Shelby Hall Graduate Research Forum Posters
Forecasting Vehicle Driving Energy Consumption Based on User Driving Patterns
Files
Description
Research on driving energy has become more popular due to the high adoption of electric vehicles (EVs). The main concern of EV users is battery charging and uncertainty of when to charge. In addition, the increasing amount of EVs poses extra load to the electric grid that might not be prepared for it. Thus, predicting driving energy even from internal combustion energy (ICE) vehicles is necessary to estimate how much the load is expected to increase when the ICE drivers change their vehicles to EVs. This research created a comprehensive dataset from real-world driving data for one month in Mobile, AL. A vehicle's CAN bus data logger was installed to collect dynamic data such as speed, acceleration, latitude, longitude, and altitude. The dataset containing about five thousand kilometers of driving distance and about one thousand individual trips was used to calculate the driving energy profile and present its time series. Statistical techniques such as the Augmented Dickey-Fuller (ADF) test, Auto-Correlation Function (ACF), and Partial Auto-Correlation Function (PACF) are implemented to evaluate stationarity, autocorrelation, and seasonality properties of the time series. The results show that the data is stationary. However, it has a seasonality of twelve hours, and energy consumption is higher at the beginning of every cycle than during the other cycle period. Then, machine learning algorithms such as Long Short-Term Memory (LSTM) are implemented to predict the vehicle's energy consumption for the following day. The prediction helps EV users plan their vehicle charging times.
Publication Date
3-2025
Department
Electrical & Computer Engineering
City
Mobile
Disciplines
Other Electrical and Computer Engineering | Power and Energy
Recommended Citation
Rahman, Md. Mizanur and Wolter Ferreira Touma, Daniela, "Forecasting Vehicle Driving Energy Consumption Based on User Driving Patterns" (2025). Shelby Hall Graduate Research Forum Posters. 25.
https://jagworks.southalabama.edu/southalabama-shgrf-posters/25