Spatiotemporal charging demand models for electric vehicles considering user strategies
As the number of urban electric vehicles continues to increase, accurate prediction of the electric vehicle (EV) spatial and temporal distribution charging demand is of great importance for safely operating the power grid. Due to the uncertainty and variability of EV user charging and discharging st...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.1013154/full |
| _version_ | 1797957782670934016 |
|---|---|
| author | Hengjie Li Hengjie Li Daming Liang Yun Zhou Yiwei Shi Donghan Feng Shanshan Shi |
| author_facet | Hengjie Li Hengjie Li Daming Liang Yun Zhou Yiwei Shi Donghan Feng Shanshan Shi |
| author_sort | Hengjie Li |
| collection | DOAJ |
| description | As the number of urban electric vehicles continues to increase, accurate prediction of the electric vehicle (EV) spatial and temporal distribution charging demand is of great importance for safely operating the power grid. Due to the uncertainty and variability of EV user charging and discharging strategies, the strategic factors behind user behavior become the key to influencing whether the charging demand prediction results are reasonable. As a result, this paper proposes a charging demand prediction model based on real-time data from Baidu map that can interpret EV user driving strategies and charging strategies based on the strategy learning capability of generative adversarial imitation learning. This paper first analyzes the correlation between strategy factors and SOC in user charging and discharging data, then describes establishing a 24-hour SOC prediction model for a single vehicle, and finally discusses building a spatiotemporal model of charging demand in the region on this basis. The results demonstrate that, while it can be combined with real-time traffic data, the method has better prediction accuracy and robustness compared with the current mainstream prediction methods and high application value. |
| first_indexed | 2024-04-11T00:08:55Z |
| format | Article |
| id | doaj.art-89a9675caaff4c40981d8a35b47c11de |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-11T00:08:55Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-89a9675caaff4c40981d8a35b47c11de2023-01-09T07:43:14ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-01-011010.3389/fenrg.2022.10131541013154Spatiotemporal charging demand models for electric vehicles considering user strategiesHengjie Li0Hengjie Li1Daming Liang2Yun Zhou3Yiwei Shi4Donghan Feng5Shanshan Shi6School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou, ChinaKey Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Shanghai, ChinaSchool of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou, ChinaKey Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Shanghai, ChinaKey Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Shanghai, ChinaKey Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Shanghai, ChinaElectric Power Research Institute, State Grid Shanghai Municipal Electric Power Company, Shanghai, ChinaAs the number of urban electric vehicles continues to increase, accurate prediction of the electric vehicle (EV) spatial and temporal distribution charging demand is of great importance for safely operating the power grid. Due to the uncertainty and variability of EV user charging and discharging strategies, the strategic factors behind user behavior become the key to influencing whether the charging demand prediction results are reasonable. As a result, this paper proposes a charging demand prediction model based on real-time data from Baidu map that can interpret EV user driving strategies and charging strategies based on the strategy learning capability of generative adversarial imitation learning. This paper first analyzes the correlation between strategy factors and SOC in user charging and discharging data, then describes establishing a 24-hour SOC prediction model for a single vehicle, and finally discusses building a spatiotemporal model of charging demand in the region on this basis. The results demonstrate that, while it can be combined with real-time traffic data, the method has better prediction accuracy and robustness compared with the current mainstream prediction methods and high application value.https://www.frontiersin.org/articles/10.3389/fenrg.2022.1013154/fulldata-drivencharging demanduser strategiesimitative learningspatiotemporal models |
| spellingShingle | Hengjie Li Hengjie Li Daming Liang Yun Zhou Yiwei Shi Donghan Feng Shanshan Shi Spatiotemporal charging demand models for electric vehicles considering user strategies Frontiers in Energy Research data-driven charging demand user strategies imitative learning spatiotemporal models |
| title | Spatiotemporal charging demand models for electric vehicles considering user strategies |
| title_full | Spatiotemporal charging demand models for electric vehicles considering user strategies |
| title_fullStr | Spatiotemporal charging demand models for electric vehicles considering user strategies |
| title_full_unstemmed | Spatiotemporal charging demand models for electric vehicles considering user strategies |
| title_short | Spatiotemporal charging demand models for electric vehicles considering user strategies |
| title_sort | spatiotemporal charging demand models for electric vehicles considering user strategies |
| topic | data-driven charging demand user strategies imitative learning spatiotemporal models |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.1013154/full |
| work_keys_str_mv | AT hengjieli spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies AT hengjieli spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies AT damingliang spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies AT yunzhou spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies AT yiweishi spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies AT donghanfeng spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies AT shanshanshi spatiotemporalchargingdemandmodelsforelectricvehiclesconsideringuserstrategies |