期刊
COMPUTERS & OPERATIONS RESEARCH
卷 66, 期 -, 页码 44-57出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cor.2015.07.011
关键词
Job shop scheduling; Total weighted tardiness; Disjunctive graph model; Neighborhoods; Heuristics
In this paper we consider the job shop scheduling problem with total weighted tardiness objective (JSPTINT). This objective reflects the goal to achieve a high service level which is of increasing importance in many branches of industry. The paper concentrates on a class of baseline heuristics for this problem, known as neighborhood search techniques. An approach based on disjunctive graphs is developed to capture the general structure of neighborhoods for the JSPTWT. Existing as well as newly designed neighborhoods are formulated and analyzed. The performance and search ability of the operators (as well as combinations thereof) are compared in a computational study. Although no dominant operator is identified, a transpose-based perturbation on multiple machines turns out as a promising choice if applied as the only operator. Combining operators improves the schedule quality only slightly. But, the implementation of operators within a meta-heuristic enables to produce a higher schedule quality. A structural classification of neighborhood operators and some new analytical results are presented as well. (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