Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Event-Triggered Learning for Resource-Efficient Networked Control

: Solowjow, Friedrich; Baumann, Dominik; Garcke, Jochen; Trimpe, Sebastian

Fulltext ()

Institute of Electrical and Electronics Engineers -IEEE-:
Annual American Control Conference, ACC 2018 : Milwaukee, Wisconsin, USA 27-29 June 2018
Red Hook, NY: Curran, 2018
ISBN: 978-1-5386-5429-3
ISBN: 978-1-5386-5428-6
ISBN: 978-1-5386-5427-9
pp.6506-6512 (Vol.9)
American Control Conference (ACC) <2018, Milwaukee/Wiss.>
Conference Paper, Electronic Publication
Fraunhofer SCAI ()

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.