Concepts of Digital Twin
NetworkChina MobileBeijing100053Chinazhouchengyjy@chinamobile.comChina MobileBeijing100053Chinayanghongwei@chinamobile.comChina MobileBeijing100053Chinaduanxiaodong@chinamobile.com
Networking
Internet Research Task ForceDigtial Twin; Digital Twin Network; DTN; IBNDigital twin technology is becoming a hot technology in industry 4.0.
The application of digital twin technology in network field helps to
realize efficient and intelligent management and network innovation.
This document presents an overview of the concepts of Digital Twin
Network (DTN), provides the definition and DTN, and then describes the
benefits and key challenges of DTN.The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
document are to be interpreted as described in RFC 2119.With the advent of 5G, Internet of Things and Cloud Computing, the
scale of network is expanding constantly. Accordingly, the network
operation and maintenance are becoming more complex due to higher
complexity of network; and innovations on network will be more and more
difficult due to the higher risk of network failure and higher trial
cost.Digital twin is the real-time representation of physical entities in
the digital world. It has the characteristics of virtual-reality
integration and real-time interaction, iterative operation and
optimization, as well as full life-cycle, and full business data-driven.
At present, it has been successfully applied in the fields of
intelligent manufacturing, smart city, complex system operation and
maintenance .A digital twin network platform can be built by applying digital twin
technology to network and creating virtual image of physical network
facilities. Through the real-time data interaction between physical
network and twin network, the digital twin network platform can help the
network to achieve more intelligent, efficient, safe and full life-cycle
operation and maintenance.So far, there is no standard definition of digital twin network in
networking industry or SDOs. This document attempts to define Digitla
Twin Network (DTN) as a virtual representation of the physical network,
analyzing, diagnosing, simulating and controlling the physical network
based on data, model and interface, so as to achieve the real-time
interactive mapping between physical network and virtual twin network.
According to the definition, DTN contains four key elements: data,
mapping, model and interface, as shown in Figure 1.Data is cornerstone for constructing a DTN system, in which
unified data repository can be the single source of the truth and
provide timely and accurate data support.Real-time interactive mapping between physical network and
virtual twin network is the most typical feature that DTN is
different from network simulation system.Data model is the ability source of DTN. Various data models can
be designed and flexibly combined to serve various network
applications.Standardized interface is the key technique enabler, which can
effectively ensure the compatibility and scalability of DTN
system.DTN can help enable closed-loop network management across the entire
lifecycle, from digital deployment and simulation, to visualized
assessment, physical deployment, and continuous verification. In doing
so, customers are able to achieve network-wide insights, precise
planning, and rapid deployment in multiple areas, including networks,
services, users, and applications. All the benefits of DTN can be
categorized into three major types: low cost of network optimization,
intelligent network decision making, and high efficient network
innovation. The following sections describe the three types of benefits
respectively.With extremely large scale, network is becoming more and more
complex and difficult to operate. Since there is no effective platform
for simulation, traditional network optimization has to be tried on
real network directly with long time cost and high service impact
running on real network. This also greatly increases network
operator’s OpEX.With DTN platform, network operators can well simulate the
candidate optimization solutions before finally deploy them to real
network. Compared with traditional methods, this is of quite low risk
and will bring much less impact on real network. In addition, the
operator’s OpEX will be greatly decreased accordingly.Traditional network operation and management mainly focus on
deploying and managing current services, while lacking of handling
past data and predicting future status. This kind of passive and
protective maintenance is difficult to adapt to large-scale network
scenarios.DTN can combine data acquisition, big data processing and AI
modeling to achieve the assessment of current status, diagnosis of
past problems, as well as prediction of future trends, then give the
results of analysis, simulate various possibilities, and provide more
comprehensive decision support. This will help network achieve
predictive maintenance from current protective maintenance.Due to higher trial risk, real network environment is normally
unavailable to network researcher when they explore innovation
techniques. Instead, researchers have to use some offline simulation
platforms. This greatly impacts the real effectiveness of the
innovation, and greatly slow down the speed of network innovation.
Moreover, risk-averse network operators naturally reluctant to try new
technologies due to higher failure risk as well as the higher failure
cost.DTN can generate virtual twin entity of the real network. This
helps researches explore network innovation (e.g. new network
protocols, network AI/ML applications, etc.) efficiently, and helps
network operators deploy new technologies quickly with lower risks.
Take AI/ML application as example, it is a conflict between the
continuous high reliability requirement (i.e. 99.999%) of network and
the slow learning speed or phase-in learning steps of AI/ML
algorithms. With DTN platform, AI/ML can fully complete the leaning
and training with the sufficient data before deploy the model to the
real network. This will greatly encourage more network AI innovations
in future network.Implementing Intent-Based Networking (IBN) via DTN can be another
example to show how DTN improves the efficiency of deploying network
innovation. IBN is an innovative technology for life-cycle network
management. Future network will be possibly Intent-based, which means
that users can input their abstract ‘intent’ to the
network, instead of detailed policies or configurations on the network
devices.
clarifies the concept of "Intent" and provides an overview of IBN
functionalities. The key character of an IBN system is that
user’s intent can be assured automatically via continuously
adjusting the policies and validating the real-time situation. To
lower the impact on real network, several rounds of adjustment and
validation can be simulated on the DTN platform instead of directly on
physical netowrk. Therefore, DTN can be an important enabler platform
to implement IBN system and speed up the deployment of IBN in
customer’s network.So far, there is no reference or standard architecture for Digital
Twin Network in network domain. Based on the definition of key elements
of DTN described in section 2, reference architecture with three layers
of Digital Twin Network can be designed as below, shown in Figure
2.Bottom layer is Physical Network. All network elements in
physical network exchange massive network data and control with
network digital twin entity, via southbound interfaces. Physical
network can be either telecommunication operator network, or data
center network, campus network, industrial Internet of things or
other network types.Middle layer is Network Digital Twin Entity, which is the core of
DTN system. This layer includes three key subsystems: Data Sharing
Repository, Service Mapping Models and Digital Twin Entity
Management.Data Sharing Repository provides accurate and complete
information for building various service models by collecting
and updating the real-time operational data of various network
elements through the southbound interface. In addition to data
storage, Data Sharing Repository is also responsible to provide
data services for the Service Mapping Models sub-system,
including fast retrieval, concurrent conflict, batch service,
unified interface, etc.Service Mapping Models completes data-based modelling,
provides data model instances for various network applications,
and maximizes the agility and programmability of network
services. The data models include two major types: basic models
and functional models.Basic Model refers to the network element model and
network topology model of the network digital twin entity
based on the basic configuration, environment information,
operational state, link topology and other information of
the network element, to complete the real-time accurate
description of the physical network.Functional model refers to various data models such as
network analysis, simulation, diagnosis, prediction,
assurance, etc. The functional models can be constructed and
expanded by multiple dimensions: by network type, there can
be models serving for single network domain or multi network
domain; by function type, it can be divided into state
monitoring, traffic analysis, security drill, fault
diagnosis, quality assurance and other models; by
generality, it can be divided into general model and
special-purpose model. Specifically, multiple dimensions can
be combined to create a data model for more specific
application scenario.Digital Twin Entity Management completes the management
function of digital twin network, records the life-cycle of the
entity, visualizes and controls various elements of network
digital twin, including topology management, model management
and security management.Top layer is Network Application. Various applications (e.g.
Network intelligent O&M, IBN, etc.) can effectively run against
Digital Twin Network platform to implement either conventional or
innovative network operations, with low cost and less service impact
on real network. Network application provide requirements to network
digital twin entity via northbound interface; then the service is
simulated by various service model instances; after fully verified,
the change control can be deployed safely to physical network.As mentioned in above section, DTN can bring many benefits to network
management as well as network innovation. However, it is still
challenging to build an effective and efficient DTN system. The
following are the major challenges and problems.Large scale challenge: The digital twin entity of large-scale
network will significantly increase the complexity of data
acquisition and storage, the design and implementation of model. And
the requirements of software and hardware of the system will be very
high.Compatibility issue: It is difficult to establish a unified
digital twin platform with unified data model in the whole network
domain due to the inconsistency of technical implementation and
supporting functionalities of different manufacturers' devices in
the network.Data modeling difficulties: Based on large-scale network data,
data modeling should not only focus on ensuring the richness of
model functions, but also need to consider the flexibility and
scalability of the model. These requirements further increase the
difficulty of building efficient and hierarchical functional data
models.Real-time requirement: For services with high real-time
requirements, the processing of model simulation and verification
through DTN system will increase the service delay, so the function
and process of the data model need to increase the processing
mechanism under various network application scenarios; at the same
time, the real-time requirements will further increase the system
software and hardware performance requirements.Security risks: Network digital twin entity synchronizes all the
data of physical network in real time, which will increase the
security risk of user data, such as information leakage or more
vulnerable to attack.To solve the above problems and challenges, Digital Twin Network
needs continuous optimization and breakthrough on key enabling
technologies including data acquisition, data storage, data modeling,
network visualization, interface standardization, and security
assurance, so as to meet the requirements of compatibility, reliability,
real-time and security under large-scale network.The research and application of Digital Twin Network is just
beginning. This document presents an overview of the concepts and
definition of DTN. Looking forward, further researches on DTN usage
scenarios, requirements, architecture and key enabling technologies
should be promoted by the industry, so as to accelerate the
implementation and deployment of DTN in real network.TBD.This document has no requests to IANA.Digital Twin in Industry: State-of-the-Art. IEEE Transactions
on Industrial Informatics, vol. 15, no. 4.