Regression model-based hourly aggregated electricity demand prediction
The ability to predict ggregated electricity demand of n electrical grid on an hourly basis is crucial for energy and demand management. In this study, demand and its categorical features data for three years are segregated into four seasons and then fed to an efficient Machine Learning Categorical...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722019382 |
| _version_ | 1797952117202223104 |
|---|---|
| author | Radharani Panigrahi Nita R. Patne Sumanth Pemmada Ashwini D. Manchalwar |
| author_facet | Radharani Panigrahi Nita R. Patne Sumanth Pemmada Ashwini D. Manchalwar |
| author_sort | Radharani Panigrahi |
| collection | DOAJ |
| description | The ability to predict ggregated electricity demand of n electrical grid on an hourly basis is crucial for energy and demand management. In this study, demand and its categorical features data for three years are segregated into four seasons and then fed to an efficient Machine Learning Categorical Boosting (ML CatBoost) Regressor model to predict the next year’s demand. It uses a new gradient boosting algorithm that handles categorical features adeptly. Also, this model uses a new scheme for estimating leaf values while choosing tree structure which reduces overfitting. Further, hourly electricity demand data from the Electricity Reliability Council of Texas (ERCOT western) is used as the benchmark data to evaluate the CatBoost model. Moreover, five other ML models were developed, analyzed, and tested for the same ERCOT data for predicting the hourly aggregated electricity demand. The suggested model is compared with the long short-term memory neural network (LSTM-NN) and five other ML models in terms of performance evaluation matrices. Here, one additional performance evaluation parameter, the Coefficient of variation Root Mean Squared (CV-RMSE) is evaluated in addition to the benchmark paper’s parameters. In addition, the importance of accurate prediction in the electric grid for clean energy is discussed. |
| first_indexed | 2024-04-10T22:42:21Z |
| format | Article |
| id | doaj.art-01d0908ed3774e71a34a5bf978077c56 |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-10T22:42:21Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-01d0908ed3774e71a34a5bf978077c562023-01-16T04:08:12ZengElsevierEnergy Reports2352-48472022-12-0181624Regression model-based hourly aggregated electricity demand predictionRadharani Panigrahi0Nita R. Patne1Sumanth Pemmada2Ashwini D. Manchalwar3Corresponding author.; Visvesvaraya National Institute of Technology, Nagpur, 440010, IndiaVisvesvaraya National Institute of Technology, Nagpur, 440010, IndiaVisvesvaraya National Institute of Technology, Nagpur, 440010, IndiaVisvesvaraya National Institute of Technology, Nagpur, 440010, IndiaThe ability to predict ggregated electricity demand of n electrical grid on an hourly basis is crucial for energy and demand management. In this study, demand and its categorical features data for three years are segregated into four seasons and then fed to an efficient Machine Learning Categorical Boosting (ML CatBoost) Regressor model to predict the next year’s demand. It uses a new gradient boosting algorithm that handles categorical features adeptly. Also, this model uses a new scheme for estimating leaf values while choosing tree structure which reduces overfitting. Further, hourly electricity demand data from the Electricity Reliability Council of Texas (ERCOT western) is used as the benchmark data to evaluate the CatBoost model. Moreover, five other ML models were developed, analyzed, and tested for the same ERCOT data for predicting the hourly aggregated electricity demand. The suggested model is compared with the long short-term memory neural network (LSTM-NN) and five other ML models in terms of performance evaluation matrices. Here, one additional performance evaluation parameter, the Coefficient of variation Root Mean Squared (CV-RMSE) is evaluated in addition to the benchmark paper’s parameters. In addition, the importance of accurate prediction in the electric grid for clean energy is discussed.http://www.sciencedirect.com/science/article/pii/S2352484722019382CatBoostElectricity demand predictionGradient boostingMachine learningOverfitting |
| spellingShingle | Radharani Panigrahi Nita R. Patne Sumanth Pemmada Ashwini D. Manchalwar Regression model-based hourly aggregated electricity demand prediction Energy Reports CatBoost Electricity demand prediction Gradient boosting Machine learning Overfitting |
| title | Regression model-based hourly aggregated electricity demand prediction |
| title_full | Regression model-based hourly aggregated electricity demand prediction |
| title_fullStr | Regression model-based hourly aggregated electricity demand prediction |
| title_full_unstemmed | Regression model-based hourly aggregated electricity demand prediction |
| title_short | Regression model-based hourly aggregated electricity demand prediction |
| title_sort | regression model based hourly aggregated electricity demand prediction |
| topic | CatBoost Electricity demand prediction Gradient boosting Machine learning Overfitting |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722019382 |
| work_keys_str_mv | AT radharanipanigrahi regressionmodelbasedhourlyaggregatedelectricitydemandprediction AT nitarpatne regressionmodelbasedhourlyaggregatedelectricitydemandprediction AT sumanthpemmada regressionmodelbasedhourlyaggregatedelectricitydemandprediction AT ashwinidmanchalwar regressionmodelbasedhourlyaggregatedelectricitydemandprediction |