Electric Bus Battery Energy Consumption Estimation and Influencing Features Analysis Using a Two-Layer Stacking Framework with SHAP-Based Interpretation

Runze Liu, Jianming Cai, Lipeng Hu, Benxiao Lou and Jinjun Tang ()
Additional contact information
Runze Liu: School of Traffic & Transportation Engineering, Central South University, Changsha 410075, China
Jianming Cai: School of Traffic & Transportation Engineering, Central South University, Changsha 410075, China
Lipeng Hu: School of Traffic & Transportation Engineering, Central South University, Changsha 410075, China
Benxiao Lou: School of Traffic & Transportation Engineering, Central South University, Changsha 410075, China
Jinjun Tang: School of Traffic & Transportation Engineering, Central South University, Changsha 410075, China

Sustainability, 2025, vol. 17, issue 15, 1-27

Abstract: The widespread adoption of electric buses represents a major step forward in sustainable transportation, but also brings new operational challenges, particularly in terms of improving their efficiency and controlling costs. Therefore, battery energy consumption management is a key approach for addressing these issues. Accurate prediction of energy consumption and interpretation of the influencing factors are essential for improving operational efficiency, optimizing energy use, and reducing operating costs. Although existing studies have made progress in battery energy consumption prediction, challenges remain in achieving high-precision modeling and conducting a comprehensive analysis of the influencing features. To address these gaps, this study proposes a two-layer stacking framework for estimating the energy consumption of electric buses. The first layer integrates the strengths of three nonlinear regression models—RF (Random Forest), GBDT (Gradient Boosted Decision Trees), and CatBoost (Categorical Boosting)—to enhance the modeling capacity for complex feature relationships. The second layer employs a Linear Regression model as a meta-learner to aggregate the predictions from the base models and improve the overall predictive performance. The framework is trained on 2023 operational data from two electric bus routes (NO. 355 and NO. W188) in Changsha, China, incorporating battery system parameters, driving characteristics, and environmental variables as independent variables for model training and analysis. Comparative experiments with various ensemble models demonstrate that the proposed stacking framework exhibits superior performance in data fitting. Furthermore, XGBoost (Extreme Gradient Boosting, version 2.1.4) is introduced as a surrogate model to approximate the decision logic of the stacking framework, enabling SHAP (SHapley Additive exPlanations) analysis to quantify the contribution and marginal effects of influencing features. The proposed stacked and surrogate models achieved superior battery energy consumption prediction accuracy (lowest MSE, RMSE, and MAE), significantly outperforming benchmark models on real-world datasets. SHAP analysis quantified the overall contributions of feature categories (battery operation parameters: 56.5%; driving characteristics: 42.3%; environmental data: 1.2%), further revealing the specific contributions and nonlinear influence mechanisms of individual features. These quantitative findings offer specific guidance for optimizing battery system control and driving behavior.

Keywords: energy consumption; stacking model; SHAP theorem; battery system; electric vehicle (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/15/7105/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/15/7105/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:15:p:7105-:d:1718265

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().