A literature review of supply chain analyses integrating discrete simulation modelling and machine learning

Loading...
Thumbnail Image

Authors

Kogler, Christoph
Maxera, Pavel

Advisor

Referee

Mark

Journal Title

Journal ISSN

Volume Title

Publisher

Altmetrics

Abstract

Simulation and machine learning offer advanced methods to analyse complex flows, risks, and disruptions in supply chains. This literature review, based on a novel classification framework, traces the development of the research area from 2013 to 2025 and confirms intensified publication activities over the past 5 years. A majority of the analysed models merge discrete event simulation with reinforcement learning to cover an operational planning horizon and detailed to intermediate abstraction level. The comprehensive synthesis of 18 review articles, 72 research and conference papers, and 43 related studies explains integration approaches, discusses the current state of the art, and identifies research gaps. Existing individual limitations of discrete simulation and machine learning can be overcome by integrating those essential methods for supply chain analyses. This sets the stage for a new generation of models to plan, design, operate, control, and monitor supply chains in a sustainable, smart, and resilient way.
Simulation and machine learning offer advanced methods to analyse complex flows, risks, and disruptions in supply chains. This literature review, based on a novel classification framework, traces the development of the research area from 2013 to 2025 and confirms intensified publication activities over the past 5 years. A majority of the analysed models merge discrete event simulation with reinforcement learning to cover an operational planning horizon and detailed to intermediate abstraction level. The comprehensive synthesis of 18 review articles, 72 research and conference papers, and 43 related studies explains integration approaches, discusses the current state of the art, and identifies research gaps. Existing individual limitations of discrete simulation and machine learning can be overcome by integrating those essential methods for supply chain analyses. This sets the stage for a new generation of models to plan, design, operate, control, and monitor supply chains in a sustainable, smart, and resilient way.

Description

Citation

Document type

Peer-reviewed

Document version

Published version

Date of access to the full text

Language of document

en

Study field

Comittee

Date of acceptance

Defence

Result of defence

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Except where otherwised noted, this item's license is described as Creative Commons Attribution 4.0 International
Citace PRO