How deals with discrete data for the reduction of simulation models using neural network

TL;DR

This paper explores how to effectively handle discrete data in neural network-based reduction of complex simulation models, focusing on bottleneck identification and pruning, with application to a sawmill supply chain.

Contribution

It introduces a method for designing reduced simulation models using neural networks that specifically addresses the challenges of discrete data handling.

Findings

Discrete data significantly impact neural network performance.

Pruning procedures improve model accuracy and simplicity.

Approach successfully applied to sawmill supply chain simulation.

Abstract

Simulation is useful for the evaluation of a Master Production/distribution Schedule (MPS). Also, the goal of this paper is the study of the design of a simulation model by reducing its complexity. According to theory of constraints, we want to build reduced models composed exclusively by bottlenecks and a neural network. Particularly a multilayer perceptron, is used. The structure of the network is determined by using a pruning procedure. This work focuses on the impact of discrete data on the results and compares different approaches to deal with these data. This approach is applied to sawmill internal supply chain