New multivariate linear regression real and reactive branch flow models for volatile scenarios

Sashirekha Appalasamy, Owen Dafydd Jones, Noor Hasnah Moin, Tan Ching Sin

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

Abstract

Nonlinearity of power flow equations is one of the major underlying factors in a power systems operation complexity. The need for a robust and less complex models rises in a volatile, dynamic and real time scenario. This paper introduces new empirical models using multivariate linear regression (MLR) methods with least squares for both real and reactive branch flows. The models do not make prior assumptions and do not depend on a particular base case. Instead they are trained on either simulated or historical data. Tests using the IEEE 14 bus system show that given similar input variables to DC models, the MLR models performs significantly better. They also show that the MLR models have good prediction accuracy in scenarios with high volatility.

Original languageEnglish
Title of host publication2015 IEEE Power and Energy Society General Meeting, PESGM 2015
PublisherIEEE Computer Society
ISBN (Electronic)9781467380409
DOIs
Publication statusPublished - 30 Sep 2015
EventIEEE Power and Energy Society General Meeting, PESGM 2015 - Denver, United States
Duration: 26 Jul 201530 Jul 2015

Publication series

NameIEEE Power and Energy Society General Meeting
Volume2015-September
ISSN (Print)1944-9925
ISSN (Electronic)1944-9933

Other

OtherIEEE Power and Energy Society General Meeting, PESGM 2015
CountryUnited States
CityDenver
Period26/07/1530/07/15

Fingerprint

Linear regression

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Nuclear Energy and Engineering
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering

Cite this

Appalasamy, S., Jones, O. D., Moin, N. H., & Sin, T. C. (2015). New multivariate linear regression real and reactive branch flow models for volatile scenarios. In 2015 IEEE Power and Energy Society General Meeting, PESGM 2015 [7285669] (IEEE Power and Energy Society General Meeting; Vol. 2015-September). IEEE Computer Society. https://doi.org/10.1109/PESGM.2015.7285669
Appalasamy, Sashirekha ; Jones, Owen Dafydd ; Moin, Noor Hasnah ; Sin, Tan Ching. / New multivariate linear regression real and reactive branch flow models for volatile scenarios. 2015 IEEE Power and Energy Society General Meeting, PESGM 2015. IEEE Computer Society, 2015. (IEEE Power and Energy Society General Meeting).
@inproceedings{89714c15f6c94088b52aec003c290e83,
title = "New multivariate linear regression real and reactive branch flow models for volatile scenarios",
abstract = "Nonlinearity of power flow equations is one of the major underlying factors in a power systems operation complexity. The need for a robust and less complex models rises in a volatile, dynamic and real time scenario. This paper introduces new empirical models using multivariate linear regression (MLR) methods with least squares for both real and reactive branch flows. The models do not make prior assumptions and do not depend on a particular base case. Instead they are trained on either simulated or historical data. Tests using the IEEE 14 bus system show that given similar input variables to DC models, the MLR models performs significantly better. They also show that the MLR models have good prediction accuracy in scenarios with high volatility.",
author = "Sashirekha Appalasamy and Jones, {Owen Dafydd} and Moin, {Noor Hasnah} and Sin, {Tan Ching}",
year = "2015",
month = "9",
day = "30",
doi = "10.1109/PESGM.2015.7285669",
language = "English",
series = "IEEE Power and Energy Society General Meeting",
publisher = "IEEE Computer Society",
booktitle = "2015 IEEE Power and Energy Society General Meeting, PESGM 2015",
address = "United States",

}

Appalasamy, S, Jones, OD, Moin, NH & Sin, TC 2015, New multivariate linear regression real and reactive branch flow models for volatile scenarios. in 2015 IEEE Power and Energy Society General Meeting, PESGM 2015., 7285669, IEEE Power and Energy Society General Meeting, vol. 2015-September, IEEE Computer Society, IEEE Power and Energy Society General Meeting, PESGM 2015, Denver, United States, 26/07/15. https://doi.org/10.1109/PESGM.2015.7285669

New multivariate linear regression real and reactive branch flow models for volatile scenarios. / Appalasamy, Sashirekha; Jones, Owen Dafydd; Moin, Noor Hasnah; Sin, Tan Ching.

2015 IEEE Power and Energy Society General Meeting, PESGM 2015. IEEE Computer Society, 2015. 7285669 (IEEE Power and Energy Society General Meeting; Vol. 2015-September).

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

TY - GEN

T1 - New multivariate linear regression real and reactive branch flow models for volatile scenarios

AU - Appalasamy, Sashirekha

AU - Jones, Owen Dafydd

AU - Moin, Noor Hasnah

AU - Sin, Tan Ching

PY - 2015/9/30

Y1 - 2015/9/30

N2 - Nonlinearity of power flow equations is one of the major underlying factors in a power systems operation complexity. The need for a robust and less complex models rises in a volatile, dynamic and real time scenario. This paper introduces new empirical models using multivariate linear regression (MLR) methods with least squares for both real and reactive branch flows. The models do not make prior assumptions and do not depend on a particular base case. Instead they are trained on either simulated or historical data. Tests using the IEEE 14 bus system show that given similar input variables to DC models, the MLR models performs significantly better. They also show that the MLR models have good prediction accuracy in scenarios with high volatility.

AB - Nonlinearity of power flow equations is one of the major underlying factors in a power systems operation complexity. The need for a robust and less complex models rises in a volatile, dynamic and real time scenario. This paper introduces new empirical models using multivariate linear regression (MLR) methods with least squares for both real and reactive branch flows. The models do not make prior assumptions and do not depend on a particular base case. Instead they are trained on either simulated or historical data. Tests using the IEEE 14 bus system show that given similar input variables to DC models, the MLR models performs significantly better. They also show that the MLR models have good prediction accuracy in scenarios with high volatility.

UR - http://www.scopus.com/inward/record.url?scp=84956854686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956854686&partnerID=8YFLogxK

U2 - 10.1109/PESGM.2015.7285669

DO - 10.1109/PESGM.2015.7285669

M3 - Conference contribution

AN - SCOPUS:84956854686

T3 - IEEE Power and Energy Society General Meeting

BT - 2015 IEEE Power and Energy Society General Meeting, PESGM 2015

PB - IEEE Computer Society

ER -

Appalasamy S, Jones OD, Moin NH, Sin TC. New multivariate linear regression real and reactive branch flow models for volatile scenarios. In 2015 IEEE Power and Energy Society General Meeting, PESGM 2015. IEEE Computer Society. 2015. 7285669. (IEEE Power and Energy Society General Meeting). https://doi.org/10.1109/PESGM.2015.7285669