TY - JOUR

T1 - Hierarchical event-triggered learning for cyclically excited systems with application to wireless sensor networks

AU - Beuchert, Jonas

AU - Solowjow, Friedrich

AU - Raisch, Jörg

AU - Trimpe, Sebastian

AU - Seel, Thomas

N1 - Funding Information: The work of F. Solowjow and S. Trimpe was supported in part by the Max Planck Society, in part by the Cyber Valley Initiative, and in part by the International Max Planck Research School for Intelligent Systems (IMPRS-IS).

PY - 2019/6/10

Y1 - 2019/6/10

N2 - Communication load is a limiting factor in many real-time systems. Event-triggered state estimation and event-triggered learning (ETL) methods reduce network communication by sending information only when it cannot be adequately predicted based on previously transmitted data. This letter proposes an ETL approach for nonlinear discrete-time systems with cyclic excitation. The method automatically recognizes cyclic patterns in data - even when they change repeatedly - and reduces communication load whenever the current data can be accurately predicted from previous cycles. Nonetheless, a bounded error between original and received signal is guaranteed. The cyclic excitation model, which is used for predictions, is updated hierarchically, i.e., a full model update is only performed if updating a small number of model parameters is not sufficient. A nonparametric statistical test enforces that model updates happen only if the cyclic excitation changed with high probability. The effectiveness of the proposed methods is demonstrated using the application example of wireless real-time pitch angle measurements of a human foot in a feedback-controlled neuroprosthesis. The experimental results show that communication load can be reduced by 70% while the root-mean-square error between measured and received angle is less than 1°.

AB - Communication load is a limiting factor in many real-time systems. Event-triggered state estimation and event-triggered learning (ETL) methods reduce network communication by sending information only when it cannot be adequately predicted based on previously transmitted data. This letter proposes an ETL approach for nonlinear discrete-time systems with cyclic excitation. The method automatically recognizes cyclic patterns in data - even when they change repeatedly - and reduces communication load whenever the current data can be accurately predicted from previous cycles. Nonetheless, a bounded error between original and received signal is guaranteed. The cyclic excitation model, which is used for predictions, is updated hierarchically, i.e., a full model update is only performed if updating a small number of model parameters is not sufficient. A nonparametric statistical test enforces that model updates happen only if the cyclic excitation changed with high probability. The effectiveness of the proposed methods is demonstrated using the application example of wireless real-time pitch angle measurements of a human foot in a feedback-controlled neuroprosthesis. The experimental results show that communication load can be reduced by 70% while the root-mean-square error between measured and received angle is less than 1°.

U2 - 10.48550/arXiv.1906.03211

DO - 10.48550/arXiv.1906.03211

M3 - Article

VL - 4

SP - 103

EP - 108

JO - IEEE Control Systems Letters

JF - IEEE Control Systems Letters

IS - 1

ER -