Home // International Journal On Advances in Systems and Measurements, volume 18, numbers 1 and 2, 2025 // View article

Implementation of a Predictive AI to Feed Simulation

Authors:
Carlo Simon
Merlin Hladik
Natan Georgievic Badurasvili

Keywords: Artificial Intelligence; Neural Networks; Machine Learning; Simulation; Petri Nets

Abstract:
This paper extends a former version presented at the SIMUL 2024 conference. Its topic resulted from a remark of an industry partner dissatisfied with the result of a traffic simulation of a warehouse. Although the simulation was a replica of the behavior on base of the current order data, it deviated from the real situation since many distributors do not adhere to their orders. Methods of predictive artificial intelligence and especially machine learning have been identified to adapt the simulation input on the base of past schedules. The paper answers the question on how to extend the previous simulation model by a suitable forecast component and explains the implementation in more detail than the original paper. Unfortunately, the industry partner does not collect the data needed for such a forecast. Therefore, test data was generated which is explained, too. By the example of a real-world warehouse scenario, the simulation of its traffic and the information needed for this is demonstrated. Afterwards, the necessary extensions of the data set are explained and how to set up a machine learning component to predict future deviations of schedules. The adapted schedules can then be simulated to create alternative schedules. Like in a construction manual, the implementation is explained step by step.

Pages: 19 to 29

Copyright: Copyright (c) to authors, 2025. Used with permission.

Publication date: June 30, 2025

Published in: journal

ISSN: 1942-261x