Entire route eco-driving method for electric bus based on rule-based reinforcement learning

Lan Yang, Zhiqiang Hu, Liang Wang, Yang Liu, Jiangbo He, Xiaobo Qu, Xiangmo Zhao and Shan Fang

Transportation Research Part E: Logistics and Transportation Review, 2024, vol. 189, issue C

Abstract: Electric bus (EB) has gradually become one of the main ways of transportation in cities due to the low energy consumption and low pollutant emissions. As battery endurance is easily affected by various factors such as external temperature, vehicle load, and driving habits, the anxiety for the endurance of EB has become a concern for researchers. To bridge the gap, an eco-driving method based on deep reinforcement learning (DRL) is proposed to achieve the entire route energy-saving. Firstly, the significant factors including the dynamic passenger load and air conditioner is considered for the energy consumption model of the EB. Secondly, a rule-based reinforcement learning algorithm is utilized for optimizing the driving speed and strategy, which can accelerate the convergence of the proposed model and improve the average reward of the reward function. Thirdly, by adjusting the reward function of reinforcement learning algorithm, three eco-driving modes of EB, namely efficiency priority mode, energy-efficiency balance mode and energy saving priority mode under various operational states are proposed. Finally, the results indicate that the efficiency priority mode achieves about an 8% increase in traffic efficiency and a reduction of approximately 20% in energy consumption compared to the baseline model. With the energy-efficiency balance mode, the model attains a 34.05% reduction in energy consumption with almost the same traffic efficiency. Under the energy saving priority mode, the proposed model exhibits a minor reduction in traffic efficiency within an acceptable limit but decreases energy consumption by 40.69%, achieving the optimization goals.

Keywords: Electric bus; Eco-driving; Entire route speed optimization; Deep reinforcement learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1366554524002278
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:transe:v:189:y:2024:i:c:s1366554524002278

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/600244/bibliographic
http://www.elsevier. ... 600244/bibliographic

DOI: 10.1016/j.tre.2024.103636

Access Statistics for this article

Transportation Research Part E: Logistics and Transportation Review is currently edited by W. Talley

More articles in Transportation Research Part E: Logistics and Transportation Review from Elsevier
Bibliographic data for series maintained by Catherine Liu ().