An Agent-Based Process Mining Architecture for Emergent Behavior Analysis

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)
5 Downloads (Pure)

Abstract

Information systems leave a traceable digital footprint whenever an action is executed. Business process modelers capture these digital traces to understand the behavior of a system, and to extract actual run-time models of those business processes. Despite the omnipresence of such traces, most organizations face substantial differences between the process specifications and the actual run-time behavior. Analyzing and implementing the results of systems that model business processes tend, however, to be difficult due to the inherent complexity of the models. Moreover, the observed reality in the form of lower-level real-time events, as recorded in event logs, is seldom solely explainable by higher-level process models. In this paper, we propose an architecture to model system-wide behavior by combining process mining with a multi-agent system. Digital traces, in the form of event logs, are used to iteratively mine process models from which agents can learn. The approach is initially applied to a case study of a simplified job-shop factory in which automated guided vehicles (AGVs) carry out transportation tasks. Numerical experiments show that the workflow of a process mining model can be used to enhance the agent-based system, particularly, in analyzing bottlenecks and improving decision-making.
Original languageEnglish
Title of host publication2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW)
PublisherIEEE
Pages54-64
Number of pages11
Volume23
ISBN (Electronic)9781728145983
DOIs
Publication statusPublished - 21 Nov 2019
Event23rd IEEE International Enterprise Distributed Object Computing Conference, EDOCW 2019: the Enterprise Computing conference - Paris, France
Duration: 28 Oct 201931 Oct 2019
Conference number: 23

Conference

Conference23rd IEEE International Enterprise Distributed Object Computing Conference, EDOCW 2019
Abbreviated titleIEEE EDOC 2019
CountryFrance
CityParis
Period28/10/1931/10/19

Fingerprint

Industry
Multi agent systems
Industrial plants
Information systems
Decision making
Specifications
Experiments

Keywords

  • Multi-agent system
  • Process mining
  • Emergent behavior
  • Enterprise architecture
  • Supply chain logistics
  • Job-shop
  • Internet of Things

Cite this

Bemthuis, R. H., Koot, M., Mes, M. R. K., Bukhsh, F. A., Iacob, M., & Meratnia, N. (2019). An Agent-Based Process Mining Architecture for Emergent Behavior Analysis. In 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW) (Vol. 23, pp. 54-64). [8907303] IEEE. https://doi.org/10.1109/EDOCW.2019.00022
Bemthuis, R. H. ; Koot, M. ; Mes, M. R. K. ; Bukhsh, F. A. ; Iacob, M. ; Meratnia, N. / An Agent-Based Process Mining Architecture for Emergent Behavior Analysis. 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW). Vol. 23 IEEE, 2019. pp. 54-64
@inproceedings{819936d6f56044fe873b439418efa5f6,
title = "An Agent-Based Process Mining Architecture for Emergent Behavior Analysis",
abstract = "Information systems leave a traceable digital footprint whenever an action is executed. Business process modelers capture these digital traces to understand the behavior of a system, and to extract actual run-time models of those business processes. Despite the omnipresence of such traces, most organizations face substantial differences between the process specifications and the actual run-time behavior. Analyzing and implementing the results of systems that model business processes tend, however, to be difficult due to the inherent complexity of the models. Moreover, the observed reality in the form of lower-level real-time events, as recorded in event logs, is seldom solely explainable by higher-level process models. In this paper, we propose an architecture to model system-wide behavior by combining process mining with a multi-agent system. Digital traces, in the form of event logs, are used to iteratively mine process models from which agents can learn. The approach is initially applied to a case study of a simplified job-shop factory in which automated guided vehicles (AGVs) carry out transportation tasks. Numerical experiments show that the workflow of a process mining model can be used to enhance the agent-based system, particularly, in analyzing bottlenecks and improving decision-making.",
keywords = "Multi-agent system, Process mining, Emergent behavior, Enterprise architecture, Supply chain logistics, Job-shop, Internet of Things",
author = "Bemthuis, {R. H.} and M. Koot and Mes, {M. R. K.} and Bukhsh, {F. A.} and M. Iacob and N. Meratnia",
year = "2019",
month = "11",
day = "21",
doi = "10.1109/EDOCW.2019.00022",
language = "English",
volume = "23",
pages = "54--64",
booktitle = "2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW)",
publisher = "IEEE",
address = "United States",

}

Bemthuis, RH, Koot, M, Mes, MRK, Bukhsh, FA, Iacob, M & Meratnia, N 2019, An Agent-Based Process Mining Architecture for Emergent Behavior Analysis. in 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW). vol. 23, 8907303, IEEE, pp. 54-64, 23rd IEEE International Enterprise Distributed Object Computing Conference, EDOCW 2019, Paris, France, 28/10/19. https://doi.org/10.1109/EDOCW.2019.00022

An Agent-Based Process Mining Architecture for Emergent Behavior Analysis. / Bemthuis, R. H.; Koot, M.; Mes, M. R. K.; Bukhsh, F. A.; Iacob, M.; Meratnia, N.

2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW). Vol. 23 IEEE, 2019. p. 54-64 8907303.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - An Agent-Based Process Mining Architecture for Emergent Behavior Analysis

AU - Bemthuis, R. H.

AU - Koot, M.

AU - Mes, M. R. K.

AU - Bukhsh, F. A.

AU - Iacob, M.

AU - Meratnia, N.

PY - 2019/11/21

Y1 - 2019/11/21

N2 - Information systems leave a traceable digital footprint whenever an action is executed. Business process modelers capture these digital traces to understand the behavior of a system, and to extract actual run-time models of those business processes. Despite the omnipresence of such traces, most organizations face substantial differences between the process specifications and the actual run-time behavior. Analyzing and implementing the results of systems that model business processes tend, however, to be difficult due to the inherent complexity of the models. Moreover, the observed reality in the form of lower-level real-time events, as recorded in event logs, is seldom solely explainable by higher-level process models. In this paper, we propose an architecture to model system-wide behavior by combining process mining with a multi-agent system. Digital traces, in the form of event logs, are used to iteratively mine process models from which agents can learn. The approach is initially applied to a case study of a simplified job-shop factory in which automated guided vehicles (AGVs) carry out transportation tasks. Numerical experiments show that the workflow of a process mining model can be used to enhance the agent-based system, particularly, in analyzing bottlenecks and improving decision-making.

AB - Information systems leave a traceable digital footprint whenever an action is executed. Business process modelers capture these digital traces to understand the behavior of a system, and to extract actual run-time models of those business processes. Despite the omnipresence of such traces, most organizations face substantial differences between the process specifications and the actual run-time behavior. Analyzing and implementing the results of systems that model business processes tend, however, to be difficult due to the inherent complexity of the models. Moreover, the observed reality in the form of lower-level real-time events, as recorded in event logs, is seldom solely explainable by higher-level process models. In this paper, we propose an architecture to model system-wide behavior by combining process mining with a multi-agent system. Digital traces, in the form of event logs, are used to iteratively mine process models from which agents can learn. The approach is initially applied to a case study of a simplified job-shop factory in which automated guided vehicles (AGVs) carry out transportation tasks. Numerical experiments show that the workflow of a process mining model can be used to enhance the agent-based system, particularly, in analyzing bottlenecks and improving decision-making.

KW - Multi-agent system

KW - Process mining

KW - Emergent behavior

KW - Enterprise architecture

KW - Supply chain logistics

KW - Job-shop

KW - Internet of Things

U2 - 10.1109/EDOCW.2019.00022

DO - 10.1109/EDOCW.2019.00022

M3 - Conference contribution

VL - 23

SP - 54

EP - 64

BT - 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW)

PB - IEEE

ER -

Bemthuis RH, Koot M, Mes MRK, Bukhsh FA, Iacob M, Meratnia N. An Agent-Based Process Mining Architecture for Emergent Behavior Analysis. In 2019 IEEE 23rd International Enterprise Distributed Object Computing Workshop (EDOCW). Vol. 23. IEEE. 2019. p. 54-64. 8907303 https://doi.org/10.1109/EDOCW.2019.00022