Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods
Plug-in Electric Vehicle (PEV) user charging behavior has a significant influence on a distribution network and its reliability. Generally, monitoring energy consumption has become one of the most important factors in green and micro grids; therefore, predicting the charging demand of PEVs (the ener...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/16/4231 |
| _version_ | 1797557821746708480 |
|---|---|
| author | Ahmad Almaghrebi Fares Aljuheshi Mostafa Rafaie Kevin James Mahmoud Alahmad |
| author_facet | Ahmad Almaghrebi Fares Aljuheshi Mostafa Rafaie Kevin James Mahmoud Alahmad |
| author_sort | Ahmad Almaghrebi |
| collection | DOAJ |
| description | Plug-in Electric Vehicle (PEV) user charging behavior has a significant influence on a distribution network and its reliability. Generally, monitoring energy consumption has become one of the most important factors in green and micro grids; therefore, predicting the charging demand of PEVs (the energy consumed during the charging session) could help to efficiently manage the electric grid. Consequently, three machine learning methods are applied in this research to predict the charging demand for the PEV user after a charging session starts. This approach is validated using a dataset consisting of seven years of charging events collected from public charging stations in the state of Nebraska, USA. The results show that the regression method, XGBoost, slightly outperforms the other methods in predicting the charging demand, with an RMSE equal to 6.68 kWh and R<sup>2</sup> equal to 51.9%. The relative importance of input variables is also discussed, showing that the user’s historical average demand has the most predictive value. Accurate prediction of session charging demand, as opposed to the daily or hourly demand of multiple users, has many possible applications for utility companies and charging networks, including scheduling, grid stability, and smart grid integration. |
| first_indexed | 2024-03-10T17:22:38Z |
| format | Article |
| id | doaj.art-9969da11c9874419a40505160ecbb31c |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T17:22:38Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-9969da11c9874419a40505160ecbb31c2023-11-20T10:18:31ZengMDPI AGEnergies1996-10732020-08-011316423110.3390/en13164231Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression MethodsAhmad Almaghrebi0Fares Aljuheshi1Mostafa Rafaie2Kevin James3Mahmoud Alahmad4Durham School of Architectural Engineering and Construction, University of Nebraska–Lincoln, Omaha, NE 68182, USADurham School of Architectural Engineering and Construction, University of Nebraska–Lincoln, Omaha, NE 68182, USADurham School of Architectural Engineering and Construction, University of Nebraska–Lincoln, Omaha, NE 68182, USADurham School of Architectural Engineering and Construction, University of Nebraska–Lincoln, Omaha, NE 68182, USADurham School of Architectural Engineering and Construction, University of Nebraska–Lincoln, Omaha, NE 68182, USAPlug-in Electric Vehicle (PEV) user charging behavior has a significant influence on a distribution network and its reliability. Generally, monitoring energy consumption has become one of the most important factors in green and micro grids; therefore, predicting the charging demand of PEVs (the energy consumed during the charging session) could help to efficiently manage the electric grid. Consequently, three machine learning methods are applied in this research to predict the charging demand for the PEV user after a charging session starts. This approach is validated using a dataset consisting of seven years of charging events collected from public charging stations in the state of Nebraska, USA. The results show that the regression method, XGBoost, slightly outperforms the other methods in predicting the charging demand, with an RMSE equal to 6.68 kWh and R<sup>2</sup> equal to 51.9%. The relative importance of input variables is also discussed, showing that the user’s historical average demand has the most predictive value. Accurate prediction of session charging demand, as opposed to the daily or hourly demand of multiple users, has many possible applications for utility companies and charging networks, including scheduling, grid stability, and smart grid integration.https://www.mdpi.com/1996-1073/13/16/4231Plug-in Electric Vehiclepublic charging stationscharging behaviorcharging demandmachine learningdata-driven |
| spellingShingle | Ahmad Almaghrebi Fares Aljuheshi Mostafa Rafaie Kevin James Mahmoud Alahmad Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods Energies Plug-in Electric Vehicle public charging stations charging behavior charging demand machine learning data-driven |
| title | Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods |
| title_full | Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods |
| title_fullStr | Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods |
| title_full_unstemmed | Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods |
| title_short | Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods |
| title_sort | data driven charging demand prediction at public charging stations using supervised machine learning regression methods |
| topic | Plug-in Electric Vehicle public charging stations charging behavior charging demand machine learning data-driven |
| url | https://www.mdpi.com/1996-1073/13/16/4231 |
| work_keys_str_mv | AT ahmadalmaghrebi datadrivenchargingdemandpredictionatpublicchargingstationsusingsupervisedmachinelearningregressionmethods AT faresaljuheshi datadrivenchargingdemandpredictionatpublicchargingstationsusingsupervisedmachinelearningregressionmethods AT mostafarafaie datadrivenchargingdemandpredictionatpublicchargingstationsusingsupervisedmachinelearningregressionmethods AT kevinjames datadrivenchargingdemandpredictionatpublicchargingstationsusingsupervisedmachinelearningregressionmethods AT mahmoudalahmad datadrivenchargingdemandpredictionatpublicchargingstationsusingsupervisedmachinelearningregressionmethods |