Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization

Chengwei Liu; Jiangliang Jin; Liangliang Hao; Qisheng Huang; Yunjian Xu

doi:10.1109/EPSIC70071.2026.11590711

Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization

Chengwei Liu
, Jiangliang Jin^*
, Liangliang Hao
, Qisheng Huang
, Yunjian Xu

^*Corresponding author for this work

Donghua University
Shandong University
School of Robotics and Advanced Manufacture, Harbin Institute of Technology Shenzhen
Chinese University of Hong Kong

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We study an electric vehicle (EV) routing problem in random traffic environments, time-varying energy prices, and uncertain service delays. Leveraging real-time information from intelligent transportation systems and smart grids, the EV's objective is to minimize the total cost of travel and charging. To capture multi-node relationships in transportation networks, we propose a hypergraph-based deep reinforcement learning method. A hypergraph neural network (HGNN) is employed to extract hypergraph neighborhood features, which are input into a proximal policy optimization (PPO) algorithm for efficient online routing decisions.

Original language	English
Title of host publication	2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331552534
DOIs	https://doi.org/10.1109/EPSIC70071.2026.11590711
State	Published - 2026
Externally published	Yes
Event	3rd IEEE International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026 - Hybrid, Tianjin, China Duration: 22 May 2026 → 24 May 2026

Publication series

Name	2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026

Conference

Conference	3rd IEEE International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026
Country/Territory	China
City	Hybrid, Tianjin
Period	22/05/26 → 24/05/26

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

deep reinforcement learning
electric vehicle routing guidance
hypergraph neural network

Access to Document

10.1109/EPSIC70071.2026.11590711

Cite this

Liu, C., Jin, J., Hao, L., Huang, Q., & Xu, Y. (2026). Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization. In 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026 (2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EPSIC70071.2026.11590711

Liu, Chengwei ; Jin, Jiangliang ; Hao, Liangliang et al. / Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization. 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026. Institute of Electrical and Electronics Engineers Inc., 2026. (2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026).

@inproceedings{2c6a2918b01b467ab7e7611f86785414,

title = "Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization",

abstract = "We study an electric vehicle (EV) routing problem in random traffic environments, time-varying energy prices, and uncertain service delays. Leveraging real-time information from intelligent transportation systems and smart grids, the EV's objective is to minimize the total cost of travel and charging. To capture multi-node relationships in transportation networks, we propose a hypergraph-based deep reinforcement learning method. A hypergraph neural network (HGNN) is employed to extract hypergraph neighborhood features, which are input into a proximal policy optimization (PPO) algorithm for efficient online routing decisions.",

keywords = "deep reinforcement learning, electric vehicle routing guidance, hypergraph neural network",

author = "Chengwei Liu and Jiangliang Jin and Liangliang Hao and Qisheng Huang and Yunjian Xu",

note = "Publisher Copyright: {\textcopyright} 2026 IEEE.; 3rd IEEE International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026 ; Conference date: 22-05-2026 Through 24-05-2026",

year = "2026",

doi = "10.1109/EPSIC70071.2026.11590711",

language = "英语",

series = "2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026",

address = "美国",

}

Liu, C, Jin, J, Hao, L, Huang, Q & Xu, Y 2026, Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization. in 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026. 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026, Institute of Electrical and Electronics Engineers Inc., 3rd IEEE International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026, Hybrid, Tianjin, China, 22/05/26. https://doi.org/10.1109/EPSIC70071.2026.11590711

Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization. / Liu, Chengwei; Jin, Jiangliang; Hao, Liangliang et al.
2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026. Institute of Electrical and Electronics Engineers Inc., 2026. (2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization

AU - Liu, Chengwei

AU - Jin, Jiangliang

AU - Hao, Liangliang

AU - Huang, Qisheng

AU - Xu, Yunjian

PY - 2026

Y1 - 2026

N2 - We study an electric vehicle (EV) routing problem in random traffic environments, time-varying energy prices, and uncertain service delays. Leveraging real-time information from intelligent transportation systems and smart grids, the EV's objective is to minimize the total cost of travel and charging. To capture multi-node relationships in transportation networks, we propose a hypergraph-based deep reinforcement learning method. A hypergraph neural network (HGNN) is employed to extract hypergraph neighborhood features, which are input into a proximal policy optimization (PPO) algorithm for efficient online routing decisions.

AB - We study an electric vehicle (EV) routing problem in random traffic environments, time-varying energy prices, and uncertain service delays. Leveraging real-time information from intelligent transportation systems and smart grids, the EV's objective is to minimize the total cost of travel and charging. To capture multi-node relationships in transportation networks, we propose a hypergraph-based deep reinforcement learning method. A hypergraph neural network (HGNN) is employed to extract hypergraph neighborhood features, which are input into a proximal policy optimization (PPO) algorithm for efficient online routing decisions.

KW - deep reinforcement learning

KW - electric vehicle routing guidance

KW - hypergraph neural network

UR - https://www.scopus.com/pages/publications/105045557002

U2 - 10.1109/EPSIC70071.2026.11590711

DO - 10.1109/EPSIC70071.2026.11590711

M3 - 会议稿件

AN - SCOPUS:105045557002

T3 - 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026

BT - 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026

Y2 - 22 May 2026 through 24 May 2026

ER -

Liu C, Jin J, Hao L, Huang Q, Xu Y. Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization. In 2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026. Institute of Electrical and Electronics Engineers Inc. 2026. (2026 IEEE 3rd International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2026). doi: 10.1109/EPSIC70071.2026.11590711

Hypergraph Deep Reinforcement Learning for Electric Vehicle Charging Route Optimization

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this