Distributed Sparse Identification for Stochastic Dynamic Systems under Cooperative Non-Persistent Excitation Condition

TL;DR

This paper introduces a distributed sparse identification algorithm for stochastic dynamic systems in sensor networks, achieving accurate estimation under cooperative non-persistent excitation without relying on independence assumptions.

Contribution

It proposes a novel distributed sparse least squares algorithm with finite-set convergence under non-persistent excitation, extending applicability to stochastic feedback systems.

Findings

Estimation error bounds are derived.

The algorithm converges with finite observations.

Numerical simulations validate theoretical results.

Abstract

This paper considers the distributed sparse identification problem over wireless sensor networks such that all sensors cooperatively estimate the unknown sparse parameter vector of stochastic dynamic systems by using the local information from neighbors. A distributed sparse least squares algorithm is proposed by minimizing a local information criterion formulated as a linear combination of accumulative local estimation error and L_1-regularization term. The upper bounds of the estimation error and the regret of the adaptive predictor of the proposed algorithm are presented. Furthermore, by designing a suitable adaptive weighting coefficient based on the local observation data, the set convergence of zero elements with a finite number of observations is obtained under a cooperative non-persistent excitation condition. It is shown that the proposed distributed algorithm can work well in a cooperative way even though none of the individual sensors can fulfill the estimation task. Our theoretical results are obtained without relying on the independency assumptions of regression signals that have been commonly used in the existing literature. Thus, our results are expected to be applied to stochastic feedback systems. Finally, the numerical simulations are provided to demonstrate the effectiveness of our theoretical results.