File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.apenergy.2020.116175
- Scopus: eid_2-s2.0-85096680952
- WOS: WOS:000599888400005
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Data-driven framework for large-scale prediction of charging energy in electric vehicles
Title | Data-driven framework for large-scale prediction of charging energy in electric vehicles |
---|---|
Authors | |
Keywords | Electric vehicle Charging energy Machine learning Large-scale prediction |
Issue Date | 2021 |
Citation | Applied Energy, 2021, v. 282, article no. 116175 How to Cite? |
Abstract | © 2020 Elsevier Ltd Large-scale and high-precision predictions of the charging energy required for electric vehicles (EVs) are essential to ensure the safety of EVs and provide reliable inputs for grid-load calculations. However, the complex and dynamic operating conditions of EVs make it challenging to accurately predict the charging energy under real-world conditions, especially for large-scale EV utilization. In this study, a novel data-driven framework for large-scale charging energy predictions is developed by individually controlling the strongly linear and weakly nonlinear contributions. The proposed framework concurrently addresses the overfitting of nonlinear networks using a low proportion of training data as well as the poorly descriptive ability of linear networks under complex environments. For each charging session, the charging energy predictions appropriately account for important factors such as the variations in the state of charge (SOC) of the battery, ambient temperatures, charging rates, and total driving distances. The results suggest that, compared with existing prediction models (such as the random forest, xgboost, and neural network), the proposed framework persists with evidently higher accuracy and stability over a wide range of the ratio between the number of EVs used for testing and training; its mean absolute percentage error (MAPE) is maintained at 2.5–3.8% when the ratio ranges from 0.1 to 1000. The proposed models can be further utilized for cloud-based battery diagnoses and large-scale forecasting of the energy demands of EVs. |
Persistent Identifier | http://hdl.handle.net/10722/296226 |
ISSN | 2023 Impact Factor: 10.1 2023 SCImago Journal Rankings: 2.820 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Yang | - |
dc.contributor.author | Wang, Zhenpo | - |
dc.contributor.author | Shen, Zuo Jun Max | - |
dc.contributor.author | Sun, Fengchun | - |
dc.date.accessioned | 2021-02-11T04:53:06Z | - |
dc.date.available | 2021-02-11T04:53:06Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Applied Energy, 2021, v. 282, article no. 116175 | - |
dc.identifier.issn | 0306-2619 | - |
dc.identifier.uri | http://hdl.handle.net/10722/296226 | - |
dc.description.abstract | © 2020 Elsevier Ltd Large-scale and high-precision predictions of the charging energy required for electric vehicles (EVs) are essential to ensure the safety of EVs and provide reliable inputs for grid-load calculations. However, the complex and dynamic operating conditions of EVs make it challenging to accurately predict the charging energy under real-world conditions, especially for large-scale EV utilization. In this study, a novel data-driven framework for large-scale charging energy predictions is developed by individually controlling the strongly linear and weakly nonlinear contributions. The proposed framework concurrently addresses the overfitting of nonlinear networks using a low proportion of training data as well as the poorly descriptive ability of linear networks under complex environments. For each charging session, the charging energy predictions appropriately account for important factors such as the variations in the state of charge (SOC) of the battery, ambient temperatures, charging rates, and total driving distances. The results suggest that, compared with existing prediction models (such as the random forest, xgboost, and neural network), the proposed framework persists with evidently higher accuracy and stability over a wide range of the ratio between the number of EVs used for testing and training; its mean absolute percentage error (MAPE) is maintained at 2.5–3.8% when the ratio ranges from 0.1 to 1000. The proposed models can be further utilized for cloud-based battery diagnoses and large-scale forecasting of the energy demands of EVs. | - |
dc.language | eng | - |
dc.relation.ispartof | Applied Energy | - |
dc.subject | Electric vehicle | - |
dc.subject | Charging energy | - |
dc.subject | Machine learning | - |
dc.subject | Large-scale prediction | - |
dc.title | Data-driven framework for large-scale prediction of charging energy in electric vehicles | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.apenergy.2020.116175 | - |
dc.identifier.scopus | eid_2-s2.0-85096680952 | - |
dc.identifier.volume | 282 | - |
dc.identifier.spage | article no. 116175 | - |
dc.identifier.epage | article no. 116175 | - |
dc.identifier.isi | WOS:000599888400005 | - |
dc.identifier.issnl | 0306-2619 | - |