Network Digital Twin for Iterative Route Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication networks face challenges in efficiently optimizing network configurations to adapt to changing traffic flows, often requiring manual intervention by experts, which is time-consuming and can lead to sub-optimal operation or outages.
Innovation Solution
The implementation of a Network Digital Twin (NDT) that combines an emulation model and an optimization model to iteratively determine configuration changes for network optimization, focusing on a cost function that includes link utilization and Quality of Service (QoS) metrics such as latency, loss, and jitter.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual configuration modification by experts is used to adapt to changing traffic flows, then network performance can be maintained, but the time required for optimization increases significantly
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the network that replicates its topology, traffic flows, and behavior. This virtual replica allows automated optimization algorithms to test and determine configuration changes without manual intervention, significantly reducing the time required for network optimization while maintaining performance through continuous automated adjustments.
Solution Approach 2:
The system enables automated self-optimization where the digital twin continuously monitors network conditions and automatically determines optimal configurations through iterative procedures. The optimization algorithm independently analyzes traffic patterns and adjusts network parameters without requiring expert manual intervention, transforming the network into a self-managing system.
2Adaptability or versatility
If manual configuration modification is used to respond to traffic flow changes, then network configurations can be adjusted, but operational costs increase due to expert time requirements
Solution Approach 1:
By creating a virtual replica of the network, the system enables cost-effective automated optimization. The digital twin allows multiple configuration scenarios to be tested virtually before implementation, reducing the need for expensive expert consultations and manual configuration adjustments while maintaining high adaptability to changing traffic conditions.
Solution Approach 2:
The patent replaces manual mechanical operations (expert human intervention) with automated algorithmic processes. The optimization algorithm automatically analyzes traffic flows, evaluates configuration options, and determines optimal settings, substituting human expertise with computational intelligence that operates continuously without additional operational costs.
3Productivity
If automated optimization algorithms are implemented, then optimization time is reduced, but system complexity increases
Solution Approach 1:
The digital twin simplifies the optimization process by creating a virtual model that mirrors the actual network. This copy allows complex optimization algorithms to operate in a controlled virtual environment, testing configurations without affecting real network operations. The virtual replica handles the computational complexity while the physical network remains simple and stable.
Solution Approach 2:
The system separates the optimization function into an independent digital twin component, isolating complexity from the main network infrastructure. The digital twin handles all computational optimizations separately, allowing the actual network to remain simple while benefiting from advanced automated optimization capabilities through the virtual replica.
Data Source
AI summary
Systems and methods include managing a Network Digital Twin (NDT) for a network, the NDT including an emulation model and an optimization model, wherein the emulation model is configured to emulate the network and the optimization model is configured to determine configuration changes to the network based on a cost function; performing an iterative procedure with the optimization model and the emulation model to determine one or more configuration changes to the network based on the cost function; and providing the one or more configuration changes from the iterative procedure for use in the network, where the one or more configuration changes address the cost function.