Probabilistic Network Digital Twin for Capacity Flow Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating a digital twin of a network that accurately reflects the interplay between access networks, user home networks, devices, and services is challenging, particularly for assessing capacity and bandwidth requirements and optimizing network configurations.
Innovation Solution
A digital twin system that selects parameters from probabilistic distributions for network configurations and service executions, determines data volume and flow sequences, and outputs information on data flow, replicating real-world network behaviors by incorporating network and service characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a digital twin system selects parameters from probabilistic distributions to replicate real-world network behaviors, then the accuracy of network performance simulation is improved, but the complexity of the system increases
Solution Approach 1:
The patent creates a digital twin that copies the essential behavior of real networks by selecting parameters from probabilistic distributions derived from actual network data. This copying approach captures realistic network behaviors without requiring exact replicas of complex physical systems, thereby improving simulation accuracy while managing system complexity through statistical abstraction
Solution Approach 2:
The system changes parameters from fixed deterministic values to probabilistic distributions, allowing network parameters to vary within realistic ranges observed in actual deployments. This parameter transformation enables more accurate simulation of real-world network variability and performance characteristics while maintaining manageable system complexity through mathematical modeling
2Reliability
If the digital twin incorporates detailed network and service characteristics, then the predictive capability is improved, but the difficulty of system operation increases
Solution Approach 1:
The digital twin system performs self-configuration by automatically selecting parameters from probabilistic distributions and determining data flow sequences without requiring manual input of detailed network specifications. This self-service capability improves predictive accuracy through comprehensive parameter incorporation while reducing operational difficulty by eliminating the need for users to provide extensive network technology or end-user behavior details
3Loss of information
If the system determines data flow through complex network configurations, then the information accuracy is improved, but the processing time increases
Solution Approach 1:
The system performs preliminary actions by pre-selecting network parameters from probabilistic distributions and pre-determining data volume sequences based on service characteristics before actual flow simulation. This preliminary preparation ensures accurate information capture while reducing processing time during execution, as the complex configuration work is done in advance
Data Source
Figure 1(a)
Figure 1(b)
Figure 2(a)~2(b)
AI summary
Disclosed herein is a system implementing a digital twin of a network, the system comprising: means for selecting one or more first values, wherein each first value represents a respective parameter of a configuration of the network and is selected from a probabilistic distribution associated with the respective parameter of the configuration of the network; means for selecting one or more second values, wherein each second value represents a respective parameter of a service to be executed on one or more end devices of the network and is selected from a probabilistic distribution associated with the respective parameter of the service to be executed, each service associated with transmission of one or more data packets through the network; means for determining, based on the one or more selected second values, a time sequence representing a volume of data to be injected into the network at each of one or more time intervals; means for determining, based on the one or more selected first values and the time sequence, a flow of the volume of data through the network; and means for outputting information indicative of the flow of the volume of data. A method for implementing a digital twin of a network and a computer program are also disclosed.