An Estimation of Distribution Algorithm With Cheap and Expensive Local Search Methods

An Estimation of Distribution Algorithm With Cheap and Expensive Local Search Methods
复制标题

一种廉价和昂贵的局部搜索方法的分布估计算法

DOI:
10.1109/tevc.2014.2387433
复制
发表时间:
2015-01
影响因子:
14.3
通讯作者:
Zhang Qingfu
Zhang Qingfu
中科院分区:
计算机科学1区
文献类型:
--
作者:
Zhou Aimin;Sun Jianyong;Zhang Qingfu

文献摘要

参考文献

被引文献

相似文献

在分布估计算法(EDA)中,全局人口分布由概率模型建模,从该概率模型中采样新的试验解,而个体位置信息没有被直接和充分利用。在本文中,我们建议结合联合收割机的EDA廉价和昂贵的本地搜索(LS)的方法,利用全球的统计信息和个人的位置信息。在我们的方法中,一个新的解决方案的一部分是从一个修改的单变量直方图概率模型采样,其余的是通过一个廉价的LS方法,不需要任何功能评估,通过细化父解决方案生成。当人口已经收敛,一个昂贵的LS方法被应用到改善一个有前途的解决方案,到目前为止。控制实验已经进行了调查的算法组件和控制参数的影响,变量的数量上的可扩展性,和运行时间。该算法已被比较与两个国家的最先进的算法在两个测试套件的27个测试实例。实验结果表明,对于简单的测试实例,该算法能得到较好或相近的解,但收敛速度比其他方法快;对于复杂的测试实例,该算法能得到较好的解。
In an estimation of distribution algorithm (EDA), global population distribution is modeled by a probabilistic model, from which new trial solutions are sampled, whereas individual location information is not directly and fully exploited. In this paper, we suggest to combine an EDA with cheap and expensive local search (LS) methods for making use of both global statistical information and individual location information. In our approach, part of a new solution is sampled from a modified univariate histogram probabilistic model and the rest is generated by refining a parent solution through a cheap LS method that does not need any function evaluation. When the population has converged, an expensive LS method is applied to improve a promising solution found so far. Controlled experiments have been carried out to investigate the effects of the algorithm components and the control parameters, the scalability on the number of variables, and the running time. The proposed algorithm has been compared with two state-of-the-art algorithms on two test suites of 27 test instances. Experimental results have shown that, for simple test instances, our algorithm can produce better or similar solutions but with faster convergence speed than the compared methods and for some complicated test instances it can find better solutions.
DOI: 10.1109/4235.797971
发表时间: 1999-11-01
影响因子: 14.3
作者:
Harik, GR;Lobo, FG;Goldberg, DE
通讯作者: Goldberg, DE
DOI: 10.1007/3-540-32494-1
发表时间: 2006
期刊: --
影响因子: --
作者:
J. A. Lozano;P. Larrañaga;Iñaki Inza;E. Bengoetxea
通讯作者: J. A. Lozano;P. Larrañaga;Iñaki Inza;E. Bengoetxea
DOI: 10.1198/jasa.2008.s236
发表时间: 2008-06
影响因子: 3.7
作者:
T. Burr
通讯作者: T. Burr
DOI: 10.1109/tsmcc.2004.841914
发表时间: 2005-05
期刊: IEEE Trans. Syst. Man Cybern. Part C
影响因子: --
作者:
Qiang Lu;X. Yao
通讯作者: Qiang Lu;X. Yao
DOI: 10.1007/3-540-45356-3_75
发表时间: 2000-09
期刊: --
影响因子: --
作者:
P. Bosman;D. Thierens
通讯作者: P. Bosman;D. Thierens