Balancing Search and Estimation in Random Search Based Stochastic Simulation Optimization

Balancing Search and Estimation in Random Search Based Stochastic Simulation Optimization
复制标题

基于随机搜索的随机模拟优化中的平衡搜索和估计

DOI:
10.1109/tac.2016.2522094
复制
发表时间:
2016-01
期刊:
IEEE Transactions on Automatic Control,2016(accepted)
影响因子:
--
通讯作者:
Hu Jian Qiang
Hu Jian Qiang
中科院分区:
其他
文献类型:
--
作者:
Zhu Chenbo;Xu Jie;Chen Chun-Hung;Lee Loo Hay;Hu Jian Qiang

文献摘要

参考文献

被引文献

相似文献

随机模拟优化包括两个基本步骤:1)搜索解空间以产生用于比较的候选解; 2)通过多次模拟来估计每个候选解的性能并选择一个解作为所找到的最佳解。虽然可以通过增加模拟重复的数量来减少估计误差,但这又会限制在固定计算预算中可以生成用于比较的候选解的数量。在一个随机搜索框架下,我们推导出一个解析公式,以(近似)最佳地确定在搜索步骤中生成的候选解决方案的数量,并在估计步骤中进行模拟复制,以最大限度地提高随机搜索算法选择的最佳解决方案的质量。然后,我们提出了一个实用的方法,基于这个公式和测试的方法在几个常见的基准问题。实验结果表明,我们的方法是相当有效的,并导致显着改善的最佳解决方案的质量。
Stochastic simulation optimization involves two fundamental steps: 1) searching the solution space to generate candidate solutions for comparison and 2) estimating the performance of each candidate solution via multiple simulations and selecting a solution as the best solution found. Comparisons of solutions via simulation estimation are subject to error due to the stochastic noise in simulation output. While estimation errors can be reduced by increasing the number of simulation replications, it would in turn limit the number of candidate solutions that can be generated for comparison in a fixed computation budget. Under a random search framework, we derive an analytical formula to (approximately) optimally determine the number of candidate solutions generated in the search step and simulation replications in the estimation step to maximize the quality of the solution selected as the best by the random search algorithm. We then propose a practical method based on this formula and test the method on several common benchmark problems. Experiment results show that our method is quite effective and leads to significant improvement in the quality of the best solution found.
DOI: 10.1109/tac.2011.2158128
发表时间: 2012
影响因子: 6.8
作者:
Jiaqiao Hu;Ping Hu;H. Chang
通讯作者: Jiaqiao Hu;Ping Hu;H. Chang
DOI: 10.2307/1269971
发表时间: 1982
期刊: --
影响因子: --
作者:
Fourth Edition;Averill M. Law
通讯作者: Fourth Edition;Averill M. Law
DOI: 10.1109/tac.2006.884993
发表时间: 2006-12
影响因子: 6.8
作者:
Chun-Hung Chen;Donghai He;M. Fu
通讯作者: Chun-Hung Chen;Donghai He;M. Fu
DOI: 10.1007/s11518-006-0195-6
发表时间: 2005-09
影响因子: 1.2
作者:
L. Lee;E. P. Chew
通讯作者: L. Lee;E. P. Chew
DOI: 10.1023/a:1010081212560
发表时间: 2000-09
影响因子: 0.9
作者:
Leyuan Shi;Sigurdur O´lafsson
通讯作者: Leyuan Shi;Sigurdur O´lafsson