1 Citation (Scopus)

Abstract

© The Institution of Engineering and Technology 2018. In order to manage the charging behaviour of electric vehicles (EVs), this study for the first time develops a set of EV charging load profiles: EV templates. EV charging profiles have unique waveforms similar to a rectangular pulse train. This characteristics significantly limits the performance of clustering analysis in that traditional distance calculation, such as Euclidean distance, which cannot reflect the morphological dissimilarities. This study proposes a novel clustering method using rough set theory to accurately measure the dissimilarity between the EV profiles. The pulse train waves are firstly extracted as mixed data features, which are partitioned by an improved K-prototypes method based on rough set distance. The proposed method is implemented on the real charging load profiles and compared with K-means and traditional K-prototypes. Their clustering performances are evaluated by diverse validity indices. The results show that the proposed method outperforms other comparison methods.
Original languageEnglish
Pages (from-to)4361-4367
Number of pages7
JournalIET Generation, Transmission and Distribution
Volume12
Issue number20
DOIs
Publication statusPublished - 13 Nov 2018

Cite this

Development of EV charging templates: An improved K-prototypes method. / Hong, Juhua; Xiang, Yue; Liu, Youbo; Liu, Junyong; Li, Ran; Li, Furong; Gou, Jing.

In: IET Generation, Transmission and Distribution, Vol. 12, No. 20, 13.11.2018, p. 4361-4367.

Research output: Contribution to journalArticle

Hong, Juhua ; Xiang, Yue ; Liu, Youbo ; Liu, Junyong ; Li, Ran ; Li, Furong ; Gou, Jing. / Development of EV charging templates: An improved K-prototypes method. In: IET Generation, Transmission and Distribution. 2018 ; Vol. 12, No. 20. pp. 4361-4367.
@article{594657faab654cc0be18dee51e6347a0,
title = "Development of EV charging templates: An improved K-prototypes method",
abstract = "{\circledC} The Institution of Engineering and Technology 2018. In order to manage the charging behaviour of electric vehicles (EVs), this study for the first time develops a set of EV charging load profiles: EV templates. EV charging profiles have unique waveforms similar to a rectangular pulse train. This characteristics significantly limits the performance of clustering analysis in that traditional distance calculation, such as Euclidean distance, which cannot reflect the morphological dissimilarities. This study proposes a novel clustering method using rough set theory to accurately measure the dissimilarity between the EV profiles. The pulse train waves are firstly extracted as mixed data features, which are partitioned by an improved K-prototypes method based on rough set distance. The proposed method is implemented on the real charging load profiles and compared with K-means and traditional K-prototypes. Their clustering performances are evaluated by diverse validity indices. The results show that the proposed method outperforms other comparison methods.",
author = "Juhua Hong and Yue Xiang and Youbo Liu and Junyong Liu and Ran Li and Furong Li and Jing Gou",
year = "2018",
month = "11",
day = "13",
doi = "10.1049/iet-gtd.2017.1911",
language = "English",
volume = "12",
pages = "4361--4367",
journal = "IET Generation, Transmission and Distribution",
issn = "1751-8687",
publisher = "Institution of Engineering and Technology",
number = "20",

}

TY - JOUR

T1 - Development of EV charging templates: An improved K-prototypes method

AU - Hong, Juhua

AU - Xiang, Yue

AU - Liu, Youbo

AU - Liu, Junyong

AU - Li, Ran

AU - Li, Furong

AU - Gou, Jing

PY - 2018/11/13

Y1 - 2018/11/13

N2 - © The Institution of Engineering and Technology 2018. In order to manage the charging behaviour of electric vehicles (EVs), this study for the first time develops a set of EV charging load profiles: EV templates. EV charging profiles have unique waveforms similar to a rectangular pulse train. This characteristics significantly limits the performance of clustering analysis in that traditional distance calculation, such as Euclidean distance, which cannot reflect the morphological dissimilarities. This study proposes a novel clustering method using rough set theory to accurately measure the dissimilarity between the EV profiles. The pulse train waves are firstly extracted as mixed data features, which are partitioned by an improved K-prototypes method based on rough set distance. The proposed method is implemented on the real charging load profiles and compared with K-means and traditional K-prototypes. Their clustering performances are evaluated by diverse validity indices. The results show that the proposed method outperforms other comparison methods.

AB - © The Institution of Engineering and Technology 2018. In order to manage the charging behaviour of electric vehicles (EVs), this study for the first time develops a set of EV charging load profiles: EV templates. EV charging profiles have unique waveforms similar to a rectangular pulse train. This characteristics significantly limits the performance of clustering analysis in that traditional distance calculation, such as Euclidean distance, which cannot reflect the morphological dissimilarities. This study proposes a novel clustering method using rough set theory to accurately measure the dissimilarity between the EV profiles. The pulse train waves are firstly extracted as mixed data features, which are partitioned by an improved K-prototypes method based on rough set distance. The proposed method is implemented on the real charging load profiles and compared with K-means and traditional K-prototypes. Their clustering performances are evaluated by diverse validity indices. The results show that the proposed method outperforms other comparison methods.

UR - http://www.scopus.com/inward/record.url?scp=85056466716&partnerID=8YFLogxK

U2 - 10.1049/iet-gtd.2017.1911

DO - 10.1049/iet-gtd.2017.1911

M3 - Article

AN - SCOPUS:85056466716

VL - 12

SP - 4361

EP - 4367

JO - IET Generation, Transmission and Distribution

JF - IET Generation, Transmission and Distribution

SN - 1751-8687

IS - 20

ER -