Data-driven Algorithm for Scheduling with Total Tardiness

Michal Bouška, Michal Bouška, Antonín Novák, Antonín Novák, Přemysl Šůcha, István Módos, István Módos, Zdeněk Hanzálek

2020

Abstract

In this paper, we investigate the use of deep learning for solving a classical N P-hard single machine scheduling problem where the criterion is to minimize the total tardiness. Instead of designing an end-to-end machine learning model, we utilize well known decomposition of the problem and we enhance it with a data-driven approach. We have designed a regressor containing a deep neural network that learns and predicts the criterion of a given set of jobs. The network acts as a polynomial-time estimator of the criterion that is used in a singlepass scheduling algorithm based on Lawler's decomposition theorem. Essentially, the regressor guides the algorithm to select the best position for each job. The experimental results show that our data-driven approach can efficiently generalize information from the training phase to significantly larger instances (up to 350 jobs) where it achieves an optimality gap of about 0.5%, which is four times less than the gap of the state-of-the-art NBR heuristic.

Paper Citation

in Harvard Style

Bouška M., Novák A., Šůcha P., Módos I. and Hanzálek Z. (2020). Data-driven Algorithm for Scheduling with Total Tardiness. In Proceedings of the 9th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES, ISBN 978-989-758-396-4, pages 59-68. DOI: 10.5220/0008915300590068

in Bibtex Style

@conference{icores20,
author={Michal Bouška and Antonín Novák and Přemysl Šůcha and István Módos and Zdeněk Hanzálek},
title={Data-driven Algorithm for Scheduling with Total Tardiness},
booktitle={Proceedings of the 9th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES,},
year={2020},
pages={59-68},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008915300590068},
isbn={978-989-758-396-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES,
TI - Data-driven Algorithm for Scheduling with Total Tardiness
SN - 978-989-758-396-4
AU - Bouška M.
AU - Novák A.
AU - Šůcha P.
AU - Módos I.
AU - Hanzálek Z.
PY - 2020
SP - 59
EP - 68
DO - 10.5220/0008915300590068