| 基于参数动态调整的多目标差分进化算法 |
| |
| 引用本文： | 侯莹,韩红桂,乔俊飞.基于参数动态调整的多目标差分进化算法[J].控制与决策,2017,32(11):1985-1990. |
| |
| 作者姓名： | 侯莹 韩红桂 乔俊飞 |
| |
| 作者单位： | 1. 北京工业大学信息学部,北京100124;2. 计算智能与智能系统北京市重点实验室,北京100124,1. 北京工业大学信息学部,北京100124;2. 计算智能与智能系统北京市重点实验室,北京100124,1. 北京工业大学信息学部,北京100124;2. 计算智能与智能系统北京市重点实验室,北京100124 |
| |
| 基金项目： | 国家自然科学基金项目(61533002,61622301)；中国博士后科学基金项目(2014M550017)；教育部博士点基金项目(20131103110016)；北京市教委项目(KM201410005001, KZ201410005002). |
| |
| 摘 要： | 针对多目标差分进化算法最优解难以获取的问题,提出一种基于参数动态调整的多目标差分进化(AMODE)算法.AMODE算法通过设计变异率和交叉率的自适应调整策略,实现进化过程中变异率和交叉率的动态调整,均衡多目标差分进化算法的局部搜索能力和全局探索能力,获得收敛性、多样性和均匀性较好的最优解.实验结果表明,基于参数动态调整的AMODE算法能够有效改善多目标差分进化算法的逼近能力(IGD)和均匀性(SP),具有较好的优化效果.
|
| 关 键 词： | 多目标优化 差分进化算法 参数动态调整 自适应 |
Adaptive multi-objective differential evolution algorithm based on the dynamic parameters adjustment |
| |
| HOU Ying,HAN Hong-gui and QIAO Jun-fei.Adaptive multi-objective differential evolution algorithm based on the dynamic parameters adjustment[J].Control and Decision,2017,32(11):1985-1990. |
| |
| Authors: | HOU Ying HAN Hong-gui and QIAO Jun-fei |
| |
| Affiliation: | 1. Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;2. Beijing Key Laboratory of Computational Intelligence and Intelligent System,Beijing 100124,China,1. Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;2. Beijing Key Laboratory of Computational Intelligence and Intelligent System,Beijing 100124,China and 1. Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;2. Beijing Key Laboratory of Computational Intelligence and Intelligent System,Beijing 100124,China |
| |
| Abstract: | To obtain the optimal solutions of the multi-objective differential evolution algorithm, an adaptive multi-objective differential evolution(AMODE) algorithm based on the dynamic parameters adjustment strategies is developed, in which the adaptive adjustment strategies are designed to select the scaling factor and crossover rate. Then, the suitable scaling factor and crossover rate can be calculated in the mutation and crossover processes to balance the local search and the global exploration abilities of the multi-objective differential evolution algorithm. Thus, the integrity and uniformity optimal solutions are able to be obtained in the evolutionary process. The experimental results show that this proposed AMODE algorithm has a better effect to improve the inverted generational distance(IGD) and spacing(SP). |
| |
| Keywords: | |
|
| 点击此处可从《控制与决策》浏览原始摘要信息 |
|
点击此处可从《控制与决策》下载全文 |
|
