Automatic design of scheduling policies for dynamic flexible job shop scheduling via surrogate-assisted cooperative co-evolution genetic programming

Zhou, Yong; Yang, Jianjun; Huang, Zhuang

doi:10.1080/00207543.2019.1620362

Cited by 71 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method MTGP is promising in terms of the effectiveness, efficiency, and the sizes of evolved rules. Genetic expression programming with multi-chromosome was also introduced to evolve two rules simultaneously [52]. This paper conducts on the MTGP framework to evolve routing and sequencing rules simultaneously.…”

Section: Representationmentioning

confidence: 99%

Collaborative Multifidelity-Based Surrogate Models for Genetic Programming in Dynamic Flexible Job Shop Scheduling

Zhang

Mei

Nguyen

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Dynamic flexible job shop scheduling 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, as a hyper-heuristic approach, has been successfully applied to evolve scheduling heuristics for job shop scheduling due to its flexible representation. However, the simulationbased evaluation is computationally expensive since there are many calculations based on individuals for making decisions in the simulation. To improve training efficiency, this paper proposes a novel multi-fidelity based surrogate-assisted genetic programming. Specifically, multi-fidelity based surrogate models are first designed by simplifying the problem expected to be solved. In addition, this paper proposes an effective collaboration mechanism with knowledge transfer for utilising the advantages of multi-fidelity based surrogate models to solve the desired problems. This paper examines the proposed algorithm in six different scenarios. The results show that the proposed algorithm can dramatically reduce the computational cost of genetic programming 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.

show abstract

Section: Representationmentioning

confidence: 99%

Collaborative Multifidelity-Based Surrogate Models for Genetic Programming in Dynamic Flexible Job Shop Scheduling

Zhang

Mei

Nguyen

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…Differently from GP, GEP-based algorithms make use of a fixed-length representation structure. We also highlight the work from Zhou et al (2019), which develops a co-evolutionary GP algorithm for due date assignment and dispatching rules. A multi-objective JSSP was tackled by and .…”

Section: Gp For the Automated Design Of Dispatching Rulesmentioning

confidence: 99%

Effective and interpretable dispatching rules for dynamic job shops via guided empirical learning

Ferreira,

Figueira,

Amorim

2021

Preprint

View full text Add to dashboard Cite

The emergence of Industry 4.0 is making production systems more flexible and also more dynamic. In these settings, schedules often need to be adapted in real-time by dispatching rules. Although substantial progress was made until the '90s, the performance of these rules is still rather limited. The machine learning literature is developing a variety of methods to improve them, but the resulting rules are difficult to interpret and do not generalise well for a wide range of settings. This paper is the first major attempt at combining machine learning with domain problem reasoning for scheduling. The idea consists of using the insights obtained with the latter to guide the empirical search of the former. Our hypothesis is that this guided empirical learning process should result in dispatching rules that are effective and interpretable and which generalise well to different instance classes. We test our approach in the classical dynamic job shop scheduling problem minimising tardiness, which is one of the most well-studied scheduling problems. Nonetheless, results suggest that our approach was able to find new state-of-the-art rules, which significantly outperform the existing literature in the vast majority of settings, from loose to tight due dates and from low utilisation conditions to congested shops. Overall, the average improvement is 19%. Moreover, the rules are compact, interpretable, and generalise well to extreme, unseen scenarios.

show abstract

“…Dispatching rule is one of the widely used approaches for sequencing decision, and readers are referred to related works [5,[40][41][42][43][44][45][46]. Designing a sophisticated rule is a trial and error process, and evolving composite rules using genetic algorithm have become a new potential solution in dynamic FJSP [47][48][49][50][51]. Cooperative coevolution has been embedded in Genetic programming (GP) to evolve routing and dispatching rules [47,51], and automatically designed rules are suggested to achieve better performances than manual designed rules in dynamic FJSP.…”

Section: Sets and Indicesmentioning

confidence: 99%

“…Designing a sophisticated rule is a trial and error process, and evolving composite rules using genetic algorithm have become a new potential solution in dynamic FJSP [47][48][49][50][51]. Cooperative coevolution has been embedded in Genetic programming (GP) to evolve routing and dispatching rules [47,51], and automatically designed rules are suggested to achieve better performances than manual designed rules in dynamic FJSP. Nondominated sorting genetic algorithm-II (NSGA-II) is incorporate into GP to solve multi-objective dynamic FJSP [47,48,51,52].…”

Section: Sets and Indicesmentioning

confidence: 99%

“…Cooperative coevolution has been embedded in Genetic programming (GP) to evolve routing and dispatching rules [47,51], and automatically designed rules are suggested to achieve better performances than manual designed rules in dynamic FJSP. Nondominated sorting genetic algorithm-II (NSGA-II) is incorporate into GP to solve multi-objective dynamic FJSP [47,48,51,52]. It is suggested that the functions of automatically designed rules have great concerns with the choice of job and shop features [49,53,54].…”

Section: Sets and Indicesmentioning

confidence: 99%

See 1 more Smart Citation

Performance Assessment of Dynamic Flexible Assembly Job Shop Control Methods

et al. 2020

View full text Add to dashboard Cite

Automatic design of scheduling policies for dynamic flexible job shop scheduling via surrogate-assisted cooperative co-evolution genetic programming

Cited by 71 publications

References 41 publications

Collaborative Multifidelity-Based Surrogate Models for Genetic Programming in Dynamic Flexible Job Shop Scheduling

Collaborative Multifidelity-Based Surrogate Models for Genetic Programming in Dynamic Flexible Job Shop Scheduling

Effective and interpretable dispatching rules for dynamic job shops via guided empirical learning

Performance Assessment of Dynamic Flexible Assembly Job Shop Control Methods

Contact Info

Product

Resources

About