Abstract:
Complex dynamical networks emerge from the physical or information based interconnection of many dynamical systems. These networks display emergent behaviour that is best...Show MoreMetadata
Abstract:
Complex dynamical networks emerge from the physical or information based interconnection of many dynamical systems. These networks display emergent behaviour that is best understood through knowledge of the interconnection structure of the network. We analyze and compare a variety of existing regression techniques (some sparsity inducing and other not) with a recursive sparse estimator, presented recently by the authors, for determining this interconnection structure. In large networks the ability to recursively estimate the interconnection structure of the network may be advantageous for a number of reasons and thus this work represents a proof-of-concept that such an approach is feasible. Results comparing existing and recursive sparse regression techniques for determining the interconnection structure of a simple complex dynamical network are presented.
Published in: 2009 European Control Conference (ECC)
Date of Conference: 23-26 August 2009
Date Added to IEEE Xplore: 02 April 2015
Print ISBN:978-3-9524173-9-3