Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies

Teemu Ikonen; Iiro Harjunkoski

doi:10.1016/B978-0-12-818634-3.50197-1

Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

148 Downloads (Pure)

Abstract

Online scheduling requires appropriate timing of rescheduling procedures, as well as the determination of relevant horizon length. Optimal choices of these quantities are highly dependent on the uncertainty of the scheduling environment and may vary over time. We propose an approach where a neural network is trained to make online decisions on these quantities, as well as on the choice of the rescheduling method (mathematical programming or metaheuristics). In our approach, the neural network is trained using neuroevolution of augmenting topologies (NEAT) in a simulated environment. In this paper, we also optimize the rescheduling interval and horizon length of a conventional periodically occurring rescheduling on a dynamic routing problem. The resulting approach is the baseline for the development of the proposed neural network approach.

Original language	English
Title of host publication	Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering
Editors	Anton Kiss, Edwin Zondervan, Richard Lakerveld, Leyla Özkan
Publisher	Elsevier
Pages	1177-1182
Volume	46
ISBN (Print)	9780128186343
DOIs	https://doi.org/10.1016/B978-0-12-818634-3.50197-1
Publication status	Published - 2019
MoE publication type	A4 Conference publication
Event	European Symposium on Computer-Aided Process Engineering - Eindhoven, Netherlands Duration: 16 Jun 2019 → 19 Jun 2019 Conference number: 29 https://escape29.nl/

Publication series

Name	Computer-aided chemical engineering
Publisher	Elsevier
Volume	46
ISSN (Electronic)	1570-7946

Conference

Conference	European Symposium on Computer-Aided Process Engineering
Abbreviated title	ESCAPE
Country/Territory	Netherlands
City	Eindhoven
Period	16/06/2019 → 19/06/2019
Internet address	https://escape29.nl/

Keywords

online scheduling
horizon length
scheduling interval
neural network
NEAT

Access to Document

10.1016/B978-0-12-818634-3.50197-1

ESCAPE19_ikonen_harjunkoski_finalAccepted author manuscript, 642 KB

Cite this

Ikonen, T., & Harjunkoski, I. (2019). Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies. In A. Kiss, E. Zondervan, R. Lakerveld, & L. Özkan (Eds.), Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering (Vol. 46, pp. 1177-1182). (Computer-aided chemical engineering; Vol. 46). Elsevier. https://doi.org/10.1016/B978-0-12-818634-3.50197-1

@inproceedings{1fac9cbbde704d3baaee1140d8a0aa91,

title = "Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies",

abstract = "Online scheduling requires appropriate timing of rescheduling procedures, as well as the determination of relevant horizon length. Optimal choices of these quantities are highly dependent on the uncertainty of the scheduling environment and may vary over time. We propose an approach where a neural network is trained to make online decisions on these quantities, as well as on the choice of the rescheduling method (mathematical programming or metaheuristics). In our approach, the neural network is trained using neuroevolution of augmenting topologies (NEAT) in a simulated environment. In this paper, we also optimize the rescheduling interval and horizon length of a conventional periodically occurring rescheduling on a dynamic routing problem. The resulting approach is the baseline for the development of the proposed neural network approach.",

keywords = "online scheduling, horizon length, scheduling interval, neural network, NEAT",

author = "Teemu Ikonen and Iiro Harjunkoski",

note = "HUOM! T{\"A}M{\"A}n MANUSKAn EMBARGO ON YLIPITK{\"A} KUNNES ARTIKKELI ON JULKAISTU JA JULKAISUVIIVE M{\"A}{\"A}RITELTY KUSTANTAJAN JULKAISUP{\"A}IV{\"A}ST{\"A} ALKAEN. The manuscript's embargo is very long until the article has been published and the embargo date can be defined. HUOM 2: Varmista, ett{\"a} julkaisun nimi pysyy samana: 29th European Symposium on Computer Aided Chemical [EI PROCESS KUTEN NYT JULKAISUN KUVAUKSESSA] Engineering ; European Symposium on Computer-Aided Process Engineering, ESCAPE ; Conference date: 16-06-2019 Through 19-06-2019",

year = "2019",

doi = "10.1016/B978-0-12-818634-3.50197-1",

language = "English",

isbn = "9780128186343 ",

volume = "46",

series = "Computer-aided chemical engineering",

publisher = "Elsevier",

pages = "1177--1182",

editor = "Kiss, {Anton } and Zondervan, {Edwin } and Lakerveld, {Richard } and {\"O}zkan, {Leyla }",

booktitle = "Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering",

address = "Netherlands",

url = "https://escape29.nl/",

}

Ikonen, T & Harjunkoski, I 2019, Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies. in A Kiss, E Zondervan, R Lakerveld & L Özkan (eds), Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering. vol. 46, Computer-aided chemical engineering, vol. 46, Elsevier, pp. 1177-1182, European Symposium on Computer-Aided Process Engineering, Eindhoven, Netherlands, 16/06/2019. https://doi.org/10.1016/B978-0-12-818634-3.50197-1

Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies. / Ikonen, Teemu ; Harjunkoski, Iiro.
Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering. ed. / Anton Kiss; Edwin Zondervan; Richard Lakerveld; Leyla Özkan. Vol. 46 Elsevier, 2019. p. 1177-1182 (Computer-aided chemical engineering; Vol. 46).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies

AU - Ikonen, Teemu

AU - Harjunkoski, Iiro

N1 - Conference code: 29

PY - 2019

Y1 - 2019

N2 - Online scheduling requires appropriate timing of rescheduling procedures, as well as the determination of relevant horizon length. Optimal choices of these quantities are highly dependent on the uncertainty of the scheduling environment and may vary over time. We propose an approach where a neural network is trained to make online decisions on these quantities, as well as on the choice of the rescheduling method (mathematical programming or metaheuristics). In our approach, the neural network is trained using neuroevolution of augmenting topologies (NEAT) in a simulated environment. In this paper, we also optimize the rescheduling interval and horizon length of a conventional periodically occurring rescheduling on a dynamic routing problem. The resulting approach is the baseline for the development of the proposed neural network approach.

AB - Online scheduling requires appropriate timing of rescheduling procedures, as well as the determination of relevant horizon length. Optimal choices of these quantities are highly dependent on the uncertainty of the scheduling environment and may vary over time. We propose an approach where a neural network is trained to make online decisions on these quantities, as well as on the choice of the rescheduling method (mathematical programming or metaheuristics). In our approach, the neural network is trained using neuroevolution of augmenting topologies (NEAT) in a simulated environment. In this paper, we also optimize the rescheduling interval and horizon length of a conventional periodically occurring rescheduling on a dynamic routing problem. The resulting approach is the baseline for the development of the proposed neural network approach.

KW - online scheduling

KW - horizon length

KW - scheduling interval

KW - neural network

KW - NEAT

U2 - 10.1016/B978-0-12-818634-3.50197-1

DO - 10.1016/B978-0-12-818634-3.50197-1

M3 - Conference article in proceedings

SN - 9780128186343

VL - 46

T3 - Computer-aided chemical engineering

SP - 1177

EP - 1182

BT - Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering

A2 - Kiss, Anton

A2 - Zondervan, Edwin

A2 - Lakerveld, Richard

A2 - Özkan, Leyla

PB - Elsevier

T2 - European Symposium on Computer-Aided Process Engineering

Y2 - 16 June 2019 through 19 June 2019

ER -

Ikonen T , Harjunkoski I. Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies. In Kiss A, Zondervan E, Lakerveld R, Özkan L, editors, Proceedings of the 29th European Symposium on Computer Aided Chemical Engineering. Vol. 46. Elsevier. 2019. p. 1177-1182. (Computer-aided chemical engineering). doi: 10.1016/B978-0-12-818634-3.50197-1

Decision-making of online rescheduling procedures using neuroevolution of augmenting topologies

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this