Synthesis of electric vehicle charging data: A real-world data-driven approach

Nowadays, electric vehicles (EVs) are increasingly equipped with advanced onboard devices capable of collecting and recording real-time charging data. The analysis of such data from a large-scale EV fleet plays a crucial role in supporting decision-making processes, particularly in the deployment of...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhi Li, Zilin Bian, Zhibin Chen, Kaan Ozbay, Minghui Zhong
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Communications in Transportation Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772424724000118
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061888386236416
author Zhi Li
Zilin Bian
Zhibin Chen
Kaan Ozbay
Minghui Zhong
author_facet Zhi Li
Zilin Bian
Zhibin Chen
Kaan Ozbay
Minghui Zhong
author_sort Zhi Li
collection DOAJ
description Nowadays, electric vehicles (EVs) are increasingly equipped with advanced onboard devices capable of collecting and recording real-time charging data. The analysis of such data from a large-scale EV fleet plays a crucial role in supporting decision-making processes, particularly in the deployment of charging infrastructure and the formulation of EV-focused policies. Nevertheless, the challenges of collecting these data are significant, primarily due to privacy concerns and the high costs associated with data access. In response, this study introduces an innovative methodology for generating large-scale and diverse EV charging data, mirroring real-world patterns for cost-efficient and privacy-compliant use. Specifically, this approach combines Gibbs sampling and conditional density networks and was trained and validated using a real-world dataset consisting of approximately 1.65 million charging events from 3,777 battery EVs (BEVs) in Shanghai over a year. Results illustrate that the proposed model can effectively capture the underlying distribution of the original charging data, enabling the generation of synthetic samples that closely resemble real-world charging events. The approach is readily employed for data imputation and augmentation, and it can also help simulate future charging distributions by conditional generation based on anticipated development premises.
format Article
id doaj-art-7db82def10e04f01a46e0d29bf902190
institution DOAJ
issn 2772-4247
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Communications in Transportation Research
spelling doaj-art-7db82def10e04f01a46e0d29bf9021902025-08-20T02:50:04ZengElsevierCommunications in Transportation Research2772-42472024-12-01410012810.1016/j.commtr.2024.100128Synthesis of electric vehicle charging data: A real-world data-driven approachZhi Li0Zilin Bian1Zhibin Chen2Kaan Ozbay3Minghui Zhong4Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning, NYU Shanghai, Shanghai, 200126, China; Shanghai Key Laboratory of Urban Design and Urban Science, NYU Shanghai, Shanghai, 200126, ChinaDepartment of Civil and Urban Engineering, New York University, New York, 11201, USAShanghai Frontiers Science Center of Artificial Intelligence and Deep Learning, NYU Shanghai, Shanghai, 200126, China; Shanghai Key Laboratory of Urban Design and Urban Science, NYU Shanghai, Shanghai, 200126, China; Corresponding author. Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning, NYU Shanghai, Shanghai, 200126, China.C2SMARTER Center (A Tier 1 USDOT UTC), Department of Civil and Urban Engineering, New York University, New York, 11201, USAShanghai Electric Vehicle Public Data Collecting, Monitoring, and Research Center, Shanghai, 201805, ChinaNowadays, electric vehicles (EVs) are increasingly equipped with advanced onboard devices capable of collecting and recording real-time charging data. The analysis of such data from a large-scale EV fleet plays a crucial role in supporting decision-making processes, particularly in the deployment of charging infrastructure and the formulation of EV-focused policies. Nevertheless, the challenges of collecting these data are significant, primarily due to privacy concerns and the high costs associated with data access. In response, this study introduces an innovative methodology for generating large-scale and diverse EV charging data, mirroring real-world patterns for cost-efficient and privacy-compliant use. Specifically, this approach combines Gibbs sampling and conditional density networks and was trained and validated using a real-world dataset consisting of approximately 1.65 million charging events from 3,777 battery EVs (BEVs) in Shanghai over a year. Results illustrate that the proposed model can effectively capture the underlying distribution of the original charging data, enabling the generation of synthetic samples that closely resemble real-world charging events. The approach is readily employed for data imputation and augmentation, and it can also help simulate future charging distributions by conditional generation based on anticipated development premises.http://www.sciencedirect.com/science/article/pii/S2772424724000118Electric vehiclesCharging dataData augmentationData generationGibbs samplingConditional density network
spellingShingle Zhi Li
Zilin Bian
Zhibin Chen
Kaan Ozbay
Minghui Zhong
Synthesis of electric vehicle charging data: A real-world data-driven approach
Communications in Transportation Research
Electric vehicles
Charging data
Data augmentation
Data generation
Gibbs sampling
Conditional density network
title Synthesis of electric vehicle charging data: A real-world data-driven approach
title_full Synthesis of electric vehicle charging data: A real-world data-driven approach
title_fullStr Synthesis of electric vehicle charging data: A real-world data-driven approach
title_full_unstemmed Synthesis of electric vehicle charging data: A real-world data-driven approach
title_short Synthesis of electric vehicle charging data: A real-world data-driven approach
title_sort synthesis of electric vehicle charging data a real world data driven approach
topic Electric vehicles
Charging data
Data augmentation
Data generation
Gibbs sampling
Conditional density network
url http://www.sciencedirect.com/science/article/pii/S2772424724000118
work_keys_str_mv AT zhili synthesisofelectricvehiclechargingdataarealworlddatadrivenapproach
AT zilinbian synthesisofelectricvehiclechargingdataarealworlddatadrivenapproach
AT zhibinchen synthesisofelectricvehiclechargingdataarealworlddatadrivenapproach
AT kaanozbay synthesisofelectricvehiclechargingdataarealworlddatadrivenapproach
AT minghuizhong synthesisofelectricvehiclechargingdataarealworlddatadrivenapproach