Reliability of electric vehicle charging infrastructure: A cross-lingual deep learning approach

Yifan Liu; Azell Francis; Catharina Hollauer; M. Cade Lawson; Omar Shaikh; Ashley Cotsman; Khushi Bhardwaj; Aline Banboukian; Mimi Li; Anne Webb; Omar Isaac Asensio

doi:10.1016/j.commtr.2023.100095

Reliability of electric vehicle charging infrastructure: A cross-lingual deep learning approach

Yifan Liu, Azell Francis, Catharina Hollauer, M. Cade Lawson, Omar Shaikh, Ashley Cotsman, Khushi Bhardwaj, Aline Banboukian, Mimi Li, Anne Webb, Omar Isaac Asensio

Research output: Contribution to journal › Article › peer-review

30 Scopus citations

Abstract

Vehicle electrification has emerged as a global strategy to address climate change and emissions externalities from the transportation sector. Deployment of charging infrastructure is needed to accelerate technology adoption; however, managers and policymakers have had limited evidence on the use of public charging stations due to poor data sharing and decentralized ownership across regions. In this article, we use machine learning based classifiers to reveal insights about consumer charging behavior in 72 detected languages including Chinese. We investigate 10 years of consumer reviews in East and Southeast Asia from 2011 to 2021 to enable infrastructure evaluation at a larger geographic scale than previously available. We find evidence that charging stations at government locations result in higher failure rates with consumers compared to charging stations at private points of interest. This evidence contrasts with predictions in the U.S. and European markets, where the performance is closer to parity. We also find that networked stations with communication protocols provide a relatively higher quality of charging services, which favors policy support for connectivity, particularly for underserved or remote areas.

Original language	English
Article number	100095
Journal	Communications in Transportation Research
Volume	3
DOIs	https://doi.org/10.1016/j.commtr.2023.100095
State	Published - Dec 2023
Externally published	Yes

Funding

This work was supported by funding from the National Science Foundation (Nos. 1931980 and 1945332); Microsoft Azure for research; and the U.S. State Department Diplomacy Lab. For valuable discussions, we thank Jeff Austin and Siree Allers from the U.S. Embassy in Brunei. We also thank Jay Forrest at the Georgia Tech Library. This research was supported in part through research cyber infrastructure resources and services provided by the Partnership for an Advanced Computing Environment (PACE) at the Georgia Institute of Technology, Atlanta, Georgia, USA. This work was supported by funding from the National Science Foundation (Nos. 1931980 and 1945332 ); Microsoft Azure for research; and the U.S. State Department Diplomacy Lab. For valuable discussions, we thank Jeff Austin and Siree Allers from the U.S. Embassy in Brunei. We also thank Jay Forrest at the Georgia Tech Library. This research was supported in part through research cyber infrastructure resources and services provided by the Partnership for an Advanced Computing Environment (PACE) at the Georgia Institute of Technology , Atlanta, Georgia, USA.

Funders	Funder number
Microsoft Azure
U.S. Embassy in Brunei
National Science Foundation	1931980, 1945332
U.S. Department of State
Georgia Institute of Technology

Keywords

Charging infrastructure
Consumer behavior
Electric vehicles
Machine learning
Natural language processing
Public policy
Transformer algorithms

UN SDGs

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

Access to Document

10.1016/j.commtr.2023.100095

Cite this

@article{c6ee9d723ccc42a989ea1ee778b4945e,

title = "Reliability of electric vehicle charging infrastructure: A cross-lingual deep learning approach",

abstract = "Vehicle electrification has emerged as a global strategy to address climate change and emissions externalities from the transportation sector. Deployment of charging infrastructure is needed to accelerate technology adoption; however, managers and policymakers have had limited evidence on the use of public charging stations due to poor data sharing and decentralized ownership across regions. In this article, we use machine learning based classifiers to reveal insights about consumer charging behavior in 72 detected languages including Chinese. We investigate 10 years of consumer reviews in East and Southeast Asia from 2011 to 2021 to enable infrastructure evaluation at a larger geographic scale than previously available. We find evidence that charging stations at government locations result in higher failure rates with consumers compared to charging stations at private points of interest. This evidence contrasts with predictions in the U.S. and European markets, where the performance is closer to parity. We also find that networked stations with communication protocols provide a relatively higher quality of charging services, which favors policy support for connectivity, particularly for underserved or remote areas.",

keywords = "Charging infrastructure, Consumer behavior, Electric vehicles, Machine learning, Natural language processing, Public policy, Transformer algorithms",

author = "Yifan Liu and Azell Francis and Catharina Hollauer and Lawson, {M. Cade} and Omar Shaikh and Ashley Cotsman and Khushi Bhardwaj and Aline Banboukian and Mimi Li and Anne Webb and Asensio, {Omar Isaac}",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors",

year = "2023",

month = dec,

doi = "10.1016/j.commtr.2023.100095",

language = "English",

volume = "3",

journal = "Communications in Transportation Research",

issn = "2772-4247",

publisher = "Elsevier",

}

TY - JOUR

T1 - Reliability of electric vehicle charging infrastructure

T2 - A cross-lingual deep learning approach

AU - Liu, Yifan

AU - Francis, Azell

AU - Hollauer, Catharina

AU - Lawson, M. Cade

AU - Shaikh, Omar

AU - Cotsman, Ashley

AU - Bhardwaj, Khushi

AU - Banboukian, Aline

AU - Li, Mimi

AU - Webb, Anne

AU - Asensio, Omar Isaac

PY - 2023/12

Y1 - 2023/12

N2 - Vehicle electrification has emerged as a global strategy to address climate change and emissions externalities from the transportation sector. Deployment of charging infrastructure is needed to accelerate technology adoption; however, managers and policymakers have had limited evidence on the use of public charging stations due to poor data sharing and decentralized ownership across regions. In this article, we use machine learning based classifiers to reveal insights about consumer charging behavior in 72 detected languages including Chinese. We investigate 10 years of consumer reviews in East and Southeast Asia from 2011 to 2021 to enable infrastructure evaluation at a larger geographic scale than previously available. We find evidence that charging stations at government locations result in higher failure rates with consumers compared to charging stations at private points of interest. This evidence contrasts with predictions in the U.S. and European markets, where the performance is closer to parity. We also find that networked stations with communication protocols provide a relatively higher quality of charging services, which favors policy support for connectivity, particularly for underserved or remote areas.

AB - Vehicle electrification has emerged as a global strategy to address climate change and emissions externalities from the transportation sector. Deployment of charging infrastructure is needed to accelerate technology adoption; however, managers and policymakers have had limited evidence on the use of public charging stations due to poor data sharing and decentralized ownership across regions. In this article, we use machine learning based classifiers to reveal insights about consumer charging behavior in 72 detected languages including Chinese. We investigate 10 years of consumer reviews in East and Southeast Asia from 2011 to 2021 to enable infrastructure evaluation at a larger geographic scale than previously available. We find evidence that charging stations at government locations result in higher failure rates with consumers compared to charging stations at private points of interest. This evidence contrasts with predictions in the U.S. and European markets, where the performance is closer to parity. We also find that networked stations with communication protocols provide a relatively higher quality of charging services, which favors policy support for connectivity, particularly for underserved or remote areas.

KW - Charging infrastructure

KW - Consumer behavior

KW - Electric vehicles

KW - Machine learning

KW - Natural language processing

KW - Public policy

KW - Transformer algorithms

UR - http://www.scopus.com/inward/record.url?scp=85152403242&partnerID=8YFLogxK

U2 - 10.1016/j.commtr.2023.100095

DO - 10.1016/j.commtr.2023.100095

M3 - Article

AN - SCOPUS:85152403242

SN - 2772-4247

VL - 3

JO - Communications in Transportation Research

JF - Communications in Transportation Research

M1 - 100095

ER -

Reliability of electric vehicle charging infrastructure: A cross-lingual deep learning approach

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this