.png){kind=icon}
.png){kind=icon}
Return
Optimal computing budget allocation for the vector evaluated genetic algorithm in multi-objective simulation optimization
.png){kind=icon}
OA
AI
DOI：10.1016/j.automatica.2021.109599.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Motivated by the vector evaluation genetic algorithm (VEGA), this research develops simulation budget allocation rules for the VEGA in solving simulation optimization problems. We formulate the selection problem of the VEGA using the optimal computing budget allocation approach, and derive the asymptotically optimal allocation rule and an easily implementable approximated allocation rule. The efficiency of the propose simulation budget allocation rules is demonstrated via comparing with some existing allocation rules. Furthermore, the proposed allocation rule is integrated with the VEGA to solve the multi-objective simulation optimization problems. The numerical experiments on the benchmarking test problems indicate that the proposed allocation rule can improve the search efficiency of the VEGA in stochastic environment by reducing the average distance towards the true Pareto front and improving the purity of the estimated Pareto front. (C) 2021 The Author(s). Published by Elsevier Ltd.
Keywords:
OCBA
Ranking and selection
Multi-objective simulation optimization
VEGA
Computing budget allocation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.9
Papers:
1.2W
Citations:
5.2W