Identifiability of linear dynamic networks

Abstract

Dynamic networks are structured interconnections of dynamical systems (modules) driven by external excitation and disturbance signals. In order to identify their dynamical properties and/or their topology consistently from measured data, we need to make sure that the network model set is identifiable. We introduce the notion of network identifiability, as a property of a parameterized model set, that ensures that different network models can be distinguished from each other when performing identification on the basis of measured data. Different from the classical notion of (parameter) identifiability, we focus on the distinction between network models in terms of their transfer functions. For a given structured model set with a pre-chosen topology, identifiability typically requires conditions on the presence and location of excitation signals, and on presence, location and correlation of disturbance signals. Because in a dynamic network, disturbances cannot always be considered to be of full-rank, the reduced-rank situation is also covered, meaning that the number of driving white noise processes can be strictly less than the number of disturbance variables. This includes the situation of having noise-free nodes.

arXiv commentProvisionally accepted for publication in Automatica

References in corpus (1)

• Network Reconstruction from Intrinsic Noise

Cited by in corpus (18)

• Prediction error identification of linear dynamic networks with rank-reduced noise
• Allocation of Excitation Signals for Generic Identifiability of Linear Dynamic Networks
• Abstractions of linear dynamic networks for input selection in local module identification
• Structure Identifiability of an NDS with LFT Parametrized Subsystems
• Optimal allocation of excitation and measurement for identification of dynamic networks
• Identification in Dynamic Networks
• Identification of diffusively coupled linear networks through structured polynomial models
• Global Structure Identifiability and Reconstructibility of an NDS with Descriptor Subsystems
• A scalable multi-step least squares method for network identification with unknown disturbance topology
• Frequency Domain Identifiability and Sloppiness of Descriptor Systems with an LFT Structure
• Network Realization Functions for Optimal Distributed Control
• Network Structure Identification from Corrupt Data Streams
• Necessary and sufficient conditions for the identifiability of isolated loops
• Excitation allocation for generic identifiability of linear dynamic networks with fixed modules
• Identification of LFT Structured Descriptor Systems with Slow and Non-uniform Sampling
• Data-informativity conditions for structured linear systems with implications for dynamic networks
• Path-Based Conditions for Local Network Identifiability -- Full Version
• Causal Structure Identification from Corrupt Data-Streams