Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts
This study aims to develop models for predicting hourly energy demand in the State of Connecticut, USA from 2011 to 2021 using machine learning algorithms inputted with airport weather stations’ data from the Automated Surface Observing System (ASOS), demand data from ISO New England (ISO...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10445218/ |
_version_ | 1797272695818158080 |
---|---|
author | Buket Sahin Kingsley Udeh David W. Wanik Diego Cerrai |
author_facet | Buket Sahin Kingsley Udeh David W. Wanik Diego Cerrai |
author_sort | Buket Sahin |
collection | DOAJ |
description | This study aims to develop models for predicting hourly energy demand in the State of Connecticut, USA from 2011 to 2021 using machine learning algorithms inputted with airport weather stations’ data from the Automated Surface Observing System (ASOS), demand data from ISO New England (ISO-NE). We built and evaluated nine different model experiments for each machine learning algorithm for each hour of the day addressing energy demand patterns, variations between workdays and weekends, and COVID-19 impacts. Error metrics analysis results highlighted that the GBR model demonstrated better performance compared to the MPR and RFR models. Incorporating both temporal and weather features in the models resulted in a noticeable improvement in error metrics. A consistent overestimation trend was observed for all models during the validation period (2018–2019) which may be attributed to energy efficiency measures and integration of behind-the-meter generation, with a further notable increase in overestimation following the onset of COVID-19 due to a change of habits during the pandemic in addition to decarbonization initiatives in the State. This study emphasizes the need for adapting models to dynamic consumption and weather patterns for improved grid management. |
first_indexed | 2024-03-07T14:33:04Z |
format | Article |
id | doaj.art-84da67d9fa834b3e9a82bd1d0bf74573 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-07T14:33:04Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-84da67d9fa834b3e9a82bd1d0bf745732024-03-06T00:00:49ZengIEEEIEEE Access2169-35362024-01-0112318243184010.1109/ACCESS.2024.337044210445218Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and ImpactsBuket Sahin0https://orcid.org/0000-0001-7541-3633Kingsley Udeh1https://orcid.org/0000-0002-3536-3659David W. Wanik2Diego Cerrai3https://orcid.org/0000-0001-5918-4885Department of Civil and Environmental Engineering, University of Connecticut, Storrs, CT, USAEversource Energy Center, Storrs, CT, USADepartment of Civil and Environmental Engineering, University of Connecticut, Storrs, CT, USADepartment of Civil and Environmental Engineering, University of Connecticut, Storrs, CT, USAThis study aims to develop models for predicting hourly energy demand in the State of Connecticut, USA from 2011 to 2021 using machine learning algorithms inputted with airport weather stations’ data from the Automated Surface Observing System (ASOS), demand data from ISO New England (ISO-NE). We built and evaluated nine different model experiments for each machine learning algorithm for each hour of the day addressing energy demand patterns, variations between workdays and weekends, and COVID-19 impacts. Error metrics analysis results highlighted that the GBR model demonstrated better performance compared to the MPR and RFR models. Incorporating both temporal and weather features in the models resulted in a noticeable improvement in error metrics. A consistent overestimation trend was observed for all models during the validation period (2018–2019) which may be attributed to energy efficiency measures and integration of behind-the-meter generation, with a further notable increase in overestimation following the onset of COVID-19 due to a change of habits during the pandemic in addition to decarbonization initiatives in the State. This study emphasizes the need for adapting models to dynamic consumption and weather patterns for improved grid management.https://ieeexplore.ieee.org/document/10445218/Energy demandmachine learningweather stationsISO New EnglandCOVID-19Bayesian optimization |
spellingShingle | Buket Sahin Kingsley Udeh David W. Wanik Diego Cerrai Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts IEEE Access Energy demand machine learning weather stations ISO New England COVID-19 Bayesian optimization |
title | Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts |
title_full | Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts |
title_fullStr | Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts |
title_full_unstemmed | Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts |
title_short | Predicting Energy Demand Using Machine Learning: Exploring Temporal and Weather-Related Patterns, Variations, and Impacts |
title_sort | predicting energy demand using machine learning exploring temporal and weather related patterns variations and impacts |
topic | Energy demand machine learning weather stations ISO New England COVID-19 Bayesian optimization |
url | https://ieeexplore.ieee.org/document/10445218/ |
work_keys_str_mv | AT buketsahin predictingenergydemandusingmachinelearningexploringtemporalandweatherrelatedpatternsvariationsandimpacts AT kingsleyudeh predictingenergydemandusingmachinelearningexploringtemporalandweatherrelatedpatternsvariationsandimpacts AT davidwwanik predictingenergydemandusingmachinelearningexploringtemporalandweatherrelatedpatternsvariationsandimpacts AT diegocerrai predictingenergydemandusingmachinelearningexploringtemporalandweatherrelatedpatternsvariationsandimpacts |