Forecasting Short-Term Electricity Load Using Validated Ensemble Learning
As short-term load forecasting is essential for the day-to-day operation planning of power systems, we built an ensemble learning model to perform such forecasting for Thai data. The proposed model uses voting regression (VR), producing forecasts with weighted averages of forecasts from five individ...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/22/8567 |
| _version_ | 1797465429219737600 |
|---|---|
| author | Chatum Sankalpa Somsak Kittipiyakul Seksan Laitrakun |
| author_facet | Chatum Sankalpa Somsak Kittipiyakul Seksan Laitrakun |
| author_sort | Chatum Sankalpa |
| collection | DOAJ |
| description | As short-term load forecasting is essential for the day-to-day operation planning of power systems, we built an ensemble learning model to perform such forecasting for Thai data. The proposed model uses voting regression (VR), producing forecasts with weighted averages of forecasts from five individual models: three parametric multiple linear regressors and two non-parametric machine-learning models. The regressors are linear regression models with gradient-descent (LR), ordinary least-squares (OLS) estimators, and generalized least-squares auto-regression (GLSAR) models. In contrast, the machine-learning models are decision trees (DT) and random forests (RF). To select the best model variables and hyper-parameters, we used cross-validation (CV) performance instead of the test data performance, which yielded overly good test performance. We compared various validation schemes and found that the Blocked-CV scheme gives the validation error closest to the test error. Using Blocked-CV, the test results show that the VR model outperforms all its individual predictors. |
| first_indexed | 2024-03-09T18:21:20Z |
| format | Article |
| id | doaj.art-388923f9b4364b11bf693adf8480e6ab |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T18:21:20Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-388923f9b4364b11bf693adf8480e6ab2023-11-24T08:15:10ZengMDPI AGEnergies1996-10732022-11-011522856710.3390/en15228567Forecasting Short-Term Electricity Load Using Validated Ensemble LearningChatum Sankalpa0Somsak Kittipiyakul1Seksan Laitrakun2Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12000, ThailandSirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12000, ThailandSirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12000, ThailandAs short-term load forecasting is essential for the day-to-day operation planning of power systems, we built an ensemble learning model to perform such forecasting for Thai data. The proposed model uses voting regression (VR), producing forecasts with weighted averages of forecasts from five individual models: three parametric multiple linear regressors and two non-parametric machine-learning models. The regressors are linear regression models with gradient-descent (LR), ordinary least-squares (OLS) estimators, and generalized least-squares auto-regression (GLSAR) models. In contrast, the machine-learning models are decision trees (DT) and random forests (RF). To select the best model variables and hyper-parameters, we used cross-validation (CV) performance instead of the test data performance, which yielded overly good test performance. We compared various validation schemes and found that the Blocked-CV scheme gives the validation error closest to the test error. Using Blocked-CV, the test results show that the VR model outperforms all its individual predictors.https://www.mdpi.com/1996-1073/15/22/8567short-term load forecastingtime series forecasting model validationensemble learningaccuracy improvementThailand EGAT dataset |
| spellingShingle | Chatum Sankalpa Somsak Kittipiyakul Seksan Laitrakun Forecasting Short-Term Electricity Load Using Validated Ensemble Learning Energies short-term load forecasting time series forecasting model validation ensemble learning accuracy improvement Thailand EGAT dataset |
| title | Forecasting Short-Term Electricity Load Using Validated Ensemble Learning |
| title_full | Forecasting Short-Term Electricity Load Using Validated Ensemble Learning |
| title_fullStr | Forecasting Short-Term Electricity Load Using Validated Ensemble Learning |
| title_full_unstemmed | Forecasting Short-Term Electricity Load Using Validated Ensemble Learning |
| title_short | Forecasting Short-Term Electricity Load Using Validated Ensemble Learning |
| title_sort | forecasting short term electricity load using validated ensemble learning |
| topic | short-term load forecasting time series forecasting model validation ensemble learning accuracy improvement Thailand EGAT dataset |
| url | https://www.mdpi.com/1996-1073/15/22/8567 |
| work_keys_str_mv | AT chatumsankalpa forecastingshorttermelectricityloadusingvalidatedensemblelearning AT somsakkittipiyakul forecastingshorttermelectricityloadusingvalidatedensemblelearning AT seksanlaitrakun forecastingshorttermelectricityloadusingvalidatedensemblelearning |