Skip to main navigation Skip to search Skip to main content

Data-driven prediction of fine-grained EV charging behaviors in public charging stations: Poster

  • Shanghai Jiao Tong University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

With the rapid growth of electrical vehicle public charging stations, accurate predictions of local charging demand enable many prospective applications. In this paper, we explore a data-driven approach to predict future charging demand, and build predictive models to characterize behaviors of both registered long-term users and unregistered short-term users. With a real-world dataset of 28053 records over 798 days at multiple locations, evaluation results demonstrate that our model with XGBoost outperforms existing solutions, reducing the prediction error up to 40.8% at the finest time granularity (15-minute interval).

Original languageEnglish
Title of host publicatione-Energy 2021 - Proceedings of the 2021 12th ACM International Conference on Future Energy Systems
PublisherAssociation for Computing Machinery, Inc
Pages276-277
Number of pages2
ISBN (Electronic)9781450383332
DOIs
StatePublished - Jun 22 2021
Event12th ACM International Conference on Future Energy Systems, e-Energy 2021 - Virtual, Online, Italy
Duration: Jun 28 2021Jul 2 2021

Publication series

Namee-Energy 2021 - Proceedings of the 2021 12th ACM International Conference on Future Energy Systems

Conference

Conference12th ACM International Conference on Future Energy Systems, e-Energy 2021
Country/TerritoryItaly
CityVirtual, Online
Period06/28/2107/2/21

Keywords

  • EV charging prediction
  • machine learning
  • user behaviors

Fingerprint

Dive into the research topics of 'Data-driven prediction of fine-grained EV charging behaviors in public charging stations: Poster'. Together they form a unique fingerprint.

Cite this