Comparative Analysis of Machine Learning Models for ERCOT Short Term Load Forecasting

dc.contributor.authorSingh, Gurkiraten
dc.contributor.committeechairEldardiry, Hoda Mohameden
dc.contributor.committeechairStewart, Shamar L.en
dc.contributor.committeememberHamouda, Sallyen
dc.contributor.committeememberChen, Hongjieen
dc.contributor.departmentComputer Science and#38; Applicationsen
dc.date.accessioned2025-01-30T09:00:19Zen
dc.date.available2025-01-30T09:00:19Zen
dc.date.issued2025-01-29en
dc.description.abstractThis study investigates the efficacy of various machine learning (ML) and deep learning (DL) models for short-term load forecasting (STLF) in the Electric Reliability Council of Texas (ERCOT) grid. A dual comparative approach is employed, evaluating models based on temporal features alone as well as in combination with actual and forecasted weather variables. The research emphasizes region-specific forecasting by capturing heterogeneous load patterns for ERCOT's individual weather zones and aggregating them to predict total load. Model evaluation is conducted using accuracy and bias metrics, with particular attention to high-demand months and peak load hours. The findings reveal that Generalized Additive Models (GAM) consistently outperform other models, most importantly during summer months and peak load hours.en
dc.description.abstractgeneralThis study investigates the efficacy of various machine learning (ML) and deep learning (DL) models for short-term load forecasting (STLF) in the Electric Reliability Council of Texas (ERCOT) grid. A dual comparative approach is employed, evaluating models based on temporal features alone as well as in combination with actual and forecasted weather variables. The research emphasizes region-specific forecasting by capturing heterogeneous load patterns for ERCOT's individual weather zones and aggregating them to predict total load. Model evaluation is conducted using accuracy and bias metrics, with particular attention to high-demand months and peak load hours. The findings reveal that Generalized Additive Models (GAM) consistently outperform other models, most importantly during summer months and peak load hours.en
dc.description.degreeMaster of Scienceen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:42197en
dc.identifier.urihttps://hdl.handle.net/10919/124443en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectLoad Forecastingen
dc.subjectMachine Learningen
dc.subjectForecast Evaluationen
dc.subjectComparative Analysisen
dc.subjectCommoditiesen
dc.titleComparative Analysis of Machine Learning Models for ERCOT Short Term Load Forecastingen
dc.typeThesisen
thesis.degree.disciplineComputer Science & Applicationsen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Singh_G_T_2025.pdf
Size:
5.46 MB
Format:
Adobe Portable Document Format

Collections