Energy Consumption Prediction for Electric Vehicles Based on Real-World Data
AbstractElectric 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. View Full-Text
Share & Cite This Article
De Cauwer, C.; Van Mierlo, J.; Coosemans, T. Energy Consumption Prediction for Electric Vehicles Based on Real-World Data. Energies 2015, 8, 8573-8593.
De Cauwer C, Van Mierlo J, Coosemans T. Energy Consumption Prediction for Electric Vehicles Based on Real-World Data. Energies. 2015; 8(8):8573-8593.Chicago/Turabian Style
De Cauwer, Cedric; Van Mierlo, Joeri; Coosemans, Thierry. 2015. "Energy Consumption Prediction for Electric Vehicles Based on Real-World Data." Energies 8, no. 8: 8573-8593.