Data-driven topology estimation

Yang Weng, Christos Faloutsos, Marija D. Ilić

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper is motivated by major needs for fast and accurate on-line data analysis tools in the emerging electric energy systems, due to the recent penetration of distributed green energy, distributed intelligence, and plug-in electric vehicles. Instead of taking the traditional complex physical model based approach, this paper proposes a data-driven method, leading to an effective topology estimation approach for the smart grid. Specifically, we first introduce the data-driven topology estimation problem. Then, a novel Logistic Kernel Regression is proposed in a Bayesian framework based on Nearest Neighbors search. Notably, unlike many machine learning approaches that do not account for physical constraints, and distinctive from deterministic engineering modeling defined solely by physical laws, this paper for the first time combines the two into one single regression modeling for topology estimation. Simulation results of the proposed method show that the new method produces a topology estimate excelling the current industrial approach. Finally, the proposed method can be implemented given recent advances in machine learning, which are becoming drivers and sources of data previously unavailable in the electric power industry.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages560-565
Number of pages6
ISBN (Electronic)9781479949342
DOIs
StatePublished - Jan 1 2015
Externally publishedYes
Event2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014 - Venice, Italy
Duration: Nov 3 2014Nov 6 2014

Other

Other2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014
CountryItaly
CityVenice
Period11/3/1411/6/14

Fingerprint

Topology
Learning systems
electric power industry
energy
regression
electric vehicle
learning
Logistics
intelligence
data analysis
driver
logistics
engineering
simulation
Law
Industry

ASJC Scopus subject areas

  • Communication
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Weng, Y., Faloutsos, C., & Ilić, M. D. (2015). Data-driven topology estimation. In 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014 (pp. 560-565). [7007706] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SmartGridComm.2014.7007706

Data-driven topology estimation. / Weng, Yang; Faloutsos, Christos; Ilić, Marija D.

2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 560-565 7007706.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Weng, Y, Faloutsos, C & Ilić, MD 2015, Data-driven topology estimation. in 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014., 7007706, Institute of Electrical and Electronics Engineers Inc., pp. 560-565, 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014, Venice, Italy, 11/3/14. https://doi.org/10.1109/SmartGridComm.2014.7007706
Weng Y, Faloutsos C, Ilić MD. Data-driven topology estimation. In 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014. Institute of Electrical and Electronics Engineers Inc. 2015. p. 560-565. 7007706 https://doi.org/10.1109/SmartGridComm.2014.7007706
Weng, Yang ; Faloutsos, Christos ; Ilić, Marija D. / Data-driven topology estimation. 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 560-565
@inproceedings{5fd9f4af70484870a628ed7f7e533055,
title = "Data-driven topology estimation",
abstract = "This paper is motivated by major needs for fast and accurate on-line data analysis tools in the emerging electric energy systems, due to the recent penetration of distributed green energy, distributed intelligence, and plug-in electric vehicles. Instead of taking the traditional complex physical model based approach, this paper proposes a data-driven method, leading to an effective topology estimation approach for the smart grid. Specifically, we first introduce the data-driven topology estimation problem. Then, a novel Logistic Kernel Regression is proposed in a Bayesian framework based on Nearest Neighbors search. Notably, unlike many machine learning approaches that do not account for physical constraints, and distinctive from deterministic engineering modeling defined solely by physical laws, this paper for the first time combines the two into one single regression modeling for topology estimation. Simulation results of the proposed method show that the new method produces a topology estimate excelling the current industrial approach. Finally, the proposed method can be implemented given recent advances in machine learning, which are becoming drivers and sources of data previously unavailable in the electric power industry.",
author = "Yang Weng and Christos Faloutsos and Ilić, {Marija D.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/SmartGridComm.2014.7007706",
language = "English (US)",
pages = "560--565",
booktitle = "2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Data-driven topology estimation

AU - Weng, Yang

AU - Faloutsos, Christos

AU - Ilić, Marija D.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - This paper is motivated by major needs for fast and accurate on-line data analysis tools in the emerging electric energy systems, due to the recent penetration of distributed green energy, distributed intelligence, and plug-in electric vehicles. Instead of taking the traditional complex physical model based approach, this paper proposes a data-driven method, leading to an effective topology estimation approach for the smart grid. Specifically, we first introduce the data-driven topology estimation problem. Then, a novel Logistic Kernel Regression is proposed in a Bayesian framework based on Nearest Neighbors search. Notably, unlike many machine learning approaches that do not account for physical constraints, and distinctive from deterministic engineering modeling defined solely by physical laws, this paper for the first time combines the two into one single regression modeling for topology estimation. Simulation results of the proposed method show that the new method produces a topology estimate excelling the current industrial approach. Finally, the proposed method can be implemented given recent advances in machine learning, which are becoming drivers and sources of data previously unavailable in the electric power industry.

AB - This paper is motivated by major needs for fast and accurate on-line data analysis tools in the emerging electric energy systems, due to the recent penetration of distributed green energy, distributed intelligence, and plug-in electric vehicles. Instead of taking the traditional complex physical model based approach, this paper proposes a data-driven method, leading to an effective topology estimation approach for the smart grid. Specifically, we first introduce the data-driven topology estimation problem. Then, a novel Logistic Kernel Regression is proposed in a Bayesian framework based on Nearest Neighbors search. Notably, unlike many machine learning approaches that do not account for physical constraints, and distinctive from deterministic engineering modeling defined solely by physical laws, this paper for the first time combines the two into one single regression modeling for topology estimation. Simulation results of the proposed method show that the new method produces a topology estimate excelling the current industrial approach. Finally, the proposed method can be implemented given recent advances in machine learning, which are becoming drivers and sources of data previously unavailable in the electric power industry.

UR - http://www.scopus.com/inward/record.url?scp=84922424396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922424396&partnerID=8YFLogxK

U2 - 10.1109/SmartGridComm.2014.7007706

DO - 10.1109/SmartGridComm.2014.7007706

M3 - Conference contribution

SP - 560

EP - 565

BT - 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -