Economical path planning for electric vehicles considering traffic information

Hongwen He*, Jianbin Lin, Jiankun Peng, Qingwu Liu, Jianwei Li

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Vehicle exhaust pollution and traffic congestion are plaguing the daily life of the citizens. Although electric vehicles represent green travel, the problem of mileage anxiety still troubles electric occupants. Aiming at the existing problems, an electric vehicle energy consumption prediction based on LSTM deep learning technology combined with traffic information is proposed to plan the economical driving path with the best coupling of energy consumption and driving distance. The method has the ability to integrate multidimensional data of heterogeneous heads, solves the problem that electric vehicle energy consumption estimation cannot take into account real traffic information. And getting rid of the shortcomings of path planning relying only on driving distance, effectively improving the driving feeling of electric vehicles and bettering travel efficiency to optimize urban traffic conditions.

Original languageEnglish
JournalEnergy Proceedings
Volume6
Publication statusPublished - 2019
Event11th International Conference on Applied Energy, ICAE 2019 - Västerås, Sweden
Duration: 12 Aug 201915 Aug 2019

Keywords

  • Data fusion
  • Electric vehicle
  • Energy consumption forecast
  • Path planning

Cite this