Digital Twin Network: Opportunities and Challenges

Almasan, Paul; Ferriol-Galmés, Miquel; Paillissé, Jordi; Suárez‐Varela, José; Perino, Diego; López, Diego; Perales, Antonio Agustin Pastor; Harvey, Paul H.; Ciavaglia, Laurent; Wong, Leon; Ram, Vishnu Ji; Xiao, Shihan; Xiang, Sheng; Cheng, Xiangle; Cabellos‐Aparicio, Albert; Barlet‐Ros, Pere

doi:10.48550/arxiv.2201.01144

“…Through the virtual representation of the environmental and network elements, GNNs can develop comprehensive insights into nodes, twins, and links in the network by leveraging the dynamic nature of the network as state features, and then aggregate these states to achieve a comprehensive E2E network understanding. From a different angle, recent results demonstrated the superiority of GNN, compared to other classes, in predicting the network E2E delay [6]. This metric can be of importance for the DT paradigm, to accurately measure the delay encountered at the CT-CT, CT-PT, and PT-PT communications, and therefore, compensate for that delay.…”

Section: A Twin-twin Coordinationmentioning

confidence: 99%

The Interplay of AI and Digital Twin: Bridging the Gap between Data-Driven and Model-Driven Approaches

Bariah¹,

Debbah²

2022

Preprint

2

0

View full text Add to dashboard Cite

<p>The advancements of mixed reality services, with the evolution of network virtualization and native artificial intelligence (AI) paradigms, have conceptualized the vision of future wireless networks as a comprehensive entity operating in whole over a digital platform, with smart interaction with the physical domain, paving the way for the blooming of the Digital Twin (DT) concept. The recent interest in the DT networks is fueled by the emergence of novel wireless technologies and use-cases, that exacerbate the level of complexity to orchestrate the network and to manage its resources. Driven by the internet-of-sensing and AI, the key principle of the DT is to create a virtual twin for the physical entities and network dynamics, where the virtual twin will be leveraged to generate synthetic data, in addition to the received sensed data from the physical twin in an on-demand manner. The available data at the twin will be the foundation for AI models training and intelligent inference process. Despite the common understanding that AI is the seed for DT, we anticipate the DT and AI will be enablers for each other, in a way that overcome their limitations and complement each other benefits. In this article, we dig into the fundamentals of DT, where we reveal the role of DT in unifying model-driven and data-driven approaches, and explore the opportunities offered by DT in order to achieve the optimistic vision of 6G networks. We further unfold the essential role of the theoretical underpinnings in unlocking further opportunities by AI, and hence, we unveil their pivotal impact on the realization of reliable, efficient, and low-latency DT. Finally, we identify the limitations of AI-DT and overview potential future research directions, to open the floor for further exploration in AI for DT and DT for AI.</p>

show abstract

“…A digital twin can be seen as a digital representation of a real-world system or phenomena. In a networking context, the community proposed the Digital Twin Network (DTN) as a key technology to enable efficient operation in modern networks [1], [2]. The DTN is a digital replica of the physical network that enables operators to design high performance optimization solutions for complex scenarios, among other use cases [2].…”

Section: Introductionmentioning

confidence: 99%

Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies

Guemes-Palau¹,

Almasan²,

Xiao

³

et al. 2022

NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium

View full text Add to dashboard Cite

The recent growth of emergent network applications (e.g., satellite networks, vehicular networks) is increasing the complexity of managing modern communication networks. As a result, the community proposed the Digital Twin Networks (DTN) as a key enabler of efficient network management. Network operators can leverage the DTN to perform different optimization tasks (e.g., Traffic Engineering, Network Planning).Deep Reinforcement Learning (DRL) showed a high performance when applied to solve network optimization problems. In the context of DTN, DRL can be leveraged to solve optimization problems without directly impacting the real-world network behavior. However, DRL scales poorly with the problem size and complexity. In this paper, we explore the use of Evolutionary Strategies (ES) to train DRL agents for solving a routing optimization problem. The experimental results show that ES achieved a training time speed-up of 128 and 6 for the NSFNET and GEANT2 topologies respectively.

show abstract

“…A digital twin can be seen as a digital representation of a real-world system or phenomena. In a networking context, the community proposed the Digital Twin Network (DTN) as a key technology to enable efficient operation in modern networks [1], [2]. The DTN is a digital representation of the physical network that enables operators to design high performance optimization solutions for complex scenarios, to efficiently plan the next network upgrades or to perform troubleshooting, among others [2].…”

Section: Introductionmentioning

confidence: 99%

“…The DTN is a key enabler for efficient optimization in modern networks [2]. In particular, the DTN models the realworld network dynamics such as the growing trend in network traffic or users.…”

Section: Introductionmentioning

confidence: 99%

Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies

Güemes-Palau¹,

Almasan²,

Xiao³

et al. 2022

Preprint

Self Cite

0

View full text Add to dashboard Cite

The recent growth of emergent network applications (e.g., satellite networks, vehicular networks) is increasing the complexity of managing modern communication networks. As a result, the community proposed the Digital Twin Networks (DTN) as a key enabler of efficient network management. Network operators can leverage the DTN to perform different optimization tasks (e.g., Traffic Engineering, Network Planning).Deep Reinforcement Learning (DRL) showed a high performance when applied to solve network optimization problems. In the context of DTN, DRL can be leveraged to solve optimization problems without directly impacting the real-world network behavior. However, DRL scales poorly with the problem size and complexity. In this paper, we explore the use of Evolutionary Strategies (ES) to train DRL agents for solving a routing optimization problem. The experimental results show that ES achieved a training time speed-up of 128 and 6 for the NSFNET and GEANT2 topologies respectively.

show abstract

Digital Twin Network: Opportunities and Challenges

Cited by 15 publications

References 10 publications

The Interplay of AI and Digital Twin: Bridging the Gap between Data-Driven and Model-Driven Approaches

The Interplay of AI and Digital Twin: Bridging the Gap between Data-Driven and Model-Driven Approaches

Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies

Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies

Contact Info

Product

Resources

About