A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques
The transition of the automotive sector to electric vehicles (EVs) necessitates research on charging demand forecasting for optimal station placement and capacity planning. In the literature, extensive studies have been conducted on model-based and probabilistic EV charging demand forecasting scheme...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Vehicular Technology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10670452/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582340159733760 |
|---|---|
| author | Mamunur Rashid Tarek Elfouly Nan Chen |
| author_facet | Mamunur Rashid Tarek Elfouly Nan Chen |
| author_sort | Mamunur Rashid |
| collection | DOAJ |
| description | The transition of the automotive sector to electric vehicles (EVs) necessitates research on charging demand forecasting for optimal station placement and capacity planning. In the literature, extensive studies have been conducted on model-based and probabilistic EV charging demand forecasting schemes. The studies provide a solid research foundation but result in complicated models with limited scalability. Meanwhile, emerging machine learning techniques bring promising prospects, yet exhibit suboptimal performance with insufficient data. Additionally, existing studies often overlook several critical areas such as overcoming data scarcity, security and privacy concerns, managing the inherent stochasticity of demand data, selecting forecasting methods for a specific feature, and developing standardized performance metrics. Considering the impact of the research topic, EV charging demand forecasting demands careful study. In this paper, we present a comprehensive survey of EV charging demand forecasting, focusing on both probabilistic and learning algorithms. First, we introduce the general procedure of EV charging demand forecasting, encompassing data sources, data pre-processing, and the key EV features. We then provide a taxonomy of existing EV charging demand forecasting techniques, followed by a critical analysis and comparative study of state-of-the-art research. Finally, we discuss open issues, which offer useful insights and future direction for various stakeholders. |
| format | Article |
| id | doaj-art-d7a6ccb2060244d791622c8dcbf88cfc |
| institution | Kabale University |
| issn | 2644-1330 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Vehicular Technology |
| spelling | doaj-art-d7a6ccb2060244d791622c8dcbf88cfc2025-01-30T00:04:36ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302024-01-0151348137310.1109/OJVT.2024.345749910670452A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting TechniquesMamunur Rashid0https://orcid.org/0000-0003-4958-6041Tarek Elfouly1https://orcid.org/0000-0002-1688-6163Nan Chen2https://orcid.org/0000-0002-8730-2575Electrical and Computer Engineering, Tennessee Tech University, Cookeville, TN, USAElectrical and Computer Engineering, Tennessee Tech University, Cookeville, TN, USAElectrical and Computer Engineering, Tennessee Tech University, Cookeville, TN, USAThe transition of the automotive sector to electric vehicles (EVs) necessitates research on charging demand forecasting for optimal station placement and capacity planning. In the literature, extensive studies have been conducted on model-based and probabilistic EV charging demand forecasting schemes. The studies provide a solid research foundation but result in complicated models with limited scalability. Meanwhile, emerging machine learning techniques bring promising prospects, yet exhibit suboptimal performance with insufficient data. Additionally, existing studies often overlook several critical areas such as overcoming data scarcity, security and privacy concerns, managing the inherent stochasticity of demand data, selecting forecasting methods for a specific feature, and developing standardized performance metrics. Considering the impact of the research topic, EV charging demand forecasting demands careful study. In this paper, we present a comprehensive survey of EV charging demand forecasting, focusing on both probabilistic and learning algorithms. First, we introduce the general procedure of EV charging demand forecasting, encompassing data sources, data pre-processing, and the key EV features. We then provide a taxonomy of existing EV charging demand forecasting techniques, followed by a critical analysis and comparative study of state-of-the-art research. Finally, we discuss open issues, which offer useful insights and future direction for various stakeholders.https://ieeexplore.ieee.org/document/10670452/Electric vehicle (EV)charging demand forecastingprobabilistic modelmachine learning |
| spellingShingle | Mamunur Rashid Tarek Elfouly Nan Chen A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques IEEE Open Journal of Vehicular Technology Electric vehicle (EV) charging demand forecasting probabilistic model machine learning |
| title | A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques |
| title_full | A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques |
| title_fullStr | A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques |
| title_full_unstemmed | A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques |
| title_short | A Comprehensive Survey of Electric Vehicle Charging Demand Forecasting Techniques |
| title_sort | comprehensive survey of electric vehicle charging demand forecasting techniques |
| topic | Electric vehicle (EV) charging demand forecasting probabilistic model machine learning |
| url | https://ieeexplore.ieee.org/document/10670452/ |
| work_keys_str_mv | AT mamunurrashid acomprehensivesurveyofelectricvehiclechargingdemandforecastingtechniques AT tarekelfouly acomprehensivesurveyofelectricvehiclechargingdemandforecastingtechniques AT nanchen acomprehensivesurveyofelectricvehiclechargingdemandforecastingtechniques AT mamunurrashid comprehensivesurveyofelectricvehiclechargingdemandforecastingtechniques AT tarekelfouly comprehensivesurveyofelectricvehiclechargingdemandforecastingtechniques AT nanchen comprehensivesurveyofelectricvehiclechargingdemandforecastingtechniques |