Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas
In this study, we consider monthly load forecasting, which is an essential decision for energy infrastructure planning and investment. This study focuses on the Texas power grid, where electricity consumption has surged due to rising industrial activity and the increased construction of data centers...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/15/4135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239643140128768 |
|---|---|
| author | Jeong-Hee Hong Geun-Cheol Lee |
| author_facet | Jeong-Hee Hong Geun-Cheol Lee |
| author_sort | Jeong-Hee Hong |
| collection | DOAJ |
| description | In this study, we consider monthly load forecasting, which is an essential decision for energy infrastructure planning and investment. This study focuses on the Texas power grid, where electricity consumption has surged due to rising industrial activity and the increased construction of data centers driven by growing demand for AI. Based on an extensive exploratory data analysis, we identify key characteristics of monthly electricity demand in Texas, including an accelerating upward trend, strong seasonality, and temperature sensitivity. In response, we propose a regression-based forecasting model that incorporates a carefully designed set of input features, including a nonlinear trend, lagged demand variables, a seasonality-adjusted month variable, average temperature of a representative area, and calendar-based proxies for industrial activity. We adopt a rolling forecasting approach, generating 12-month-ahead forecasts for both 2023 and 2024 using monthly data from 2013 onward. Comparative experiments against benchmarks including Holt–Winters, SARIMA, Prophet, RNN, LSTM, Transformer, Random Forest, LightGBM, and XGBoost show that the proposed model achieves superior performance with a mean absolute percentage error of approximately 2%. The results indicate that a well-designed regression approach can effectively outperform even the latest machine learning methods in monthly load forecasting. |
| format | Article |
| id | doaj-art-1c52574d690f464c99f1b35c6d2ea149 |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-1c52574d690f464c99f1b35c6d2ea1492025-08-20T04:00:54ZengMDPI AGEnergies1996-10732025-08-011815413510.3390/en18154135Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of TexasJeong-Hee Hong0Geun-Cheol Lee1Graduate School of Management of Technology, Korea University, Seoul 02841, Republic of KoreaCollege of Business, Konkuk University, Seoul 05029, Republic of KoreaIn this study, we consider monthly load forecasting, which is an essential decision for energy infrastructure planning and investment. This study focuses on the Texas power grid, where electricity consumption has surged due to rising industrial activity and the increased construction of data centers driven by growing demand for AI. Based on an extensive exploratory data analysis, we identify key characteristics of monthly electricity demand in Texas, including an accelerating upward trend, strong seasonality, and temperature sensitivity. In response, we propose a regression-based forecasting model that incorporates a carefully designed set of input features, including a nonlinear trend, lagged demand variables, a seasonality-adjusted month variable, average temperature of a representative area, and calendar-based proxies for industrial activity. We adopt a rolling forecasting approach, generating 12-month-ahead forecasts for both 2023 and 2024 using monthly data from 2013 onward. Comparative experiments against benchmarks including Holt–Winters, SARIMA, Prophet, RNN, LSTM, Transformer, Random Forest, LightGBM, and XGBoost show that the proposed model achieves superior performance with a mean absolute percentage error of approximately 2%. The results indicate that a well-designed regression approach can effectively outperform even the latest machine learning methods in monthly load forecasting.https://www.mdpi.com/1996-1073/18/15/4135monthly load forecastingenergy demandregression modeldata centersTexas power system |
| spellingShingle | Jeong-Hee Hong Geun-Cheol Lee Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas Energies monthly load forecasting energy demand regression model data centers Texas power system |
| title | Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas |
| title_full | Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas |
| title_fullStr | Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas |
| title_full_unstemmed | Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas |
| title_short | Monthly Load Forecasting in a Region Experiencing Demand Growth: A Case Study of Texas |
| title_sort | monthly load forecasting in a region experiencing demand growth a case study of texas |
| topic | monthly load forecasting energy demand regression model data centers Texas power system |
| url | https://www.mdpi.com/1996-1073/18/15/4135 |
| work_keys_str_mv | AT jeongheehong monthlyloadforecastinginaregionexperiencingdemandgrowthacasestudyoftexas AT geuncheollee monthlyloadforecastinginaregionexperiencingdemandgrowthacasestudyoftexas |