What question did this study set out to answer?

The aim is to enhance the accuracy of remaining driving range predictions for electric two-wheelers.

June 3, 2026World Electric Vehicle Journal0 citationsOpen Access

A Stacked Regression Framework for Remaining Driving Range Estimation in Electric Two-Wheelers

Key Points

The aim is to enhance the accuracy of remaining driving range predictions for electric two-wheelers.
Developed a stacked ensemble model using AdaBoost, CatBoost, Gradient Boosting, and Lasso Regression.
Used Grid Search Cross-Validation for model selection and hyperparameter tuning.
Validated with real-world driving data collected from three different electric two-wheeler models.
Achieved a Mean Absolute Error of 0.13, equating to an average prediction error of 130 m per trip.
The ensemble model demonstrated enhanced accuracy compared to baseline models.

Abstract

Accurate range prediction is crucial for reducing range anxiety and optimizing the energy management of electric two-wheelers (E2Ws). In this study, we propose a stacked ensemble model to predict the remaining driving range (RDR) of E2Ws with enhanced accuracy. Grid Search Cross-Validation (Grid Search CV) was employed for model selection and hyperparameter tuning to ensure the most effective regression models were chosen as base learners. The final ensemble consists of AdaBoost, CatBoost, Gradient Boosting, and Lasso Regression as base learners, while Ridge Regression serves as the meta-learner to refine predictions. To develop and validate the model, real-world driving data was collected from three different E2W models. The dataset underwent preprocessing and was evaluated using 10-fold cross-validation to ensure robustness. Experimental results demonstrate that the proposed stacked model achieves a Mean Absolute Error (MAE) of 0.13, corresponding to an average prediction error of 130 m per trip.

Ask AI

Helpful

Bookmark

View Full Paper