Digital Twin Network Analytics for Confidence and Delivery Time

Solution Overview

Problem

Existing wireless communication systems face challenges in providing network analytics with the required confidence level and time frame, leading to errors and the need for consumers to switch to different functions, without mechanisms to ensure accuracy or improve confidence levels.

Innovation Solution

Implementing a Digital Twin Controller Function (DTCF) within the 5G Core Network to create and manage digital twins, allowing network analytics functions to collect additional data and verify accuracy through simulations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If network analytics function collects more data to meet confidence level, then analytics accuracy improves, but time to deliver analytics increases

Engineering Contradiction:

Improveanalytics confidence levelVSAvoidtime to deliver analytics

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent creates digital twin instances that are virtual copies of physical network resources. These digital twins generate synthetic data that mirrors real network behavior, allowing the analytics function to obtain additional data samples without waiting for actual network data collection. This copying approach enables meeting confidence level requirements while maintaining delivery timeframes, as the digital twins can generate data on-demand rather than waiting for real network observations.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system pre-creates and maintains digital twin instances that continuously generate synthetic network data in advance. By having these digital twins ready beforehand and continuously producing data, the analytics function has immediate access to additional data samples when needed, eliminating the delay that would occur from collecting real network data in real-time while still achieving the required confidence levels.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If network analytics function uses limited data, then delivery time is reduced, but confidence level cannot be met

Engineering Contradiction:

Improveanalytics delivery speedVSAvoidanalytics confidence level

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent creates digital twin instances that are virtual copies of physical network resources. These digital twins generate synthetic data that mirrors real network behavior, allowing the analytics function to obtain additional data samples without waiting for actual network data collection. This copying approach enables meeting confidence level requirements while maintaining delivery timeframes, as the digital twins can generate data on-demand rather than waiting for real network observations.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The digital twin instances act as intermediaries between the physical network resources and the analytics function. Instead of the analytics function directly collecting data from physical networks (which is time-consuming), the digital twins serve as intermediate data sources that provide synthetic data samples rapidly, bridging the gap between speed requirements and confidence level requirements.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If digital twin instances are created to provide additional data, then data availability improves, but system complexity increases

Engineering Contradiction:

Improvedata availabilityVSAvoidsystem complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The digital twin instances are designed to be multi-functional, serving as both virtual representations of physical network resources and as data generation sources for analytics. This universal design allows the same digital twin infrastructure to support multiple analytics functions and use cases, reducing overall system complexity compared to creating separate specialized systems for each analytics need.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent creates digital twin instances that are virtual copies of physical network resources. These digital twins generate synthetic data that mirrors real network behavior, allowing the analytics function to obtain additional data samples without waiting for actual network data collection. This copying approach enables meeting confidence level requirements while maintaining delivery timeframes, as the digital twins can generate data on-demand rather than waiting for real network observations.

Inventive Principle:

Principle #26Copying

Data Source

PatentEP4466836B1Improving confidence of network analytics using a digital twin

Publication Date: 2025.11.12 LENOVO (SINGAPORE) PTE LTD

Figure 1
Figure 2
Figure 3

AI summary

Apparatuses, methods, and systems are disclosed for improving confidence of network analytics using a digital twin. An apparatus (800) includes a transceiver (825) that receives a request for analytics that includes a threshold minimum confidence level for the analytics and a specified time period for delivering the analytics and a processor (805) that determines a set of additional data to use for satisfying the threshold minimum confidence level available from a set of physical network resources associated with at least one digital twin instance. The transceiver (825) receives the set of additional data from the at least one digital twin instance and delivers the analytics at the specified time period in response to the analytics, derived based on the set of additional data from the at least one digital twin instance, satisfying the threshold minimum confidence level.