DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days

Abstract

Understanding the conditions associated with stress on the electricity grid is important in the development of contingency plans for maintaining reliability during periods when the grid is stressed. In this paper, heat-related grid stress and the relationship with weather conditions were examined using data from the eastern United States. Penalized logistic regression models were developed and applied to predict stress on the electric grid using weather data. The inclusion of other weather variables, such as precipitation, in addition to temperature improved model performance. Several candidate models and combinations of predictive variables were examined. A penalized logistic regression model which was fit at the operation-zone level was found to provide predictive value and interpretability. Additionally, the importance of different weather variables observed at various time scales were examined. Maximum temperature and precipitation were identified as important across all zones while the importance of other weather variables was zone specific. In conclusion, the methods presented in this work are extensible to other regions and can be used to aid in planning and development of the electrical grid.

Authors:
 [1];  [1];  [1];  [1];  [1];  [2];  [1]
  1. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  2. Smarter Decisions, LLC, Portland, OR (United States)
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1395358
Alternate Identifier(s):
OSTI ID: 1495528
Report Number(s):
PNNL-SA-126567
Journal ID: ISSN 0306-2619; PII: S0306261917313697
Grant/Contract Number:  
AC05-76RL01830
Resource Type:
Accepted Manuscript
Journal Name:
Applied Energy
Additional Journal Information:
Journal Volume: 205; Journal ID: ISSN 0306-2619
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; Electrical grid; Grid stress; Heatwave; Statistical modeling

Citation Formats

Bramer, Lisa M., Rounds, J., Burleyson, C. D., Fortin, D., Hathaway, J., Rice, J., and Kraucunas, I. Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days. United States: N. p., 2017. Web. doi:10.1016/J.APENERGY.2017.09.087.
Bramer, Lisa M., Rounds, J., Burleyson, C. D., Fortin, D., Hathaway, J., Rice, J., & Kraucunas, I. Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days. United States. https://doi.org/10.1016/J.APENERGY.2017.09.087
Bramer, Lisa M., Rounds, J., Burleyson, C. D., Fortin, D., Hathaway, J., Rice, J., and Kraucunas, I. Fri . "Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days". United States. https://doi.org/10.1016/J.APENERGY.2017.09.087. https://www.osti.gov/servlets/purl/1395358.
@article{osti_1395358,
title = {Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days},
author = {Bramer, Lisa M. and Rounds, J. and Burleyson, C. D. and Fortin, D. and Hathaway, J. and Rice, J. and Kraucunas, I.},
abstractNote = {Understanding the conditions associated with stress on the electricity grid is important in the development of contingency plans for maintaining reliability during periods when the grid is stressed. In this paper, heat-related grid stress and the relationship with weather conditions were examined using data from the eastern United States. Penalized logistic regression models were developed and applied to predict stress on the electric grid using weather data. The inclusion of other weather variables, such as precipitation, in addition to temperature improved model performance. Several candidate models and combinations of predictive variables were examined. A penalized logistic regression model which was fit at the operation-zone level was found to provide predictive value and interpretability. Additionally, the importance of different weather variables observed at various time scales were examined. Maximum temperature and precipitation were identified as important across all zones while the importance of other weather variables was zone specific. In conclusion, the methods presented in this work are extensible to other regions and can be used to aid in planning and development of the electrical grid.},
doi = {10.1016/J.APENERGY.2017.09.087},
journal = {Applied Energy},
number = ,
volume = 205,
place = {United States},
year = {2017},
month = {9}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Energy sector vulnerability to climate change: A review
journal, February 2012


Global observed changes in daily climate extremes of temperature and precipitation
journal, January 2006

  • Alexander, L. V.; Zhang, X.; Peterson, T. C.
  • Journal of Geophysical Research, Vol. 111, Issue D5
  • DOI: 10.1029/2005JD006290

Quantifying the influence of global warming on unprecedented extreme climate events
journal, April 2017

  • Diffenbaugh, Noah S.; Singh, Deepti; Mankin, Justin S.
  • Proceedings of the National Academy of Sciences, Vol. 114, Issue 19
  • DOI: 10.1073/pnas.1618082114

Impacts of climate change on electric power supply in the Western United States
journal, May 2015

  • Bartos, Matthew D.; Chester, Mikhail V.
  • Nature Climate Change, Vol. 5, Issue 8
  • DOI: 10.1038/nclimate2648

Vulnerability of US and European electricity supply to climate change
journal, June 2012

  • van Vliet, Michelle T. H.; Yearsley, John R.; Ludwig, Fulco
  • Nature Climate Change, Vol. 2, Issue 9
  • DOI: 10.1038/nclimate1546

Transforming the Electric Infrastructure
journal, December 2004

  • Gellings, Clark W.; Yeager, Kurt E.
  • Physics Today, Vol. 57, Issue 12
  • DOI: 10.1063/1.1878334

Modelling influence of temperature on daily peak electricity demand in South Africa
journal, November 2013


Temperature and seasonality influences on Spanish electricity load
journal, January 2002


Modeling Utility Load and Temperature Relationships for Use with Long-Lead Forecasts
journal, May 1997


A hybrid dynamic and fuzzy time series model for mid-term power load forecasting
journal, January 2015


A computational intelligence scheme for the prediction of the daily peak load
journal, December 2011


Relationships between meteorological variables and monthly electricity demand
journal, October 2012


Models for mid-term electricity demand forecasting incorporating weather influences
journal, March 2005


Genome-wide association analysis by lasso penalized logistic regression
journal, January 2009


The class imbalance problem: A systematic study1
journal, November 2002

  • Japkowicz, Nathalie; Stephen, Shaju
  • Intelligent Data Analysis, Vol. 6, Issue 5
  • DOI: 10.3233/IDA-2002-6504

Facing Imbalanced Data--Recommendations for the Use of Performance Metrics
conference, September 2013

  • Jeni, Laszlo A.; Cohn, Jeffrey F.; De La Torre, Fernando
  • 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII)
  • DOI: 10.1109/ACII.2013.47

Ward’s Hierarchical Agglomerative Clustering Method: Which Algorithms Implement Ward’s Criterion?
journal, October 2014


Works referencing / citing this record:

Compounding climate change impacts during high stress periods for a high wind and solar power system in Texas
journal, January 2020

  • Craig, Michael T.; Jaramillo, Paulina; Hodge, Bri-Mathias
  • Environmental Research Letters, Vol. 15, Issue 2
  • DOI: 10.1088/1748-9326/ab6615