期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 52, 期 8, 页码 8142-8156出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2021.3050141
关键词
Dynamic scheduling; Job shop scheduling; Sequential analysis; Routing; Heuristic algorithms; Computational modeling; Processor scheduling; Collaboration; dynamic flexible job shop scheduling (DFJSS); genetic programming (GP); knowledge transfer; multifidelity-based surrogate models
类别
资金
- Marsden Fund of New Zealand Government [VUW1509, VUW1614]
- Science for Technological Innovation Challenge (SfTI) fund [E3603/2903]
- MBIE SSIF Fund [VUW RTVU1914]
- China Scholarship Council (CSC)/Victoria University Scholarship
Dynamic flexible job shop scheduling (JSS) has attracted attention for its practical application value, requiring complex routing decisions. Genetic programming (GP) has been successfully applied to evolve scheduling heuristics for JSS. However, simulation-based evaluation is computationally expensive. This article proposes a novel multifidelity-based surrogate-assisted GP to reduce computational cost without sacrificing performance.
Dynamic flexible job shop scheduling (JSS) has received widespread attention from academia and industry due to its practical application value. It requires complex routing and sequencing decisions under unpredicted dynamic events. Genetic programming (GP), as a hyperheuristic approach, has been successfully applied to evolve scheduling heuristics for JSS due to its flexible representation. However, the simulation-based evaluation is computationally expensive since there are many calculations based on individuals for making decisions in the simulation. To improve training efficiency, this article proposes a novel multifidelity-based surrogate-assisted GP. Specifically, multifidelity-based surrogate models are first designed by simplifying the problem expected to be solved. In addition, this article proposes an effective collaboration mechanism with knowledge transfer for utilizing the advantages of multifidelity-based surrogate models to solve the desired problems. This article examines the proposed algorithm in six different scenarios. The results show that the proposed algorithm can dramatically reduce the computational cost of GP without sacrificing the performance in all scenarios. With the same training time, the proposed algorithm can achieve significantly better performance than its counterparts in most scenarios while no worse in others.
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