Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting
Speed forecasting has numerous applications in intelligent transport systems’ design and control, especially for safety and road efficiency applications. In the field of electromobility, it represents the most dynamic parameter for efficient online in-vehicle energy management. However, vehicles’ sp...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2021-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2020.9020027 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572804925489152 |
|---|---|
| author | Youssef Nait Malek Mehdi Najib Mohamed Bakhouya Mohammed Essaaidi |
| author_facet | Youssef Nait Malek Mehdi Najib Mohamed Bakhouya Mohammed Essaaidi |
| author_sort | Youssef Nait Malek |
| collection | DOAJ |
| description | Speed forecasting has numerous applications in intelligent transport systems’ design and control, especially for safety and road efficiency applications. In the field of electromobility, it represents the most dynamic parameter for efficient online in-vehicle energy management. However, vehicles’ speed forecasting is a challenging task, because its estimation is closely related to various features, which can be classified into two categories, endogenous and exogenous features. Endogenous features represent electric vehicles’ characteristics, whereas exogenous ones represent its surrounding context, such as traffic, weather, and road conditions. In this paper, a speed forecasting method based on the Long Short-Term Memory (LSTM) is introduced. The LSTM model training is performed upon a dataset collected from a traffic simulator based on real-world data representing urban itineraries. The proposed models are generated for univariate and multivariate scenarios and are assessed in terms of accuracy for speed forecasting. Simulation results show that the multivariate model outperforms the univariate model for short- and long-term forecasting. |
| format | Article |
| id | doaj-art-51f64d259a724d98a74d2c330a74e011 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2021-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-51f64d259a724d98a74d2c330a74e0112025-02-02T06:50:16ZengTsinghua University PressBig Data Mining and Analytics2096-06542021-03-0141566410.26599/BDMA.2020.9020027Multivariate Deep Learning Approach for Electric Vehicle Speed ForecastingYoussef Nait Malek0Mehdi Najib1Mohamed Bakhouya2Mohammed Essaaidi3<institution content-type="dept">LERMA Lab, College of Engineering and Architecture</institution>, <institution>International University of Rabat</institution>, <city>Sala Al Jadida</city> <postal-code>11100</postal-code>, <country>Morocco</country>.<institution content-type="dept">TICLab, College of Engineering and Architecture</institution>, <institution>International University of Rabat</institution>, <city>Sala Al Jadida</city> <postal-code>11100</postal-code>, <country>Morocco</country>.<institution content-type="dept">LERMA Lab, College of Engineering</institution>, <institution>International University of Rabat</institution>, <city>Sala Al Jadida</city> <postal-code>11100</postal-code>, <country>Morocco</country>.<institution>ENSIAS, Mohamed V University</institution>, <city>Agdal Rabat</city> <postal-code>10112</postal-code>, <country>Morocco</country>.Speed forecasting has numerous applications in intelligent transport systems’ design and control, especially for safety and road efficiency applications. In the field of electromobility, it represents the most dynamic parameter for efficient online in-vehicle energy management. However, vehicles’ speed forecasting is a challenging task, because its estimation is closely related to various features, which can be classified into two categories, endogenous and exogenous features. Endogenous features represent electric vehicles’ characteristics, whereas exogenous ones represent its surrounding context, such as traffic, weather, and road conditions. In this paper, a speed forecasting method based on the Long Short-Term Memory (LSTM) is introduced. The LSTM model training is performed upon a dataset collected from a traffic simulator based on real-world data representing urban itineraries. The proposed models are generated for univariate and multivariate scenarios and are assessed in terms of accuracy for speed forecasting. Simulation results show that the multivariate model outperforms the univariate model for short- and long-term forecasting.https://www.sciopen.com/article/10.26599/BDMA.2020.9020027electric vehicle (ev)multivariate long short-term memory (lstm)speed forecastingdeep learning |
| spellingShingle | Youssef Nait Malek Mehdi Najib Mohamed Bakhouya Mohammed Essaaidi Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting Big Data Mining and Analytics electric vehicle (ev) multivariate long short-term memory (lstm) speed forecasting deep learning |
| title | Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting |
| title_full | Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting |
| title_fullStr | Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting |
| title_full_unstemmed | Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting |
| title_short | Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting |
| title_sort | multivariate deep learning approach for electric vehicle speed forecasting |
| topic | electric vehicle (ev) multivariate long short-term memory (lstm) speed forecasting deep learning |
| url | https://www.sciopen.com/article/10.26599/BDMA.2020.9020027 |
| work_keys_str_mv | AT youssefnaitmalek multivariatedeeplearningapproachforelectricvehiclespeedforecasting AT mehdinajib multivariatedeeplearningapproachforelectricvehiclespeedforecasting AT mohamedbakhouya multivariatedeeplearningapproachforelectricvehiclespeedforecasting AT mohammedessaaidi multivariatedeeplearningapproachforelectricvehiclespeedforecasting |