Cyber attacks detection in electric vehicles fast charging stations using wavelets and deep learning

The Integration of the electric vehicles fast charging stations with smart electric grid allows the electric vehicles to provide regulation services (e.g., voltage and frequency) to the grid through the Vehicle-to-Grid (V2G) concept. An effective service provision dictates the integration of communication networks to smart grid components, which makes many of the smart grid assets prone to cyber vulnerability threats. This thesis addresses the impact of cyber-attack in the electric vehicles fast charging stations and its consequences on the power quality. The thesis proposes a cyber-attacks detection approach based on signal processing and deep learning to early detect such attacks. The proposed detection approach has the ability to learn, detect and classify such attacks under different operating conditions and using different time resolutions of smart meters. The results have shown that the proposed approach was effective in detecting the cyber-attacks at an average accuracy of nearly 99.4%.

Name thesis:degree_name

Master of Applied Science (MASc)

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Ontario Institute of Technology

Year dc:date.issued

2022

Author dc:creator

• Abu Nassar, Ahmad

Advisor dc:contributor.advisor

• Ibrahim, Walid Morsi

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10155/2028

OAI identifier oai:identifier

oai:ontariotechu.scholaris.ca:10155/2028