arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1803.06282cs.NE
收藏

一种全局循环更新的多目标进化算法

A mullti- or many- objective evolutionary algorithm with global loop update

Yingyu Zhang, Bing Zeng, Yuanzhen Li, Junqing Li

摘要:

近年来,多目标进化算法,特别是基于分解的多目标进化算法得到了广泛的关注。基于分解的MOEA强调收敛性和多样性在一个简单的模型,并取得了巨大的成功,在处理理论和实际的多目标或多目标优化问题。在本文中,我们着重于基于分解的MOEA的更新策略,以及它们的比较标准。分析和讨论了基于局部更新策略的MOEA分解算法的三个缺点和现有的几个比较解的标准。提出了一种全局循环更新策略和两种混合准则。随后,一个进化算法的全局循环更新的实现和比较的几个最好的多目标或多目标优化算法在两个著名的无约束测试套件多达15个目标。实验结果表明,与采用局部更新策略的进化算法不同,该算法的种群在进化过程中不会退化,保证了种群的多样性.此外,我们的算法赢得了在大多数情况下的两个测试套件,这表明它是非常有竞争力的收敛性和多样性。我们的算法与不同的标准比较解决方案的运行结果进行了比较。它们的差异是非常显着的,表明我们的算法的性能受到它所采用的标准。

英文摘要:

Multi- or many-objective evolutionary algorithm- s(MOEAs), especially the decomposition-based MOEAs have been widely concerned in recent years. The decomposition-based MOEAs emphasize convergence and diversity in a simple model and have made a great success in dealing with theoretical and practical multi- or many-objective optimization problems. In this paper, we focus on update strategies of the decomposition- based MOEAs, and their criteria for comparing solutions. Three disadvantages of the decomposition-based MOEAs with local update strategies and several existing criteria for comparing solutions are analyzed and discussed. And a global loop update strategy and two hybrid criteria are suggested. Subsequently, an evolutionary algorithm with the global loop update is implement- ed and compared to several of the best multi- or many-objective optimization algorithms on two famous unconstraint test suites with up to 15 objectives. Experimental results demonstrate that unlike evolutionary algorithms with local update strategies, the population of our algorithm does not degenerate at any generation of its evolution, which guarantees the diversity of the resulting population. In addition, our algorithm wins in most instances of the two test suites, indicating that it is very compet- itive in terms of convergence and diversity. Running results of our algorithm with different criteria for comparing solutions are also compared. Their differences are very significant, indicating that the performance of our algorithm is affected by the criterion it adopts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑