Scalable Distributed Evolutionary Algorithm Orchestration using Docker Containers

Piotr Dziurzanski; Shuai Zhao; Michael Przewozniczek; Marcin  Komarnicki; Leandro Soares Indrusiak

doi:10.1016/j.jocs.2019.101069

Scalable Distributed Evolutionary Algorithm Orchestration using Docker Containers

Piotr Dziurzanski, Shuai Zhao, Michael Przewozniczek, Marcin Komarnicki, Leandro Soares Indrusiak

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

In smart factories, integrated optimisation of manufacturing process planning and scheduling leads to better results than a traditional sequential approach but is computationally more expensive and thus difficult to be applied to real-world manufacturing scenarios. In this paper, a working approach for cloud-based distributed optimisation for process planning and scheduling is presented. Three managers dynamically governing the creation and deletion of subpopulations (islands) evolved by a multi-objective genetic algorithm are proposed, compared and contrasted. A number of test cases based on two real-world manufacturing scenarios are used to show the applicability of the proposed solution.

Original language	English
Article number	101069
Pages (from-to)	1-14
Number of pages	14
Journal	Journal of Computational Science
Volume	40
Early online date	7 Jan 2020
DOIs	https://doi.org/10.1016/j.jocs.2019.101069
Publication status	E-pub ahead of print - 7 Jan 2020

Bibliographical note

Keywords

Smart factory
Industry 4.0
Evolutionary algorithms
Distributed optimisation
Multi-objective optimisation
Integrated process planning and scheduling

Access to Document

10.1016/j.jocs.2019.101069

JoCS_28th_Feb
© 2019 Elsevier B.V. All rights reserved. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy.
Accepted author manuscript, 1.18 MBLicence: CC BY-NC-ND

SAFIRE
Soares Indrusiak, L. & Audsley, N. C.
EUROPEAN COMMISSION
1/10/16 → 30/09/19
Project: Research project (funded) › Research

Cite this

@article{bc949a211b724dc7b5c4799d4951d771,

title = "Scalable Distributed Evolutionary Algorithm Orchestration using Docker Containers",

abstract = "In smart factories, integrated optimisation of manufacturing process planning and scheduling leads to better results than a traditional sequential approach but is computationally more expensive and thus difficult to be applied to real-world manufacturing scenarios. In this paper, a working approach for cloud-based distributed optimisation for process planning and scheduling is presented. Three managers dynamically governing the creation and deletion of subpopulations (islands) evolved by a multi-objective genetic algorithm are proposed, compared and contrasted. A number of test cases based on two real-world manufacturing scenarios are used to show the applicability of the proposed solution.",

keywords = "Smart factory, Industry 4.0, Evolutionary algorithms, Distributed optimisation, Multi-objective optimisation, Integrated process planning and scheduling",

author = "Piotr Dziurzanski and Shuai Zhao and Michael Przewozniczek and Marcin Komarnicki and {Soares Indrusiak}, Leandro",

note = "{\textcopyright} 2019 Elsevier B.V. All rights reserved. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. ",

year = "2020",

month = jan,

day = "7",

doi = "10.1016/j.jocs.2019.101069",

language = "English",

volume = "40",

pages = "1--14",

journal = "Journal of Computational Science",

issn = "1877-7503",

publisher = "Elsevier",

}

TY - JOUR

T1 - Scalable Distributed Evolutionary Algorithm Orchestration using Docker Containers

AU - Dziurzanski, Piotr

AU - Zhao, Shuai

AU - Przewozniczek, Michael

AU - Komarnicki, Marcin

AU - Soares Indrusiak, Leandro

PY - 2020/1/7

Y1 - 2020/1/7

N2 - In smart factories, integrated optimisation of manufacturing process planning and scheduling leads to better results than a traditional sequential approach but is computationally more expensive and thus difficult to be applied to real-world manufacturing scenarios. In this paper, a working approach for cloud-based distributed optimisation for process planning and scheduling is presented. Three managers dynamically governing the creation and deletion of subpopulations (islands) evolved by a multi-objective genetic algorithm are proposed, compared and contrasted. A number of test cases based on two real-world manufacturing scenarios are used to show the applicability of the proposed solution.

AB - In smart factories, integrated optimisation of manufacturing process planning and scheduling leads to better results than a traditional sequential approach but is computationally more expensive and thus difficult to be applied to real-world manufacturing scenarios. In this paper, a working approach for cloud-based distributed optimisation for process planning and scheduling is presented. Three managers dynamically governing the creation and deletion of subpopulations (islands) evolved by a multi-objective genetic algorithm are proposed, compared and contrasted. A number of test cases based on two real-world manufacturing scenarios are used to show the applicability of the proposed solution.

KW - Smart factory

KW - Industry 4.0

KW - Evolutionary algorithms

KW - Distributed optimisation

KW - Multi-objective optimisation

KW - Integrated process planning and scheduling

U2 - 10.1016/j.jocs.2019.101069

DO - 10.1016/j.jocs.2019.101069

M3 - Article

SN - 1877-7503

VL - 40

SP - 1

EP - 14

JO - Journal of Computational Science

JF - Journal of Computational Science

M1 - 101069

ER -

Scalable Distributed Evolutionary Algorithm Orchestration using Docker Containers

Abstract

Bibliographical note

Keywords

Access to Document

Projects

SAFIRE

Cite this