Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique
Accurate and efficient demand forecasting is essential to grid stability, supply, and management in today’s electricity markets. Due to the complex pattern of electric power demand time series, it is challenging to model them directly. Therefore, this research proposes a novel time series ensemble a...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | inglés |
| Publicado: |
2024
|
| Acceso en línea: | Enlace permanente (DOI o Handle) Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881508904894988288 |
|---|---|
| author | Iftikhar, Hasnain Mancha Gonzales, Salvatore Zywiołek, Justyna López Gonzales, Javier Linkolk |
| author_browse | Iftikhar, Hasnain López Gonzales, Javier Linkolk Mancha Gonzales, Salvatore Zywiołek, Justyna |
| author_facet | Iftikhar, Hasnain Mancha Gonzales, Salvatore Zywiołek, Justyna López Gonzales, Javier Linkolk |
| author_sort | Iftikhar, Hasnain |
| collection | Producción científica |
| description | Accurate and efficient demand forecasting is essential to grid stability, supply, and management in today’s electricity markets. Due to the complex pattern of electric power demand time series, it is challenging to model them directly. Therefore, this research proposes a novel time series ensemble approach to forecast electric power demand in the Peruvian electricity market one month ahead. This approach treats the first preprocessed electricity demand time series for missing values, variance stabilization, normalization, stationarity, and seasonality issues. Secondly, six single time series and three of their proposed ensemble models forecast the clean demand time series. The results indicate that the proposed time ensemble approach is an efficient and precise one-month-ahead forecast for electricity demand in the Peruvian electricity market. Additionally, the final best ensemble forecasting model within the proposed ensemble time series forecasting approach obtained the smallest average accuracy errors, performing statistically significantly better than those mentioned in the best-proposed models in the literature. Lastly, while numerous global studies have been conducted from various perspectives, no analysis has been undertaken using an ensemble learning approach to forecast electric power demand in the Peruvian electricity market. |
| format | Article |
| id | oai:cris.upeu.edu.pe:20.500.15037/419 |
| institution | UPeU |
| language | English |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| record_format | dspace |
| spelling | oai:cris.upeu.edu.pe:20.500.15037/4192026-11-02T22:00:04ZElectricity Demand Forecasting Using a Novel Time Series Ensemble TechniqueIftikhar, HasnainMancha Gonzales, SalvatoreZywiołek, JustynaLópez Gonzales, Javier LinkolkAccurate and efficient demand forecasting is essential to grid stability, supply, and management in today’s electricity markets. Due to the complex pattern of electric power demand time series, it is challenging to model them directly. Therefore, this research proposes a novel time series ensemble approach to forecast electric power demand in the Peruvian electricity market one month ahead. This approach treats the first preprocessed electricity demand time series for missing values, variance stabilization, normalization, stationarity, and seasonality issues. Secondly, six single time series and three of their proposed ensemble models forecast the clean demand time series. The results indicate that the proposed time ensemble approach is an efficient and precise one-month-ahead forecast for electricity demand in the Peruvian electricity market. Additionally, the final best ensemble forecasting model within the proposed ensemble time series forecasting approach obtained the smallest average accuracy errors, performing statistically significantly better than those mentioned in the best-proposed models in the literature. Lastly, while numerous global studies have been conducted from various perspectives, no analysis has been undertaken using an ensemble learning approach to forecast electric power demand in the Peruvian electricity market.Articlehttps://doi.org/10.1109/access.2024.341955110.1109/access.2024.3419551https://hdl.handle.net/20.500.15037/419W4400033304enIEEE Access2169-35362024-01-012026-06-13T08:13:10Z2026-06-13T08:13:10Z |
| spellingShingle | Iftikhar, Hasnain Mancha Gonzales, Salvatore Zywiołek, Justyna López Gonzales, Javier Linkolk Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique |
| title | Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique |
| title_full | Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique |
| title_fullStr | Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique |
| title_full_unstemmed | Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique |
| title_short | Electricity Demand Forecasting Using a Novel Time Series Ensemble Technique |
| title_sort | electricity demand forecasting using a novel time series ensemble technique |
| url | https://doi.org/10.1109/access.2024.3419551 https://hdl.handle.net/20.500.15037/419 |
| work_keys_str_mv | AT iftikharhasnain electricitydemandforecastingusinganoveltimeseriesensembletechnique AT manchagonzalessalvatore electricitydemandforecastingusinganoveltimeseriesensembletechnique AT zywiołekjustyna electricitydemandforecastingusinganoveltimeseriesensembletechnique AT lopezgonzalesjavierlinkolk electricitydemandforecastingusinganoveltimeseriesensembletechnique |