Full-scene energy consumption prediction for electric vehicles: A knowledge-enhanced hybrid-driven framework

Dong Xie, Yu Jiang, Jianhua Guo and Yanbo Wang

Energy, 2025, vol. 333, issue C

Abstract: The increasing demand for decarbonization, combined with the development of intelligent transportation systems, has driven the emergence of eco-driving technologies for electric vehicles. Accurate energy consumption prediction is a crucial prerequisite and key input for these technologies. However, existing prediction models often struggle to balance interpretability with accuracy and tend to perform poorly in extreme scenarios. Therefore, this study proposes a knowledge-enhanced hybrid-driven framework for accurate energy consumption prediction across diverse scenarios. First, a hierarchical Markov-based model is employed, which integrates online-obtained StateTokens with an offline-constructed transition probability matrix library (TPML) to accurately predict future driving cycles. Subsequently, optimal energy consumption compensation knowledge is generated for various scenarios using the deep reinforcement learning algorithm, forming an optimal knowledge repository. Finally, in the online phase, adaptive knowledge transfer is employed to precisely integrate the optimal knowledge into a physical model, thereby enhancing the adaptability and generalization of the energy consumption model. Comprehensive validation across diverse scenarios and multiple dimensions demonstrates that the proposed framework outperforms baseline methods in predictive accuracy, achieving a mean absolute percentage error (MAPE) of only 6.69%, while maintaining strong interpretability. This innovative hybrid-driven framework offers a new avenue for energy consumption modeling and can inform the development of eco-driving technologies.

Keywords: Intelligent transportation system; Eco-driving; Electric vehicles; Energy consumption; Knowledge-enhanced; Deep reinforcement learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225027781
Full text for ScienceDirect subscribers only

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:eee:energy:v:333:y:2025:i:c:s0360544225027781

DOI: 10.1016/j.energy.2025.137136

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().