Adaptive accelerated proximal gradient algorithm for auto-regressive exogenous models with outliers

This study introduces an enhanced recursive least-squares algorithm that applies the adaptive accelerated proximal gradient method to identify Auto-Regressive Exogenous models with output outliers. First, the outlier problem was converted into a robust principal component analysis problem. The adapt...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied mathematical modelling Jg. 133; S. 310 - 326
Hauptverfasser: Ji, Xixi, Chen, Jing, Liu, Qiang, Zhu, Quanmin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.09.2024
Schlagworte:
Adaptive accelerated proximal gradient
Convergence properties
Outputs with outliers
Recursive identification
State of charge
Unbiased parameter estimate
Adaptive accelerated proximal gradient
Recursive identification
Unbiased parameter estimate
State of charge
Outputs with outliers
Convergence properties
ISSN:0307-904X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study introduces an enhanced recursive least-squares algorithm that applies the adaptive accelerated proximal gradient method to identify Auto-Regressive Exogenous models with output outliers. First, the outlier problem was converted into a robust principal component analysis problem. The adaptive accelerated proximal gradient method is then introduced to recover the information matrix, and the recursive least squares algorithm is applied to estimate the model parameters. Furthermore, we demonstrated that the parameter estimation is unbiased and that the parameter estimation error converges to zero under persistent excitation. A series of bench tests consistently highlighted the practicality and effectiveness of the proposed algorithm. •The accelerated proximal gradient algorithm is introduced for effective outlier recovery.•The proposed adaptive accelerated proximal gradient algorithm can adaptively adjust the step-size.•A comprehensive framework is established by integrating accelerated proximal gradient and recursive least squares algorithms.•The proposed algorithm is validated through a state of charge estimation problem, demonstrating its effectiveness.
ISSN:0307-904X
DOI:10.1016/j.apm.2024.05.017