Energy Consumption Prediction for Electric Vehicles Based on Real-World Data

Cedric De Cauwer, Joeri Van Mierlo and Thierry Coosemans
Additional contact information
Cedric De Cauwer: Electrotechnical Engineering and Energy Technology, MOBI Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium
Joeri Van Mierlo: Electrotechnical Engineering and Energy Technology, MOBI Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium
Thierry Coosemans: Electrotechnical Engineering and Energy Technology, MOBI Research Group, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium

Energies, 2015, vol. 8, issue 8, 1-21

Abstract: Electric vehicle (EV) energy consumption is variable and dependent on a number of external factors such as road topology, traffic, driving style, ambient temperature, etc. The goal of this paper is to detect and quantify correlations between the kinematic parameters of the vehicle and its energy consumption. Real-world data of EV energy consumption are used to construct the energy consumption calculation models. Based on the vehicle dynamics equation as underlying physical model, multiple linear regression is used to construct three models. Each model uses a different level of aggregation of the input parameters, allowing predictions using different types of available input parameters. One model uses aggregated values of the kinematic parameters of trips. This model allows prediction with basic, easily available input parameters such as travel distance, travel time, and temperature. The second model extends this by including detailed acceleration data. The third model uses the raw data of the kinematic parameters as input parameters to predict the energy consumption. Using detailed values of kinematic parameters for the prediction in theory increases the link between the statistical model and its underlying physical principles, but requires these parameters to be available as input in order to make predictions. The first two models show similar results. The third model shows a worse fit than the first two, but has a similar accuracy. This model has great potential for future improvement.

Keywords: electric vehicle; energy consumption; real-world data; prediction (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2015
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (57)

Downloads: (external link)
https://www.mdpi.com/1996-1073/8/8/8573/pdf (application/pdf)
https://www.mdpi.com/1996-1073/8/8/8573/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:8:y:2015:i:8:p:8573-8593:d:54101

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().