DE结合算法——AMDABC。AMDABC遵循人工蜂群算法的框架,包括雇佣蜂阶段、跟随蜂阶段和侦查蜂阶段。在雇用蜂阶段引入了两个DE算子(JADE算子、CoDE算子),同时给出两个控制参数,根据控制参数的值自适应地交替执行CoDE算子、JADE算子或ABC搜索方程,以达到全局探索能力和局部利用能力的平衡。在跟随蜂阶段,同样结合JADE差分算子产生候选解,以更好地解决ABC算法局部利用能力弱的问题。在19个标准函数上的实验结果表明,AMDABC算法性能优于典型ABC算法、典型DE算法、典型ABC和DE结合算法。

关键词: 人工蜂群算法(ABC), 差分进化, 全局优化, 混合框架

Abstract: Artificial bee colony (ABC) algorithm does well in exploration but badly in exploitation. Unlike ABC, DE tends to exploit well but weakly in exploration. Therefore, the combination algorithm of ABC and DE is proposed, named AMDABC (adaptive modified differential operators based artificial bee colony). AMDABC follows the framework of artificial bee colony algorithm, including the phase of employing bees, onlooker bees and scout bees. This paper introduces two DE operators, operators of CoDE and operators of JADE in the employing bee phase and gives two control parameters. According to the value of the control parameter, the CoDE operator, JADE operator or ABC search equation are performed adaptively and alternately to achieve the balance between global exploration ability and local exploitation ability. In the onlooker bee phase, the JADE difference operator is also used to generate candidate solutions to be a better way to solve the problem of weak exploitation ability of ABC algorithm. Experiments on 19 benchmark functions show that the performance of AMDABC is superior to that of ABC, DE and hybrid algorithm of ABC and DE.

Key words: artificial bee colony (ABC) algorithm, differential evolution, global optimization, hybrid framework