The rapid growth of transportation sector and related emissions are attracting the attention of policymakers to ensure environmental sustainability. Therefore, the deriving factors of transport emissions are extremely important to comprehend. The role of electric vehicles is imperative amid rising transport emissions. Electric vehicles pave the way towards a low-carbon economy and sustainable environment. Successful deployment of electric vehicles relies heavily on energy consumption models that can predict energy consumption efficiently and reliably. Improving electric vehicles’ energy consumption efficiency will significantly help to alleviate driver anxiety and provide an essential framework for operation, planning, and management of the charging infrastructure. To tackle the challenge of electric vehicles’ energy consumption prediction, this study aims to employ advanced machine learning models, extreme gradient boosting, and light gradient boosting machine to compare with traditional machine learning models, multiple linear regression, and artificial neural network. Electric vehicles energy consumption data in the analysis were collected in Aichi Prefecture, Japan. To evaluate the performance of the prediction models, three evaluation metrics were used; coefficient of determination ( R²), root mean square error, and mean absolute error. The prediction outcome exhibits that the extreme gradient boosting and light gradient boosting machine provided better and robust results compared to multiple linear regression and artificial neural network. The models based on extreme gradient boosting and light gradient boosting machine yielded higher values of R², lower mean absolute error, and root mean square error values have proven to be more accurate. However, the results demonstrated that the light gradient boosting machine is outperformed the extreme gradient boosting model. A detailed feature important analysis was carried out to demonstrate the impact and relative influence of different input variables on electric vehicles energy consumption prediction. The results imply that an advanced machine learning model can enhance the prediction performance of electric vehicles energy consumption.

In this paper, we present an ensemble stacked generalization (ESG) approach for better prediction of electric vehicles (EVs) energy consumption. ESG is a weighted combination of multiple base regression models to one meta-regressor, which enhances the model prediction and decreases the model variance over a single regressor model. For the current study, we develop ESG by combining three individual base machine learning algorithms, i.e., Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbor (KNN), to predict the EVs’ energy consumption. Tackling the challenge of predicting EVs’ energy consumption, the data were collected from Aichi Prefecture, Japan, combining the digital elevation map with long-term GPS tracking data. EVs energy consumption in terms of energy efficiency (kWh/km) was estimated using several important variables such as average trip speed (km/h), trip distance, nighttime lighting, air conditioner (A/C), heater usage ratio, and road gradient. Several statistical evaluation metrics were used to evaluate the performance of the proposed methods. The prediction results show that ESG is more robust in predicting EVs’ energy consumption and outperformed other models by yielding more acceptable values for proposed evaluation metrics. The results further demonstrate that the accuracy of predictive models for EVs energy consumption can be reasonably accomplished by adopting stacking techniques. The finding of this study could provide essential guidance to decision-makers and practitioners for planned development and optimal placing of EV charging infrastructures in urban areas.