TSN Digital Twin for Dynamic TAS Customization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Time-Sensitive Networking (TSN) systems face challenges in dynamically adjusting their settings to accommodate changing network conditions, such as new applications or congestion, which affects the reliability and predictability of data packet delivery.
Innovation Solution
The implementation of digital twins in TSN networks allows for real-time monitoring and dynamic customization of the Time-Aware Scheduler (TAS) using Reinforcement Learning (RL) models. These digital twins simulate different network states, train RL models, and adjust TAS settings to optimize packet scheduling and prioritize data packets effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If TSN networks use static configurations for Time-Aware Scheduler, then device complexity is reduced, but adaptability to changing network conditions deteriorates
Solution Approach 1:
The patent creates a digital twin - a virtual copy of the TSN network - to simulate and predict the impact of configuration changes before applying them to the actual network. This allows complex adaptive configurations to be tested and optimized in the virtual environment, reducing the complexity burden on the physical network while maintaining high adaptability.
Solution Approach 2:
The system performs preliminary actions by using the digital twin to pre-calculate and simulate the effects of potential configuration changes before implementing them in the actual TSN network. This allows the network to proactively adapt to changing conditions without requiring complex real-time decision-making in the physical system.
2Adaptability or versatility
If TSN networks implement dynamic customization with digital twins and RL models, then adaptability to changing conditions improves, but device complexity increases
Solution Approach 1:
The digital twin acts as an intermediary between the complex adaptive system and the physical TSN network. It absorbs the complexity of simulating multiple scenarios and training reinforcement learning models, while presenting simplified configuration recommendations to the actual network. This mediator approach allows dynamic customization capability without directly increasing the complexity of the core network infrastructure.
3Productivity
If TSN networks adjust settings manually, then control precision is maintained, but productivity decreases due to slower response time
Solution Approach 1:
The system implements self-service automation where the digital twin continuously monitors network conditions and automatically adjusts TSN configurations based on simulated optimal performance. The reinforcement learning models enable the system to autonomously learn from network behavior and make adaptive decisions without manual intervention, significantly improving response speed while maintaining control precision through virtual validation.
Solution Approach 2:
The digital twin provides continuous feedback about the impact of configuration changes on network performance metrics such as latency, jitter, and packet loss. This feedback loop allows the system to automatically adjust settings in real-time based on actual network conditions, achieving both high productivity and precise control through automated closed-loop optimization.
Data Source
AI summary
One example method includes accessing at a Time-Aware Scheduler (TAS) of a Time-Sensitive Networking (TSN) network a plurality of data packets, where each data packet includes a data packet priority that defines an order for transmitting the plurality of data packets by the TSN network; grouping the plurality of data packets into a cluster according to the data packet priorities, the cluster identifying a first TSN network state; applying a first machine-learning model to the cluster to determine a TAS cycle policy that defines a timing schedule for data packet transmission in the TSN network; and providing the TAS cycle policy to components of the TSN network.