EUVIMEDEUVIMED entdecken
Crossref

Cy-Phy ADS: Cyber-Physical Anomaly Detection Framework for EV Charging Systems

Harindra S. Mavikumbure, Victor Cobilean, Chathurika S. Wickramasinghe, Benny J. Varghese, Richard B. Carlson, Craig Rieger, Timothy Pennington, Milos Manic

IEEE Transactions on Transportation Electrification · 2024-12 · 10 (4) · 9904-9917

DOI: 10.1109/tte.2024.3363672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2024-12. Verfasst von Harindra S. Mavikumbure und 7 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Department of Energy through the U.S. DOE Idaho Operations Office, Commonwealth Cyber Initiative, an Investment in the Advancement of Cyber Research and Development, Innovation and Workforce Development.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Today’s large-scale electric vehicle (EV) infrastructures are heavily dependent on information communication technologies to maintain their operation and to support communication within sub-system components as well as the outside world. These technologies are vulnerable to various cyber and physical threats. Timely identification and mitigation of these threats are critical for improving human safety, avoiding economic losses, and preventing catastrophic system failures. By addressing this, our work presents a ResNet autoencoder (AE)-based cyber-physical anomaly detection system (Cy-Phy ADS) for detecting anomalies in EV controller area network (CAN) protocol communication. It consists of four main components: cyber-physical feature extractor, ResNet AE (RAE)-based anomaly detection (AD) framework, cyber-physical health metric (CPHM), and visualization dashboard. The presented framework was trained and tested using CAN data collected from the EV charging system testbed at the Idaho National Laboratory (INL). The presented Cy-Phy ADS was compared against six widely used unsupervised AD algorithms: one class support vector machine (OCSVM), variational AE (VAE), long short-term memory AE (LSTM AE), isolation forest (IForest), principal component analysis (PCA), and local outlier factor (LOF). The presented approach showed the highest accuracy among the compared methods. Further, the proposed approach showed comparable performance in terms of precision, F1, and false positive rate (FPR). It also showed the lowest training and inference time compared to the neural network (NN)-based baseline algorithms compared against with. Additionally, the Cy-Phy ADS has advantages such as unsupervised training, the ability to provide a holistic metric for system health characterization, and non-linear feature extraction.

Förderung

  • Department of Energy through the U.S. DOE Idaho Operations Office
  • Commonwealth Cyber Initiative, an Investment in the Advancement of Cyber Research and Development, Innovation and Workforce Development

Zitieren

APA

Mavikumbure, H. S., Cobilean, V., Wickramasinghe, C. S., Varghese, B. J., Carlson, R. B., Rieger, C., Pennington, T., & Manic, M. (2024). Cy-Phy ADS: Cyber-Physical Anomaly Detection Framework for EV Charging Systems. IEEE Transactions on Transportation Electrification, 10(4), 9904-9917. https://doi.org/10.1109/tte.2024.3363672

Vancouver

Mavikumbure HS, Cobilean V, Wickramasinghe CS, Varghese BJ, Carlson RB, Rieger C, et al. Cy-Phy ADS: Cyber-Physical Anomaly Detection Framework for EV Charging Systems. IEEE Transactions on Transportation Electrification. 2024;10(4):9904-9917. doi:10.1109/tte.2024.3363672

BibTeX
@article{Mavikumbure2024,
  author = {Mavikumbure, Harindra S. and Cobilean, Victor and Wickramasinghe, Chathurika S. and Varghese, Benny J. and Carlson, Richard B. and Rieger, Craig and Pennington, Timothy and Manic, Milos},
  title = {Cy-Phy ADS: Cyber-Physical Anomaly Detection Framework for EV Charging Systems},
  journal = {IEEE Transactions on Transportation Electrification},
  year = {2024},
  volume = {10},
  number = {4},
  pages = {9904--9917},
  doi = {10.1109/tte.2024.3363672}
}
Kostenlos starten →