Quantifying and combining uncertainty for improving the behavior of Digital Twin Systems

TL;DR

This paper presents a method to explicitly quantify and combine uncertainties in Digital Twin systems, enhancing their behavior and consistency by better comparison and averaging of uncertainties, validated on an incubator system.

Contribution

It introduces an explicit uncertainty representation for Digital Twins, enabling improved comparison and system performance through uncertainty reduction.

Findings

Enhanced accuracy in twin behavior comparison

Reduced overall system uncertainty

Validated approach on an incubator system

Abstract

Uncertainty is an inherent property of any complex system, especially those that integrate physical parts or operate in real environments. In this paper, we focus on the Digital Twins of adaptive systems, which are particularly complex to design, verify, and optimize. One of the problems of having two systems (the physical one and its digital replica) is that their behavior may not always be consistent. In addition, both twins are normally subject to different types of uncertainties, which complicates their comparison. In this paper we propose the explicit representation and treatment of the uncertainty of both twins, and show how this enables a more accurate comparison of their behaviors. Furthermore, this allows us to reduce the overall system uncertainty and improve its behavior by properly averaging the individual uncertainties of the two twins. An exemplary incubator system is used to illustrate and validate our proposal.