Andrea Munari

Federico Chiariotti, Fabio Saggese, Andrea Munari et al.

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.

Yu Heng Wu, Houman Asgari, Stefano Rini et al.

This paper studies the problem of federated training of a deep neural network (DNN) over a random access channel (RACH) such as in computer networks, wireless networks, and cellular systems. More precisely, a set of remote users participate in training a centralized DNN model using SGD under the coordination of a parameter server (PS). The local model updates are transmitted from the remote users to the PS over a RACH using a slotted ALOHA protocol. The PS collects the updates from the remote users, accumulates them, and sends central model updates to the users at regular time intervals. We refer to this setting as the RACH-FL setting. The RACH-FL setting crucially addresses the problem of jointly designing a (i) client selection and (ii) gradient compression strategy which addresses the communication constraints between the remote users and the PS when transmission occurs over a RACH. For the RACH-FL setting, we propose a policy, which we term the ''age-of-gradient'' (AoG) policy in which (i) gradient sparsification is performed using top-K sparsification, (ii) the error correction is performed using memory accumulation, and (iii) the slot transmission probability is obtained by comparing the current local memory magnitude minus the magnitude of the gradient update to a threshold. Intuitively, the AoG measure of ''freshness'' of the memory state is reminiscent of the concept of age-of-information (AoI) in the context of communication theory and provides a rather natural interpretation of this policy. Numerical simulations show the superior performance of the AoG policy as compared to other RACH-FL policies.