期刊
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
卷 44, 期 -, 页码 79-90出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.engappai.2015.05.009
关键词
Automated warehousing; Travel time analysis; Multi-objective optimization; Simulation; Performance analysis
类别
资金
- National Science Foundation [1344954]
- National Natural Science Foundation of China [61305078, 61074032, 61179041]
- Shaoxing City Public Technology Applied Research Project [2013B70004]
This paper proposes an ensemble multi-objective biogeography-based optimization (EMBBO) algorithm, which is inspired by ensemble learning, to solve the automated warehouse scheduling problem. First, a real-world automated warehouse scheduling problem is formulated as a constrained multi-objective optimization problem. Then EMBBO is formulated as a combination of several multi-objective biogeography-based optimization (MBBO) algorithms, including vector evaluated biogeography-based optimization (VEBBO), non-dominated sorting biogeography-based optimization (NSBBO), and niched Pareto biogeography-based optimization (NPBBO). Performance is tested on a set of 10 unconstrained multi-objective benchmark functions and 10 constrained multi-objective benchmark functions from the 2009 Congress on Evolutionary Computation (CEC), and compared with single constituent MBBO and CEC competition algorithms. Results show that EMBBO is better than its constituent algorithms, and among the best CEC competition algorithms, for the benchmark functions studied in this paper. Finally, EMBBO is successfully applied to the automated warehouse scheduling problem, and the results show that EMBBO is a competitive algorithm for automated warehouse scheduling. (C) 2015 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据