Physics informed topology learning in networks of linear dynamical systems

Saurav Talukdar; Deepjyoti Deka; Harish Doddi; Donatello Materassi; Michael Chertkov; Murti V. Salapaka

doi:10.1016/j.automatica.2019.108705

Physics informed topology learning in networks of linear dynamical systems

Saurav Talukdar, Deepjyoti Deka, Harish Doddi, Donatello Materassi, Michael Chertkov, Murti V. Salapaka

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

Learning influence pathways in a network of dynamically related processes from observations is of considerable importance in many disciplines. In this article, influence networks of agents which interact dynamically via linear dependencies are considered. An algorithm for the reconstruction of the topology of interaction based on multivariate Wiener filtering is analyzed. It is shown that for a vast and important class of interactions, that includes physical systems with flow conservation, the topology of the interactions can be exactly recovered, even for colored exogenous inputs. The efficacy of the approach is illustrated through simulation and experiments on multiple important networks, including consensus networks, IEEE power networks and EnergyPlus based simulation of thermal dynamics of buildings.

Original language	English (US)
Article number	108705
Journal	Automatica
Volume	112
DOIs	https://doi.org/10.1016/j.automatica.2019.108705
State	Published - Feb 2020

Bibliographical note

Funding Information:
The authors S. Talukdar, H. Doddi, D. Materassi and M.V. Salapaka acknowledge the support of ARPA-E for supporting this research through the project titled ‘A Robust Distributed Framework for Flexible Power Grids’ via Grant No. DEAR000071 . Authors D. Deka and M. Chertkov acknowledge the support from the Department of Energy through the Grid Modernization Lab Consortium, and the Center for Non Linear Studies (CNLS) at Los Alamos National Laboratory . The material in this paper was presented at the Eighth ACM International Conference on Future Energy Systems, May 16–19, 2017, Shatin, Hong Kong, China; the 56th IEEE Conference on Decision and Control, December 12–15, 2017, Melbourne, Australia; the 57th IEEE Conference on Decision and Control, December 17–19, 2018, Miami Beach, Florida, USA. This paper was recommended for publication in revised form by Associate Editor Julien M. Hendrickx under the direction of Editor Christos G. Cassandras

Publisher Copyright:
© 2019

Keywords

Graphical models
Networks
Structure learning of time series
Topology learning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access

10.1016/j.automatica.2019.108705

OpenUrl availability

Full text

Cite this

@article{0b7032eff51a4d65a198578ac5ab4380,

title = "Physics informed topology learning in networks of linear dynamical systems",

abstract = "Learning influence pathways in a network of dynamically related processes from observations is of considerable importance in many disciplines. In this article, influence networks of agents which interact dynamically via linear dependencies are considered. An algorithm for the reconstruction of the topology of interaction based on multivariate Wiener filtering is analyzed. It is shown that for a vast and important class of interactions, that includes physical systems with flow conservation, the topology of the interactions can be exactly recovered, even for colored exogenous inputs. The efficacy of the approach is illustrated through simulation and experiments on multiple important networks, including consensus networks, IEEE power networks and EnergyPlus based simulation of thermal dynamics of buildings.",

keywords = "Graphical models, Networks, Structure learning of time series, Topology learning",

author = "Saurav Talukdar and Deepjyoti Deka and Harish Doddi and Donatello Materassi and Michael Chertkov and Salapaka, {Murti V.}",

note = "Funding Information: The authors S. Talukdar, H. Doddi, D. Materassi and M.V. Salapaka acknowledge the support of ARPA-E for supporting this research through the project titled {\textquoteleft}A Robust Distributed Framework for Flexible Power Grids{\textquoteright} via Grant No. DEAR000071 . Authors D. Deka and M. Chertkov acknowledge the support from the Department of Energy through the Grid Modernization Lab Consortium, and the Center for Non Linear Studies (CNLS) at Los Alamos National Laboratory . The material in this paper was presented at the Eighth ACM International Conference on Future Energy Systems, May 16–19, 2017, Shatin, Hong Kong, China; the 56th IEEE Conference on Decision and Control, December 12–15, 2017, Melbourne, Australia; the 57th IEEE Conference on Decision and Control, December 17–19, 2018, Miami Beach, Florida, USA. This paper was recommended for publication in revised form by Associate Editor Julien M. Hendrickx under the direction of Editor Christos G. Cassandras Publisher Copyright: {\textcopyright} 2019",

year = "2020",

month = feb,

doi = "10.1016/j.automatica.2019.108705",

language = "English (US)",

volume = "112",

journal = "Automatica",

issn = "0005-1098",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Physics informed topology learning in networks of linear dynamical systems

AU - Talukdar, Saurav

AU - Deka, Deepjyoti

AU - Doddi, Harish

AU - Materassi, Donatello

AU - Chertkov, Michael

AU - Salapaka, Murti V.

N1 - Funding Information: The authors S. Talukdar, H. Doddi, D. Materassi and M.V. Salapaka acknowledge the support of ARPA-E for supporting this research through the project titled ‘A Robust Distributed Framework for Flexible Power Grids’ via Grant No. DEAR000071 . Authors D. Deka and M. Chertkov acknowledge the support from the Department of Energy through the Grid Modernization Lab Consortium, and the Center for Non Linear Studies (CNLS) at Los Alamos National Laboratory . The material in this paper was presented at the Eighth ACM International Conference on Future Energy Systems, May 16–19, 2017, Shatin, Hong Kong, China; the 56th IEEE Conference on Decision and Control, December 12–15, 2017, Melbourne, Australia; the 57th IEEE Conference on Decision and Control, December 17–19, 2018, Miami Beach, Florida, USA. This paper was recommended for publication in revised form by Associate Editor Julien M. Hendrickx under the direction of Editor Christos G. Cassandras Publisher Copyright: © 2019

PY - 2020/2

Y1 - 2020/2

N2 - Learning influence pathways in a network of dynamically related processes from observations is of considerable importance in many disciplines. In this article, influence networks of agents which interact dynamically via linear dependencies are considered. An algorithm for the reconstruction of the topology of interaction based on multivariate Wiener filtering is analyzed. It is shown that for a vast and important class of interactions, that includes physical systems with flow conservation, the topology of the interactions can be exactly recovered, even for colored exogenous inputs. The efficacy of the approach is illustrated through simulation and experiments on multiple important networks, including consensus networks, IEEE power networks and EnergyPlus based simulation of thermal dynamics of buildings.

AB - Learning influence pathways in a network of dynamically related processes from observations is of considerable importance in many disciplines. In this article, influence networks of agents which interact dynamically via linear dependencies are considered. An algorithm for the reconstruction of the topology of interaction based on multivariate Wiener filtering is analyzed. It is shown that for a vast and important class of interactions, that includes physical systems with flow conservation, the topology of the interactions can be exactly recovered, even for colored exogenous inputs. The efficacy of the approach is illustrated through simulation and experiments on multiple important networks, including consensus networks, IEEE power networks and EnergyPlus based simulation of thermal dynamics of buildings.

KW - Graphical models

KW - Networks

KW - Structure learning of time series

KW - Topology learning

UR - http://www.scopus.com/inward/record.url?scp=85075480191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075480191&partnerID=8YFLogxK

U2 - 10.1016/j.automatica.2019.108705

DO - 10.1016/j.automatica.2019.108705

M3 - Article

AN - SCOPUS:85075480191

SN - 0005-1098

VL - 112

JO - Automatica

JF - Automatica

M1 - 108705

ER -

Physics informed topology learning in networks of linear dynamical systems

Abstract

Bibliographical note

Keywords

UN SDGs

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this