Abstract
In recent years, the deployment of charging infrastructures has been increasing exponentially due to the high energy demand of electric vehicles, forming complex charging networks. These networks pave the way for the emergence of new unknown threats in both the energy and transportation sectors. Economic damages and energy theft are the most frequent risks in these environments. Thus, this paper aims to present a solution capable of accurately detecting unforeseen events and possible fraud threats that arise during charging sessions at charging stations through the current capabilities of the Machine Learning (ML) algorithms. However, these algorithms have the drawback of not fitting well in large networks and generating a high number of false positives and negatives, mainly due to the mismatch with the distribution of data over time. For that reason, a Collaborative Anomaly Detection System for Charging Stations (here referred to as CADS4CS) is proposed as an optimization measure. CADS4CS has a central analysis unit that coordinates a group of independent anomaly detection systems to provide greater accuracy using a voting algorithm. In addition, CADS4CS has the feature of continuously retraining ML models in a collaborative manner to ensure that they are adjusted to the distribution of the data. To validate the approach, different use cases and practical studies are addressed to demonstrate the effectiveness and efficiency of the solution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abdar, M., Yen, N.Y., Hung, J.C.S.: Improving the diagnosis of liver disease using multilayer perceptron neural network and boosted decision trees. J. Med. Biol. Eng. 38(6), 953–965 (2018)
Alcaraz, C., Cazorla, L., Fernandez, G.: Context-awareness using anomaly-based detectors for smart grid domains. In: Lopez, J., Ray, I., Crispo, B. (eds.) CRiSIS 2014. LNCS, vol. 8924, pp. 17–34. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-17127-2_2
Alcaraz, C., Lopez, J., Wolthusen, S.: OCPP protocol: security threats and challenges. IEEE Trans. Smart Grid 8(5), 2452–2459 (2017)
Open Charge Alliance: OCPP 2.0.1 (2020). https://www.openchargealliance.org/protocols/ocpp-201/. Accessed 24 May 2022
Antoun, J., Kabir, M.E., Moussa, B., Atallah, R., Assi, C.: A detailed security assessment of the EV charging ecosystem. IEEE Netw. 34(3), 200–207 (2020)
Basnet, M., Ali, M.H.: Deep learning-based intrusion detection system for electric vehicle charging station. In: 2nd International Conference on Smart Power and Internet Energy Systems, SPIES, pp. 408–413 (2020)
Bhusal, N., Gautam, M., Benidris, M.: Cybersecurity of electric vehicle smart charging management systems. In: 52nd North American Power Symposium, NAPS (2020)
Brighente, A., Conti, M., Donadel, D., Turrin, F.: EVScout2. 0: electric vehicle profiling through charging profile. arXiv preprint arXiv:2106.16016 (2021)
Bristow, M.: A SANS survey: OT/ICS cybersecurity, pp. 1–23 (2021). www.cisa.gov/critical-infrastructure-sectors
Cazorla, L., Alcaraz, C., Lopez, J.: Cyber stealth attacks in critical information infrastructures. IEEE Syst. J. 12, 1778–1792 (2018)
Chahla, C., Snoussi, H., Merghem, L., Esseghir, M.: A deep learning approach for anomaly detection and prediction in power consumption data. Energ. Effi. 13(8), 1633–1651 (2020). https://doi.org/10.1007/s12053-020-09884-2
Chung, Y.W., et al.: The framework of invariant electric vehicle charging network for anomaly detection. In: IEEE Transportation Electrification Conference and Expo, ITEC, pp. 631–636 (2020)
Deloitte: Electric vehicle trends | Deloitte Insights. https://www2.deloitte.com/us/en/insights/focus/future-of-mobility/electric-vehicle-trends-2030.html. Accessed 18 May 2022
Drive Dundee Electric: Electric Vehicle Charging Sessions Dundee - Datasets (2019). https://data.dundeecity.gov.uk/dataset/ev-charging-data. Accessed 08 May 2022
ENISA: ENISA Threat Landscape 2021 (2021). https://doi.org/10.2824/324797, https://www.enisa.europa.eu/news/enisa-news/enisa-threat-landscape-2021
Gottumukkala, R., Merchant, R., Tauzin, A., Leon, K., Roche, A., Darby, P.: Cyber-physical system security of vehicle charging stations. In: IEEE Green Technologies Conference (2019)
Hollingsworth, K., et al.: Energy anomaly detection with forecasting and deep learning. In: Proceedings of the IEEE International Conference on Big Data, Big Data, pp. 4921–4925 (2018)
Janetzko, H., Stoffel, F., Mittelstädt, S., Keim, D.A.: Anomaly detection for visual analytics of power consumption data. Comput. Graph. (Pergamon) 38(1), 27–37 (2014)
Khan, O.G.M., El-Saadany, E., Youssef, A., Shaaban, M.: Impact of electric vehicles botnets on the power grid. In: IEEE Electrical Power and Energy Conference, pp. 1–5. IEEE (2019)
Amara Korba, A., Tamani, N., Ghamri-Doudane, Y., karabadji, N.E.I.: Anomaly-based framework for detecting power overloading cyberattacks in smart grid AMI. Comput. Secur. 96, 101896 (2020)
Köhler, S., Baker, R., Strohmeier, M., Martinovic, I.: BROKENWIRE: wireless disruption of CCS electric vehicle charging (2022). https://www.brokenwire.fail/. Accessed 25 May 2022
Li, W., Meng, W., Kwok, L.F.: Surveying trust-based collaborative intrusion detection: state-of-the-art, challenges and future directions. IEEE Commun. Surv. Tut. 24(1), 280–305 (2021)
Li, Y., Ji, X., Jiang, D., Meng, T.: Abnormal detection system design of charging pile based on machine learning. IOP Conf. Ser. Earth Environ. Sci. 772(1), 012058 (2021)
Li, Y., Zhang, L., Lv, Z., Wang, W.: Detecting anomalies in intelligent vehicle charging and station power supply systems with multi-head attention models. IEEE Trans. Intell. Transp. Syst. 22(1), 555–564 (2021)
Lightman, S., Brewer, T.: Symposium on Federally Funded Research on Cybersecurity of Electric Vehicle Supply Equipment (EVSE) (2020). https://doi.org/10.6028/NIST.IR.8294
Mishra, M.K., Dash, R.: A comparative study of chebyshev functional link artificial neural network, multi-layer perceptron and decision tree for credit card fraud detection. In: 2014 International Conference on Information Technology, pp. 228–233 (2014)
Mokhtari, S., Abbaspour, A., Yen, K.K., Sargolzaei, A.: A machine learning approach for anomaly detection in industrial control systems based on measurement data. Electronics 10(4), 407 (2021)
Nejabatkhah, F., Li, Y.W., Liang, H., Reza Ahrabi, R.: Cyber-security of smart microgrids: a survey. Energies 14(1), 27 (2020)
ElaadNL: Data delen @ Elaad NL (2021), https://platform.elaad.io/download-data/. Accessed 08 May 2022
Open-Data Boulder Colorado: Electric Vehicle Charging Station Energy Consumption (2021). https://open-data.bouldercolorado.gov/datasets/183adc24880b41c4be9fd6a14eb6165f_0/explore. Accessed 08 May 2022
Ouyang, Z., Sun, X., Chen, J., Yue, D., Zhang, T.: Multi-view stacking ensemble for power consumption anomaly detection in the context of industrial internet of things. IEEE Access 6, 9623–9631 (2018)
City of Palo Alto: Electric Vehicle Charging Station Usage (July 2011–Dec 2020) \(\cdot \) Open Data \(\cdot \) City of Palo Alto (2021). https://data.cityofpaloalto.org/dataviews/257812/electric-vehicle-charging-station-usage-july-2011-dec-2020/. Accessed 08 May 2022
Perth & Kinross Council: Electric Vehicle Charging Station Usage - Datasets - Perth and Kinross - Open Data (2021). https://data.pkc.gov.uk/dataset/ev-charging-data. Accessed 08 May 2022
Pourmirza, Z., Walker, S.: Electric vehicle charging station: cyber security challenges and perspective. In: 9th IEEE International Conference on Smart Energy Grid Engineering, SEGE, pp. 111–116 (2021)
Robles-Durazno, A., Moradpoor, N., McWhinnie, J., Russell, G.: A supervised energy monitoring-based machine learning approach for anomaly detection in a clean water supply system. In: International Conference on Cyber Security and Protection of Digital Services, Cyber Security, pp. 1–8 (2018)
Rubio, J.E., Alcaraz, C., Lopez, J.: Addressing security in OCPP: protection against man-in-the-middle attacks. In: 9th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2018 - Proceedings, pp. 1–5 (2018)
Rubio, J.E., Manulis, M., Alcaraz, C., Lopez, J.: Enhancing security and dependability of industrial networks with opinion dynamics. In: Sako, K., Schneider, S., Ryan, P.Y.A. (eds.) ESORICS 2019. LNCS, vol. 11736, pp. 263–280. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29962-0_13
Panda Security: Electric vehicle charging stations are vulnerable to hacker attacks (2022). https://www.pandasecurity.com/en/mediacenter/security/ev-charging-stations/. Accepted 03 May 2022
Streubel, T., Kattmann, C., Eisenmann, A., Rudion, K.: Detection and monitoring of supraharmonic anomalies of an electric vehicle charging station. In: IEEE Milan PowerTech, PowerTech, pp. 1–5 (2019)
Vasilomanolakis, E., Karuppayah, S., Muhlhauser, M., Fischer, M.: Taxonomy and survey of collaborative intrusion detection. ACM Comput. Surv. 47(4), 1–33 (2015)
XGBoost: XGBoost Documentation - xgboost 1.6.0 documentation. https://xgboost.readthedocs.io/en/stable/. Accessed 22 May 2022
Yandex: CatBoost - open-source gradient boosting library. https://catboost.ai/. Accessed 22 May 2022
Zhang, W., Yang, Q., Geng, Y.: A survey of anomaly detection methods in networks. In: Proceedings of the 1st International Symposium on Computer Network and Multimedia Technology, CNMT, pp. 10–12 (2009)
Zhou, C.V., Leckie, C., Karunasekera, S.: A survey of coordinated attacks and collaborative intrusion detection. Comput. Secur. 29(1), 124–140 (2010)
Acknowledgements
This work has been supported by the “Smart and Secure EV Urban Lab II” through the Second Own Plan of Smart-Campus of the University of Malaga, by the EC under the SealedGRID project (H2020-MSCA-RISE-2017) with GA no. 777996, by the Ministry of Science and Innovation under SECUREDGE project (PID2019-110565RB-I00 − AEI/10.13039/501100011033/), and by the Andalusian Government under the SAVE project (P18-TP-3724).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Design and threats of a public charging infrastructure
A Design and threats of a public charging infrastructure
Deployment diagram of a public charging infrastructure
This appendix provides an overview of the components that compose a charging infrastructure and clarifies the level of susceptibility of these infrastructures to attacks according to the state of the art. Public CSs are usually managed by a CSMS, which has the ability to use ITs and OTs to efficiently control each CS and its charging sessions initialized by the users. Specifically, this control center is in charge of authenticating, authorizing and billing users, and diagnosing. Figure 10 shows a generic public charging infrastructure based on the Open Charge Point Protocol (OCPP) standard [4].
The combination of ITs and OTs in these cyber-physical systems leads to new security risks that must be considered right from the design stage. Above all, the addition of new functionalities, communications and external actors in the charging infrastructures open the door to new threats to the system. For this reason, we include in this appendix a high-level review of the state of the art [7, 16, 28] to show the susceptibility of this infrastructure to attacks and their impact on the end user and the power grid. Among the most common threats are: (T1) natural disasters, (T2) physical damage, (T3) DoS, (T4) identity theft or spoofing, (T5) malware injection, (T6) false data injection, (T7) tampering and (T8) sniffing or information disclosure.
Table 5 shows a summary of these threats with their corresponding environmental, social and economic impacts. As can be seen in the table, blackouts, economic damages and energy theft correspond to the impacts with the greatest likelihood and risk in a public charging infrastructure. This work therefore aims to mitigate these impacts through the use of Machine Learning techniques for anomaly detection. Its scope has been limited to the detection of threats related to T6 and T7, and focuses on studying the normal behavior of energy consumption data.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cumplido, J., Alcaraz, C., Lopez, J. (2022). Collaborative Anomaly Detection System for Charging Stations. In: Atluri, V., Di Pietro, R., Jensen, C.D., Meng, W. (eds) Computer Security – ESORICS 2022. ESORICS 2022. Lecture Notes in Computer Science, vol 13555. Springer, Cham. https://doi.org/10.1007/978-3-031-17146-8_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-17146-8_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17145-1
Online ISBN: 978-3-031-17146-8
eBook Packages: Computer ScienceComputer Science (R0)