Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI

Hydroelectric power plants (HEPPs) are vital components of the renewable energy infrastructure, making their operational security and efficiency critical. HEPPs face increasing vulnerability to cyber threats, which can disrupt operations and compromise energy production. This study investigates the...

Full description

Saved in:
Bibliographic Details
Main Authors: Ismail Erkek, Erdal Irmak
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10909089/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770710479667200
author Ismail Erkek
Erdal Irmak
author_facet Ismail Erkek
Erdal Irmak
author_sort Ismail Erkek
collection DOAJ
description Hydroelectric power plants (HEPPs) are vital components of the renewable energy infrastructure, making their operational security and efficiency critical. HEPPs face increasing vulnerability to cyber threats, which can disrupt operations and compromise energy production. This study investigates the integration of Digital Twin (DT) technology with Explainable Artificial Intelligence (XAI) to improve cybersecurity and anomaly detection in a HEPP located in Türkiye. The DT model simulates key operational parameters, such as water flow, mechanical power, and turbine speed, enabling real-time monitoring, optimization, and secure cybersecurity testing. Simulated cyberattacks on the DT have revealed vulnerabilities in the Modbus protocol, while SHapley Additive exPlanations (SHAP) analysis, an XAI technique, clarifies the influence of operational parameters on anomaly detection outcomes. Gravity with a SHAP value of 0.0001 and water density with a SHAP value of 0.0018 have been identified as the least influential parameters, suggesting limited variability or impact on the detected anomalies. These findings enable the prioritization of critical variables while reducing unnecessary monitoring efforts. The proposed integration improves the accuracy of anomaly detection, enables precise vulnerability identification, and mitigates operational risks without impacting real-world systems. The results demonstrate the effectiveness of the model in detecting anomalies and strengthening the resilience of the system against cyber threats. This approach also provides actionable insights to optimize operational processes, ensuring secure and efficient energy production. The study highlights the transformative potential of DT-XAI integration in advancing the sustainability, security, and resilience of critical energy infrastructures.
format Article
id doaj-art-818262d3b1b6490f92c75dc1a06dc58e
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-818262d3b1b6490f92c75dc1a06dc58e2025-08-20T03:02:55ZengIEEEIEEE Access2169-35362025-01-0113418874190810.1109/ACCESS.2025.354767210909089Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AIIsmail Erkek0https://orcid.org/0000-0003-0703-5970Erdal Irmak1https://orcid.org/0000-0002-4712-6861Department of Information Security Engineering, Graduate School of Natural and Applied Sciences, Gazi University, Ankara, TürkiyeDepartment of Electrical and Electronics Engineering, Faculty of Technology, Gazi University, Ankara, TürkiyeHydroelectric power plants (HEPPs) are vital components of the renewable energy infrastructure, making their operational security and efficiency critical. HEPPs face increasing vulnerability to cyber threats, which can disrupt operations and compromise energy production. This study investigates the integration of Digital Twin (DT) technology with Explainable Artificial Intelligence (XAI) to improve cybersecurity and anomaly detection in a HEPP located in Türkiye. The DT model simulates key operational parameters, such as water flow, mechanical power, and turbine speed, enabling real-time monitoring, optimization, and secure cybersecurity testing. Simulated cyberattacks on the DT have revealed vulnerabilities in the Modbus protocol, while SHapley Additive exPlanations (SHAP) analysis, an XAI technique, clarifies the influence of operational parameters on anomaly detection outcomes. Gravity with a SHAP value of 0.0001 and water density with a SHAP value of 0.0018 have been identified as the least influential parameters, suggesting limited variability or impact on the detected anomalies. These findings enable the prioritization of critical variables while reducing unnecessary monitoring efforts. The proposed integration improves the accuracy of anomaly detection, enables precise vulnerability identification, and mitigates operational risks without impacting real-world systems. The results demonstrate the effectiveness of the model in detecting anomalies and strengthening the resilience of the system against cyber threats. This approach also provides actionable insights to optimize operational processes, ensuring secure and efficient energy production. The study highlights the transformative potential of DT-XAI integration in advancing the sustainability, security, and resilience of critical energy infrastructures.https://ieeexplore.ieee.org/document/10909089/Cyber securitydigital twinsexplainable artificial intelligencehydroelectric power plant
spellingShingle Ismail Erkek
Erdal Irmak
Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI
IEEE Access
Cyber security
digital twins
explainable artificial intelligence
hydroelectric power plant
title Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI
title_full Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI
title_fullStr Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI
title_full_unstemmed Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI
title_short Enhancing Cybersecurity of a Hydroelectric Power Plant Through Digital Twin Modeling and Explainable AI
title_sort enhancing cybersecurity of a hydroelectric power plant through digital twin modeling and explainable ai
topic Cyber security
digital twins
explainable artificial intelligence
hydroelectric power plant
url https://ieeexplore.ieee.org/document/10909089/
work_keys_str_mv AT ismailerkek enhancingcybersecurityofahydroelectricpowerplantthroughdigitaltwinmodelingandexplainableai
AT erdalirmak enhancingcybersecurityofahydroelectricpowerplantthroughdigitaltwinmodelingandexplainableai