An eco-driving strategy for electric buses at signalized intersection with a bus stop based on energy consumption prediction
Yingjiu Pan,
Yi Xi,
Wenpeng Fang,
Yansen Liu,
Yali Zhang and
Wenshan Zhang
Energy, 2025, vol. 317, issue C
Abstract:
The interaction between signalized intersections and downstream bus stops often leads to increased energy consumption in electric city buses. To address this issue, this study proposes a specialized eco-driving strategy tailored for electric buses operating at signalized intersections and bus stops. First, this study investigates how driving behavior affects energy consumption and develops a predictive model for energy consumption utilizing real-world driving data. Second, an optimized reward function is formulated based on the constructed energy consumption prediction model, incorporating considerations of safety, efficiency, and comfort. Subsequently, an acceleration and deceleration strategy are established using the Soft Actor-Critic framework to generate an eco-velocity curve. The effectiveness of this strategy is evaluated against real-world driving data. When compared to the driving behaviors observed in three distinct real-world scenarios, the proposed strategy demonstrates energy savings of 31.19 %, 20.84 %, and 30.29 % for electric buses navigating signalized intersections and bus stops continuously.
Keywords: Connected electric buses; Energy consumption prediction; Eco-driving; Deep reinforcement learning; Signalized intersection with a bus stop (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225003147
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:317:y:2025:i:c:s0360544225003147
DOI: 10.1016/j.energy.2025.134672
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 ().