Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Empirical Application Insights on Industrial Data and Service Aspects of Digital Twin Networks

Marco Becattini, Davide Borsatti, Armir Bujari, Laura Carnevali, Andrea Garbugli, Hrant Khachatrian, Theofanis P. Raptis, Daniele Tarchi

TL;DR

The paper addresses how to operationalize Digital Twin Networks in industrial settings by aligning theory with practice across data fidelity, workload management, and service provisioning. It develops empirical methods, including Doppelgänger vs lightweight DTs, synthetic data for environment reconstruction, and MDN-based latency distributions within KubeTwin, to enable realistic DTN simulations. It then introduces Generalized Digital Twin Networks (G_DTNs) and demonstrates a PoC that maps DTNs to stochastic models and connects network-level and asset-level twins, aided by ITU-T Y.3090. The work identifies key open challenges in data interoperability, real-world validation, and edge-to-cloud orchestration needed to realize low-latency, high-reliability industrial services.

Abstract

Digital twin networks (DTNs) serve as an emerging facilitator in the industrial networking sector, enabling the management of new classes of services, which require tailored support for improved resource utilization, low latencies and accurate data fidelity. In this paper, we explore the intersection between theoretical recommendations and practical implications of applying DTNs to industrial networked environments, sharing empirical findings and lessons learned from our ongoing work. To this end, we first provide experimental examples from selected aspects of data representations and fidelity, mixed-criticality workload support, and application-driven services. Then, we introduce an architectural framework for DTNs, exposing a more practical extension of existing standards; notably the ITU-T Y.3090 (2022) recommendation. Specifically, we explore and discuss the dual nature of DTNs, meant as a digital twin of the network and a network of digital twins, allowing the co-existence of both paradigms.

Empirical Application Insights on Industrial Data and Service Aspects of Digital Twin Networks

TL;DR

The paper addresses how to operationalize Digital Twin Networks in industrial settings by aligning theory with practice across data fidelity, workload management, and service provisioning. It develops empirical methods, including Doppelgänger vs lightweight DTs, synthetic data for environment reconstruction, and MDN-based latency distributions within KubeTwin, to enable realistic DTN simulations. It then introduces Generalized Digital Twin Networks (G_DTNs) and demonstrates a PoC that maps DTNs to stochastic models and connects network-level and asset-level twins, aided by ITU-T Y.3090. The work identifies key open challenges in data interoperability, real-world validation, and edge-to-cloud orchestration needed to realize low-latency, high-reliability industrial services.

Abstract

Digital twin networks (DTNs) serve as an emerging facilitator in the industrial networking sector, enabling the management of new classes of services, which require tailored support for improved resource utilization, low latencies and accurate data fidelity. In this paper, we explore the intersection between theoretical recommendations and practical implications of applying DTNs to industrial networked environments, sharing empirical findings and lessons learned from our ongoing work. To this end, we first provide experimental examples from selected aspects of data representations and fidelity, mixed-criticality workload support, and application-driven services. Then, we introduce an architectural framework for DTNs, exposing a more practical extension of existing standards; notably the ITU-T Y.3090 (2022) recommendation. Specifically, we explore and discuss the dual nature of DTNs, meant as a digital twin of the network and a network of digital twins, allowing the co-existence of both paradigms.
Paper Structure (6 sections, 6 figures)

This paper contains 6 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Data representations, fidelity and prediction
  3. Layered management and orchestration for mixed-criticality workloads
  4. Application-driven services
  5. Toward a practical DT network architecture
  6. Open challenges

Figures (6)

  • Figure 1: Logical diagram of our approach.
  • Figure 2: Environment digital reconstruction.
  • Figure 3: Layered architecture for end-to-end QoS management of mixed-critical workloads.
  • Figure 4: Observed latencies before and after the reconfiguration phase, passing from flow 1 to flow 2.
  • Figure 5: Comparison between the mean and 99th percentile response time of the real application and KubeTwin.
  • ...and 1 more figures