EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques

Dmitry Efrosinin iD, Vladimir Vishnevsky iD, Natalia Stepanova iD

Sensors · 2023

DOI: 10.3390/s23125479 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Dmitry Efrosinin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Stochastics, Johannes Kepler University Linz, 4040 Linz, Austria. Hauptthemen laut MEDLINE: Software, Computers. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Johannes Kepler University Linz, Russian Science Foundation, RUDN University Strategic Academic Leadership Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The problem of optimal scheduling in a system with parallel queues and a single server has been extensively studied in queueing theory. However, such systems have mostly been analysed by assuming homogeneous attributes of arrival and service processes, or Markov queueing models were usually assumed in heterogeneous cases. The calculation of the optimal scheduling policy in such a queueing system with switching costs and arbitrary inter-arrival and service time distributions is not a trivial task. In this paper, we propose to combine simulation and neural network techniques to solve this problem. The scheduling in this system is performed by means of a neural network informing the controller at a service completion epoch on a queue index which has to be serviced next. We adapt the simulated annealing algorithm to optimize the weights and the biases of the multi-layer neural network initially trained on some arbitrary heuristic control policy with the aim to minimize the average cost function which in turn can be calculated only via simulation. To verify the quality of the obtained optimal solutions, the optimal scheduling policy was calculated by solving a Markov decision problem formulated for the corresponding Markovian counterpart. The results of numerical analysis show the effectiveness of this approach to find the optimal deterministic control policy for the routing, scheduling or resource allocation in general queueing systems. Moreover, a comparison of the results obtained for different distributions illustrates statistical insensitivity of the optimal scheduling policy to the shape of inter-arrival and service time distributions for the same first moments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareComputersComputer SimulationAlgorithmsNeural Networks, Computer

Stichwörter der Autor:innen

Markov decision problemheterogeneous queuesneural networkoptimal schedulingqueue simulationsimulated annealing

Autor:innen und Institutionen

  • Institute for Stochastics, Johannes Kepler University Linz, 4040 Linz, Austria.
  • Department of Information Sciences, Peoples' Friendship University of Russia (RUDN University), Moscow 117198, Russia.
  • V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow 117997, Russia.
  • Scientific and Production Company "INSET", Moscow 129085, Russia.

ORCID-Profile: Dmitry Efrosinin, Vladimir Vishnevsky, Natalia Stepanova

Förderung

  • Johannes Kepler University Linz
  • Russian Science Foundation
  • RUDN University Strategic Academic Leadership Program
  • University of Linz
  • RSF

Zitieren

APA

Efrosinin, D., Vishnevsky, V., & Stepanova, N. (2023). Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques. Sensors. https://doi.org/10.3390/s23125479

Vancouver

Efrosinin D, Vishnevsky V, Stepanova N. Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques. Sensors. 2023. doi:10.3390/s23125479

BibTeX
@article{Efrosinin2023,
  author = {Efrosinin, Dmitry and Vishnevsky, Vladimir and Stepanova, Natalia},
  title = {Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23125479}
}
Kostenlos starten →