TY - GEN
T1 - Physical Anomaly Detection in EV Charging Stations
T2 - 32nd IEEE International Symposium on Industrial Electronics, ISIE 2023
AU - Mavikumbure, Harindra S.
AU - Cobilean, Victor
AU - Wickramasinghe, Chathurika S.
AU - Phillips, Tyler
AU - Varghese, Benny J.
AU - Carlson, Barney
AU - Rieger, Craig
AU - Pennington, Timothy
AU - Manic, Milos
N1 - Funding Information:
The objective of this paper is to develop a physical anomaly detection approach without using labeled data to improve the resiliency of electric vehicle charging stations. First, we explored a physics-based system identification model for the anomaly detection task. However, we demonstrate that there are limitations to this approach. Specifically, with attacks that alter the system but result in input and output data that follow the physics of the system. Therefore, we explored ResNet AE-based approach for unsupervised physical anomaly detection and our outcomes show that the ResNet AE approach has improved detection performance. More precisely, we show that by using a ResNet AE it is possible to detect the attacks with a High Accuracy (96.82), Recall(1.00), Precision (92.43), and F1 score (96.07). In the future, we intend to improve our anomaly detection system by incorporating cybersecurity-related scenarios of EV charging systems. ACKNOWLEDGMENT This work was supported in part by the Department of Energy through the U.S. DOE Idaho Operations Office under Contract DE-AC07-05ID14517, and in part by the Commonwealth Cyber Initiative, an Investment in the Advancement of Cyber Research and Development, Innovation and Workforce Development (cyberinitiative.org).
Publisher Copyright:
© 2023 IEEE.
PY - 2023/8/31
Y1 - 2023/8/31
N2 - The number of electric car users has grown in recent years, increasing the demand for reliable electric vehicle charging stations (EVCS). The safety of EVCSs is very important as compromised charging stations can disrupt the grid, injure the end-users, and damage the vehicle. In this paper, we will focus on the physical security of EVCS, because physical attacks tend to be more harmful to the end user. Two anomaly detection approaches were presented for detecting physical anomalies: physics-based anomaly detection and deep learning-based anomaly detection (ResNet Autoencoder). The presented approaches were trained and tested using data collected from the EV Charging Station System testbed of the Idaho National Laboratory. Anomaly detection performance was evaluated on three different attack scenarios, targeting various parts of the system including power transfer subsystems and the cooling subsystem of the charger. The presented approaches were compared against two widely used unsupervised anomaly detection algorithms: OCSVM and LOF. Moreover, we evaluated the advantages and limitations of the physics-based vs ResNet Autoencoder approaches for each of the three attack scenarios. The ResNet Autoencoder approach showed the highest performance in terms of accuracy, F1, recall, and precision. Furthermore, this approach demonstrated a number of advantages including automated non-linear feature extraction and unsupervised learning.
AB - The number of electric car users has grown in recent years, increasing the demand for reliable electric vehicle charging stations (EVCS). The safety of EVCSs is very important as compromised charging stations can disrupt the grid, injure the end-users, and damage the vehicle. In this paper, we will focus on the physical security of EVCS, because physical attacks tend to be more harmful to the end user. Two anomaly detection approaches were presented for detecting physical anomalies: physics-based anomaly detection and deep learning-based anomaly detection (ResNet Autoencoder). The presented approaches were trained and tested using data collected from the EV Charging Station System testbed of the Idaho National Laboratory. Anomaly detection performance was evaluated on three different attack scenarios, targeting various parts of the system including power transfer subsystems and the cooling subsystem of the charger. The presented approaches were compared against two widely used unsupervised anomaly detection algorithms: OCSVM and LOF. Moreover, we evaluated the advantages and limitations of the physics-based vs ResNet Autoencoder approaches for each of the three attack scenarios. The ResNet Autoencoder approach showed the highest performance in terms of accuracy, F1, recall, and precision. Furthermore, this approach demonstrated a number of advantages including automated non-linear feature extraction and unsupervised learning.
KW - Anomaly Detection
KW - Autoencoders
KW - Deep Neural Networks
KW - Electric Vehicle Charging Systems
KW - Physics-based models
KW - Unsupervised Learning
UR - https://www.scopus.com/pages/publications/85172150618
UR - https://www.mendeley.com/catalogue/3ade0141-4d0b-3b3a-8b42-3d8700c5939e/
U2 - 10.1109/ISIE51358.2023.10228104
DO - 10.1109/ISIE51358.2023.10228104
M3 - Conference contribution
AN - SCOPUS:85172150618
SN - 9798350399714
T3 - 2023 IEEE 32nd International Symposium on Industrial Electronics (ISIE)
SP - 1
EP - 7
BT - 2023 IEEE 32nd International Symposium on Industrial Electronics, ISIE 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 June 2023 through 21 June 2023
ER -