Online Edge Flow Imputation on Networks

Rohan Money; Joshin Krishnan; Baltasar Beferull-Lozano; Elvin Isufi

doi:10.1109/LSP.2022.3221846

Online Edge Flow Imputation on Networks

Rohan Money, Joshin Krishnan, Baltasar Beferull-Lozano, Elvin Isufi

Multimedia Computing

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

3 Citations (Scopus)

22 Downloads (Pure)

Abstract

An online algorithm for missing data imputation for networks with signals defined on the edges is presented. Leveraging the prior knowledge intrinsic to real-world networks, we propose a bi-level optimization scheme that exploits the causal dependencies and the flow conservation, respectively via <italic>(i)</italic> a sparse line graph identification strategy based on a group-Lasso and <italic>(ii)</italic> a Kalman filtering-based signal reconstruction strategy developed using simplicial complex (SC) formulation. The advantages of this first SC-based attempt for time-varying signal imputation have been demonstrated through numerical experiments using EPANET models of both synthetic and real water distribution networks.

Original language	English
Pages (from-to)	115-119
Number of pages	5
Journal	IEEE Signal Processing Letters
Volume	30
DOIs	https://doi.org/10.1109/LSP.2022.3221846
Publication status	Published - 2022

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Kalman filters
Laplace equations
Line Graph
Missing Flow Imputation
Optimization
Reactive power
Signal processing algorithms
Signal reconstruction
Simplicial Complex
Time series analysis
Topological Signal Processing

Access to Document

10.1109/LSP.2022.3221846

Online_Edge_Flow_Imputation_on_NetworksFinal published version, 931 KB

Cite this

@article{1a75ec152a3740e398fadbdeff906d2a,

title = "Online Edge Flow Imputation on Networks",

abstract = "An online algorithm for missing data imputation for networks with signals defined on the edges is presented. Leveraging the prior knowledge intrinsic to real-world networks, we propose a bi-level optimization scheme that exploits the causal dependencies and the flow conservation, respectively via (i) a sparse line graph identification strategy based on a group-Lasso and (ii) a Kalman filtering-based signal reconstruction strategy developed using simplicial complex (SC) formulation. The advantages of this first SC-based attempt for time-varying signal imputation have been demonstrated through numerical experiments using EPANET models of both synthetic and real water distribution networks.",

keywords = "Kalman filters, Laplace equations, Line Graph, Missing Flow Imputation, Optimization, Reactive power, Signal processing algorithms, Signal reconstruction, Simplicial Complex, Time series analysis, Topological Signal Processing",

author = "Rohan Money and Joshin Krishnan and Baltasar Beferull-Lozano and Elvin Isufi",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ",

year = "2022",

doi = "10.1109/LSP.2022.3221846",

language = "English",

volume = "30",

pages = "115--119",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "IEEE",

}

TY - JOUR

T1 - Online Edge Flow Imputation on Networks

AU - Money, Rohan

AU - Krishnan, Joshin

AU - Beferull-Lozano, Baltasar

AU - Isufi, Elvin

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - An online algorithm for missing data imputation for networks with signals defined on the edges is presented. Leveraging the prior knowledge intrinsic to real-world networks, we propose a bi-level optimization scheme that exploits the causal dependencies and the flow conservation, respectively via (i) a sparse line graph identification strategy based on a group-Lasso and (ii) a Kalman filtering-based signal reconstruction strategy developed using simplicial complex (SC) formulation. The advantages of this first SC-based attempt for time-varying signal imputation have been demonstrated through numerical experiments using EPANET models of both synthetic and real water distribution networks.

AB - An online algorithm for missing data imputation for networks with signals defined on the edges is presented. Leveraging the prior knowledge intrinsic to real-world networks, we propose a bi-level optimization scheme that exploits the causal dependencies and the flow conservation, respectively via (i) a sparse line graph identification strategy based on a group-Lasso and (ii) a Kalman filtering-based signal reconstruction strategy developed using simplicial complex (SC) formulation. The advantages of this first SC-based attempt for time-varying signal imputation have been demonstrated through numerical experiments using EPANET models of both synthetic and real water distribution networks.

KW - Kalman filters

KW - Laplace equations

KW - Line Graph

KW - Missing Flow Imputation

KW - Optimization

KW - Reactive power

KW - Signal processing algorithms

KW - Signal reconstruction

KW - Simplicial Complex

KW - Time series analysis

KW - Topological Signal Processing

UR - http://www.scopus.com/inward/record.url?scp=85142858185&partnerID=8YFLogxK

U2 - 10.1109/LSP.2022.3221846

DO - 10.1109/LSP.2022.3221846

M3 - Article

AN - SCOPUS:85142858185

SN - 1070-9908

VL - 30

SP - 115

EP - 119

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

ER -

Online Edge Flow Imputation on Networks

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this