An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales
Electric power load forecasting is essential for the efficient operation and strategic planning of utilities. Decisions regarding the electric market, power generation, load management, and infrastructure development all rely on accurate load predictions. This work presents a novel methodology for d...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/9/4717 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850278923572609024 |
|---|---|
| author | Monica Borunda Arturo Ortega Vega Raul Garduno Luis Conde Manuel Adam Medina Jeannete Ramírez Aparicio Lorena Magallón Cacho O. A. Jaramillo |
| author_facet | Monica Borunda Arturo Ortega Vega Raul Garduno Luis Conde Manuel Adam Medina Jeannete Ramírez Aparicio Lorena Magallón Cacho O. A. Jaramillo |
| author_sort | Monica Borunda |
| collection | DOAJ |
| description | Electric power load forecasting is essential for the efficient operation and strategic planning of utilities. Decisions regarding the electric market, power generation, load management, and infrastructure development all rely on accurate load predictions. This work presents a novel methodology for day-ahead load forecasting. The approach employs a long short-term memory neural network (LSTM NN) trained on representative load and meteorological data from the region. Before training, the load dataset is grouped by its statistical seasonality through K-means clustering analysis. Clustering load demand, along with similar-day data management, enables more focused training of the LSTM network on uniform data subsets, enhancing the model’s ability to capture temporal patterns and reducing the complexity associated with high variability in demand data. A case study using hourly load demand time-series data provided by the Centro Nacional de Control de Energía (CENACE) is analyzed, and the mean absolute percentage error (MAPE) is calculated, showing lower MAPE than traditional methods. This hybrid approach demonstrates the potential of integrating clustering techniques with neural networks and representative meteorological data from the region to achieve more reliable and accurate regional day-ahead load forecasting. |
| format | Article |
| id | doaj-art-67b3c5e506ff46f9b81d99f46e57f4c9 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-67b3c5e506ff46f9b81d99f46e57f4c92025-08-20T01:49:16ZengMDPI AGApplied Sciences2076-34172025-04-01159471710.3390/app15094717An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual ScalesMonica Borunda0Arturo Ortega Vega1Raul Garduno2Luis Conde3Manuel Adam Medina4Jeannete Ramírez Aparicio5Lorena Magallón Cacho6O. A. Jaramillo7SECIHTI, Centro Nacional de Investigación y Desarrollo Tecnológico, Tecnológico Nacional de México, Cuernavaca 62490, MexicoFacultad de Ciencias, Universidad Nacional Autónoma de México, Ciudad de México 04510, MexicoInstituto Nacional de Electricidad y Energías Limpias, Cuernavaca 62490, MexicoCentro Nacional de Control de Energía, Gerencia de Control Regional Oriental, Heroica Puebla de Zaragoza 72307, MexicoCentro Nacional de Investigación y Desarrollo Tecnológico, Tecnológico Nacional de México, Cuernavaca 62490, MexicoSECIHTI, Centro de Investigación en Ingeniería y Ciencias Aplicadas, Universidad Autónoma del Estado de Morelos, Cuernavaca 62209, MexicoSECIHTI, Centro de Investigación en Ingeniería y Ciencias Aplicadas, Universidad Autónoma del Estado de Morelos, Cuernavaca 62209, MexicoInstituto de Energías Renovables, Universidad Nacional Autónoma de México, Temixco 62590, MexicoElectric power load forecasting is essential for the efficient operation and strategic planning of utilities. Decisions regarding the electric market, power generation, load management, and infrastructure development all rely on accurate load predictions. This work presents a novel methodology for day-ahead load forecasting. The approach employs a long short-term memory neural network (LSTM NN) trained on representative load and meteorological data from the region. Before training, the load dataset is grouped by its statistical seasonality through K-means clustering analysis. Clustering load demand, along with similar-day data management, enables more focused training of the LSTM network on uniform data subsets, enhancing the model’s ability to capture temporal patterns and reducing the complexity associated with high variability in demand data. A case study using hourly load demand time-series data provided by the Centro Nacional de Control de Energía (CENACE) is analyzed, and the mean absolute percentage error (MAPE) is calculated, showing lower MAPE than traditional methods. This hybrid approach demonstrates the potential of integrating clustering techniques with neural networks and representative meteorological data from the region to achieve more reliable and accurate regional day-ahead load forecasting.https://www.mdpi.com/2076-3417/15/9/4717day-ahead forecastingLSTM NNhourly electrical load forecastingsimilar daysclusteringK-means |
| spellingShingle | Monica Borunda Arturo Ortega Vega Raul Garduno Luis Conde Manuel Adam Medina Jeannete Ramírez Aparicio Lorena Magallón Cacho O. A. Jaramillo An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales Applied Sciences day-ahead forecasting LSTM NN hourly electrical load forecasting similar days clustering K-means |
| title | An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales |
| title_full | An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales |
| title_fullStr | An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales |
| title_full_unstemmed | An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales |
| title_short | An Intelligent Method for Day-Ahead Regional Load Demand Forecasting via Machine-Learning Analysis of Energy Consumption Patterns Across Daily, Weekly, and Annual Scales |
| title_sort | intelligent method for day ahead regional load demand forecasting via machine learning analysis of energy consumption patterns across daily weekly and annual scales |
| topic | day-ahead forecasting LSTM NN hourly electrical load forecasting similar days clustering K-means |
| url | https://www.mdpi.com/2076-3417/15/9/4717 |
| work_keys_str_mv | AT monicaborunda anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT arturoortegavega anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT raulgarduno anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT luisconde anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT manueladammedina anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT jeanneteramirezaparicio anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT lorenamagalloncacho anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT oajaramillo anintelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT monicaborunda intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT arturoortegavega intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT raulgarduno intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT luisconde intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT manueladammedina intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT jeanneteramirezaparicio intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT lorenamagalloncacho intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales AT oajaramillo intelligentmethodfordayaheadregionalloaddemandforecastingviamachinelearninganalysisofenergyconsumptionpatternsacrossdailyweeklyandannualscales |