Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on Electric Vehicle Routing Problem Based on Reinforcement Learning

Download as PDF

DOI: 10.23977/autml.2023.040106 | Downloads: 17 | Views: 612

Author(s)

Shaomin Zhang 1, Kunpeng Wang 1, Baoyi Wang 1

Affiliation(s)

1 School of Control and Computer Engineering, North China Electric Power University, Baoding, Hebei, 071003, China

Corresponding Author

Shaomin Zhang

ABSTRACT

As an emerging means of transportation, electric vehicles have been regarded as having broad application prospects due to their advantages in energy conservation, emission reduction and carbon neutrality. However, due to the limitation of cruise range and the inconvenience of charging process, the promotion of electric vehicles is not smooth. So we introduces the application of reinforcement learning in this field and proposes a deep reinforcement learning scheme based on D3QN (Dueling Double DQN) to solve it. Finally, we compare D3QN algorithm with the current general DQN and DDQN algorithms in terms of success rate and reward value through comparative experiments.

KEYWORDS

Electric vehicle, Deep learning, Reinforcement learning, Path planning

CITE THIS PAPER

Shaomin Zhang, Kunpeng Wang, Baoyi Wang, Research on Electric Vehicle Routing Problem Based on Reinforcement Learning. Automation and Machine Learning (2023) Vol. 4: 41-46. DOI: http://dx.doi.org/10.23977/autml.2023.040106.

REFERENCES

[1] G. B. Dantzig and J. H. Ramser. The Truck Dispatching Problem [J]. Management Science, 1959, 6(1): 80-91.
[2] C. Zhang, Y. Liu, F. Wu, B. Tang and W. Fan, "Effective Charging Planning Based on Deep Reinforcement Learning for Electric Vehicles," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 1, pp. 542-554, Jan. 2021, doi: 10.1109/TITS. 2020.3002271.
[3] Rafael Basso, Balázs Kulcsár, Ivan Sanchez-Diaz, Xiaobo Qu, Dynamic stochastic electric vehicle routing with safe reinforcement learning, Transportation Research Part E: Logistics and Transportation Review, Volume 157, 2022, 102496, ISSN 1366-5545.
[4] Q. Zhang, K. Wu and Y. Shi, "Route Planning and Power Management for PHEVs With Reinforcement Learning," in IEEE Transactions on Vehicular Technology, vol. 69, no. 5, pp. 4751-4762, May 2020, doi: 10.1109/TVT. 2020.2979623.
[5] M. Ye, C. Tianqing and F. Wenhui, "A single-task and multi-decision evolutionary game model based on multi-agent reinforcement learning," in Journal of Systems Engineering and Electronics, vol. 32, no. 3, pp. 642-657, June 2021, doi: 10.23919/JSEE. 2021.000055.
[6] Y. Huang, G. Wei and Y. Wang, "V-D D3QN: the Variant of Double Deep Q-Learning Network with Dueling Architecture," 2018 37th Chinese Control Conference (CCC), 2018, pp. 9130-9135, doi: 10.23919/ChiCC. 2018.8483478.
[7] Queck B., Lau H. C. (2020). A Genetic Algorithm to Minimise the Number of Vehicles in the Electric Vehicle Routing Problem. In: Lalla-Ruiz, E., Mes, M., Voß, S. (eds) Computational Logistics. ICCL 2020. Lecture Notes in Computer Science, vol 12433. Springer, Cham. 
[8] Ben Abbes S., Rejeb L., Baati L.: Route planning for electric vehicles. IET Intell. Transp. Syst. 16, 875– 889 (2022).
[9] C. Zhang, Y. Liu, F. Wu, B. Tang and W. Fan, "Effective Charging Planning Based on Deep Reinforcement Learning for Electric Vehicles," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 1, pp. 542-554, Jan. 2021, doi: 10.1109/TITS. 2020.3002271. 
[10] R. Szczepanski, T. Tarczewski and K. Erwinski, "Energy Efficient Local Path Planning Algorithm Based on Predictive Artificial Potential Field," in IEEE Access, vol. 10, pp. 39729-39742, 2022, doi: 10. 1109/ ACCESS. 2022. 3166632.

Downloads: 1592
Visits: 67135

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.