Event-triggered Learning for Resource-efficient Networked Control

TL;DR

This paper introduces event-triggered learning to enhance resource efficiency in networked control by adaptively updating models only when communication performance degrades, thus reducing unnecessary data transmission.

Contribution

It proposes a novel event-triggered learning method that triggers model updates based on communication performance, improving robustness and reducing communication in networked control systems.

Findings

Event-triggered learning reduces communication more effectively than traditional ETSE.

The trigger mechanism is proven to activate only when necessary, based on statistical analysis.

Experiments show improved robustness and lower communication rates.

Abstract

Common event-triggered state estimation (ETSE) algorithms save communication in networked control systems by predicting agents' behavior, and transmitting updates only when the predictions deviate significantly. The effectiveness in reducing communication thus heavily depends on the quality of the dynamics models used to predict the agents' states or measurements. Event-triggered learning is proposed herein as a novel concept to further reduce communication: whenever poor communication performance is detected, an identification experiment is triggered and an improved prediction model learned from data. Effective learning triggers are obtained by comparing the actual communication rate with the one that is expected based on the current model. By analyzing statistical properties of the inter-communication times and leveraging powerful convergence results, the proposed trigger is proven to limit learning experiments to the necessary instants. Numerical and physical experiments demonstrate that event-triggered learning improves robustness toward changing environments and yields lower communication rates than common ETSE.