Incorporation of parameter prediction models of different fidelity into job shop scheduling

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Standard

Incorporation of parameter prediction models of different fidelity into job shop scheduling. / Ikonen, Teemu; Harjunkoski, Iiro.

julkaisussa: IFAC-PapersOnLine, Vuosikerta 52, Nro 1, 2019, s. 142-147.

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Harvard

APA

Vancouver

Author

Bibtex - Lataa

@article{1c8febaf971544a897f21ee7a681f1bc,
title = "Incorporation of parameter prediction models of different fidelity into job shop scheduling",
abstract = "Scheduling of industrial job shop processes is normally conducted using estimates of parameters (e.g. processing times) defining the optimization problem. Inaccuracy in these estimated parameters can significantly affect the optimality, or even feasibility, of the scheduling solution. In this work, we incorporate data-driven parameter prediction models of different fidelity into a unit-specific continuous time scheduling model, and investigate the dependency of the solution quality on the prediction model fidelity. Our high-fidelity prediction model is based on Gaussian processes (GP); more specifically we use the maximum a posteriori probability (MAP) estimate. The low and medium-fidelity prediction models rely on determining the average processing time or average processing rate, respectively, from the dataset. In our test case, involving prediction of taxi durations in New York City, the use of GP prediction model yielded, on average, 5.8{\%} and 1.8{\%} shorter realized make spans in comparison to using the low and medium-fidelity prediction models, respectively.",
keywords = "Scheduling Algorithms, Optimization, Parameter Estimation, Machine Learning, Gaussian Processes",
author = "Teemu Ikonen and Iiro Harjunkoski",
year = "2019",
doi = "10.1016/j.ifacol.2019.06.051",
language = "English",
volume = "52",
pages = "142--147",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "Elsevier Science Publishers BV",
number = "1",

}

RIS - Lataa

TY - JOUR

T1 - Incorporation of parameter prediction models of different fidelity into job shop scheduling

AU - Ikonen, Teemu

AU - Harjunkoski, Iiro

PY - 2019

Y1 - 2019

N2 - Scheduling of industrial job shop processes is normally conducted using estimates of parameters (e.g. processing times) defining the optimization problem. Inaccuracy in these estimated parameters can significantly affect the optimality, or even feasibility, of the scheduling solution. In this work, we incorporate data-driven parameter prediction models of different fidelity into a unit-specific continuous time scheduling model, and investigate the dependency of the solution quality on the prediction model fidelity. Our high-fidelity prediction model is based on Gaussian processes (GP); more specifically we use the maximum a posteriori probability (MAP) estimate. The low and medium-fidelity prediction models rely on determining the average processing time or average processing rate, respectively, from the dataset. In our test case, involving prediction of taxi durations in New York City, the use of GP prediction model yielded, on average, 5.8% and 1.8% shorter realized make spans in comparison to using the low and medium-fidelity prediction models, respectively.

AB - Scheduling of industrial job shop processes is normally conducted using estimates of parameters (e.g. processing times) defining the optimization problem. Inaccuracy in these estimated parameters can significantly affect the optimality, or even feasibility, of the scheduling solution. In this work, we incorporate data-driven parameter prediction models of different fidelity into a unit-specific continuous time scheduling model, and investigate the dependency of the solution quality on the prediction model fidelity. Our high-fidelity prediction model is based on Gaussian processes (GP); more specifically we use the maximum a posteriori probability (MAP) estimate. The low and medium-fidelity prediction models rely on determining the average processing time or average processing rate, respectively, from the dataset. In our test case, involving prediction of taxi durations in New York City, the use of GP prediction model yielded, on average, 5.8% and 1.8% shorter realized make spans in comparison to using the low and medium-fidelity prediction models, respectively.

KW - Scheduling Algorithms

KW - Optimization

KW - Parameter Estimation

KW - Machine Learning

KW - Gaussian Processes

U2 - 10.1016/j.ifacol.2019.06.051

DO - 10.1016/j.ifacol.2019.06.051

M3 - Conference article

VL - 52

SP - 142

EP - 147

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 1

ER -

ID: 33956209