Maximum Likelihood Estimation for System Identification of Networks of Dynamical Systems

TL;DR

This paper presents a maximum likelihood estimation method for identifying networks of dynamical systems, demonstrating its consistency, efficiency, and broader applicability, even with partial measurements, and offering a predictor-free formulation for computational efficiency.

Contribution

It introduces a novel maximum likelihood approach for network system identification that is consistent, efficient, and applicable with incomplete data, without requiring a predictor.

Findings

Method is consistent and efficient.

Applicable even with missing node measurements.

Formulation allows for computationally efficient solutions.

Abstract

This paper investigates maximum likelihood estimation for direct system identification in networks of dynamical systems. We establish that the proposed approach is both consistent and efficient. In addition, it is more generally applicable than existing methods, since it can be employed even when measurements are unavailable for all network nodes, provided that network identifiability is satisfied. Finally, we demonstrate that the maximum likelihood problem can be formulated without relying on a predictor, which is key to achieving computationally efficient numerical solutions.