A Combined Push-Pull Access Framework for Digital Twin Alignment and Anomaly Reporting
It addresses the trade-off between digital twin alignment and anomaly detection for real-time systems, offering a practical improvement over existing methods.
The paper proposes a push-pull scheduler (PPS) for digital twins that balances model alignment and anomaly reporting, reducing model drift by over 20% compared to state-of-the-art and cutting worst-case anomaly detection age of incorrect information from 70 ms to 30 ms under the same drift constraint.
A digital twin (DT) contains a set of virtual models of real systems that are synchronized to their physical counterparts. This enables quick experimentation, simulating the consequences of decisions in real time. However, the DT's accuracy depends on timely updates that maintain alignment with the real system. We can distinguish between: (i) pull-updates, which follow a request from the DT to the sensors, to decrease its drift from the physical state; (ii) push-updates, which contain anomalies and are sent proactively by the sensors. In this work, we devise a push-pull scheduler (PPS) to integrate the two types of updates and dynamically allocate resources. Our scheme strikes a balance in the trade-off between DT alignment in normal conditions and anomaly reporting, reducing model drift by over 20% with respect to state-of-the-art solutions, while maintaining the same anomaly detection guarantees, as well as reducing the worst-case anomaly detection age of incorrect information (AoII) from 70 ms to 30 ms under the same drift constraint.