“Optimizing And Predicting Energy Consumption In Electric Vehicles Using Deep Learning: A Comparative Study Of GRU And LSTM Models”

In this paper, we present a deep learning approach, using the Gated Recurrent Unit (GRU) model, for predicting energy consumption in electric vehicles (EVs) energy consumption. The adoption of electric vehicles in the market still faces challenges due to their limited driving range, in addition to the time required for charging batteries. Each time, before starting a journey, the driver has to assess whether the available charge on the battery is enough or not. Frequently, this estimation is based on the travelling distance and past consumption. There are two aspects that can have a very significant influence on the battery consumption: the route and the driving style.  For the current study, we predict power consumption (kilowatt-hours per 100 kilometers). In this, combinedly utilizes   three individual base machine learning algorithms, i.e., Linear regression, Random Forest (RF), and Support Vector Mechanism (SVMs), and Two Deep Learning technique as LSTM and The Gated Recurrent Unit (GRU) to predict the EVs’ energy consumption. Tackling the challenge of predicting EVs’ energy consumption, the data were collected from Volkswagen_e_golf-n (30 e-vehicles data). EVs energy consumption in terms of energy efficiency (kilowatt-hours per 100 kilometers) was estimated using several important variables as Trip distance (Km), consumption (kWh), Rural/ Urban, road condition, Temperature condition, park heating, average speed (Km/Hr.), Driving style, and Target consumption as kilowatt-hours per 100 kilometers.   The prediction results demonstrate that GRU is more robust in predicting EVs’ energy consumption. The results also indicate that the accuracy of predictive models for EVs energy consumption can be reasonably accomplished by adopting GRU techniques. The GRU model achieved a mean squared error of X, outperforming Linear Regression (Y), Random Forest (Z), and LSTM (W), thus demonstrating superior accuracy in predicting energy consumption. The adoption rate of electric vehicles is likely to increase as charging infrastructure becomes more widespread and accessible. These results can significantly aid in improving EV range estimations, potentially encouraging broader adoption of electric vehicles.