Identification of Switched Autoregressive and Switched Autoregressive Exogenous Systems from Large Noisy Data Sets

TL;DR

This paper presents new methods for identifying coefficients of switched autoregressive systems from large noisy datasets, effective even with limited noise distribution info and high measurement noise, outperforming previous computationally intensive approaches.

Contribution

The paper introduces novel identification algorithms for switched autoregressive models that handle large noise and partial noise distribution info, reducing computational complexity.

Findings

Effective with large datasets and high noise levels

Outperforms polynomial and mixed-integer optimization methods

Validated with academic examples

Abstract

The paper introduces novel methodologies for the identification of coefficients of switched autoregressive and switched autoregressive exogenous linear models. We consider cases which system's outputs are contaminated by possibly large values of noise for the both case of measurement noise in switched autoregressive models and process noise in switched autoregressive exogenous models. It is assumed that only partial information on the probability distribution of the noise is available. Given input-output data, we aim at identifying switched system coefficients and parameters of the distribution of the noise, which are compatible with the collected data. We demonstrate the efficiency of the proposed approach with several academic examples. The method is shown to be extremely effective in the situations where a large number of measurements is available; cases in which previous approaches based on polynomial or mixed-integer optimization cannot be applied due to very large computational burden.