Recognition of electric vehicles charging patterns with machine learning techniques

Shekari, M, Arasteh, H and Vahidinasab, V ORCID: https://orcid.org/0000-0002-0779-8727, 2022. Recognition of electric vehicles charging patterns with machine learning techniques. In: Vahidinasab, V ORCID: https://orcid.org/0000-0002-0779-8727 and Mohammadi-Ivatloo, B, eds., Electric vehicle integration via smart charging: technology, standards, implementation, and applications. Green Energy and Technology . Cham: Springer, pp. 49-83. ISBN 9783031059087

Preview

Text 1601397_Vahidinasab.pdf - Post-print Download (1MB) | Preview

Abstract

In recent years, the utilization of electric vehicles (EVs) and renewable energy sources (RESs) are highly interested in supplying some parts of the required energy and paving the way for reaching other goals, such as emission reduction. However, uncontrolled energy management of the EVs’ high penetration may adversely affect the distribution system. The chapter aims to investigate the charging behavior of EVs. By analyzing the charging patterns of the EV stations, different rules could be developed to manage the EV charging patterns. This chapter introduced the machine learning (ML)-based approach to cluster the EV charging behaviors and improve the management of EVs by distinguishing the most representative charging patterns. Identifying clusters of EV charging patterns was conducted via the unsupervised learning ML method, while the supervised learning ML method was utilized for further classification of the dataset. An example was also used to demonstrate the effectiveness of the proposed method.

Item Type:	Chapter in book
Creators:	Shekari, M., Arasteh, H. and Vahidinasab, V.
Publisher:	Springer
Place of Publication:	Cham
Date:	2022
ISBN:	9783031059087
Identifiers:	Number Type 10.1007/978-3-031-05909-4_3 DOI 1601387 Other
Divisions:	Schools > School of Science and Technology
Record created by:	Laura Ward
Date Added:	26 Sep 2022 11:25
Last Modified:	10 Sep 2024 03:00
URI:	https://irep.ntu.ac.uk/id/eprint/47118

Actions (login required)

Edit View

Statistics

Views

Downloads