EconPapers    
Economics at your fingertips  
 

Evolution of Artificial Intelligence-Based OT Cybersecurity Models in Energy Infrastructures: Services, Technical Means, Facilities and Algorithms

Hipolito M. Rodriguez-Casavilca, David Mauricio and Juan M. Mauricio Villanueva ()
Additional contact information
Hipolito M. Rodriguez-Casavilca: Faculty of Systems and Informatics Engineering, Universidad Nacional Mayor de San Marcos, Lima 15081, Peru
David Mauricio: Faculty of Systems and Informatics Engineering, Universidad Nacional Mayor de San Marcos, Lima 15081, Peru
Juan M. Mauricio Villanueva: Electrical Engineering Department, Federal University of Paraíba, Joao Pessoa 58051-900, Brazil

Energies, 2025, vol. 18, issue 19, 1-32

Abstract: Critical energy infrastructures (CEIs) are fundamental pillars for economic and social development. However, their accelerated digitalization and the convergence between operational technologies (OTs) and information technologies (ITs) have increased their exposure to advanced cyber threats. This study examines the evolution of OT cybersecurity models with artificial intelligence in the energy sector between 2015 and 2024, through a systematic literature review following a four-phase method (planning, development, results, and analysis). To this end, we answer the following questions about the aspects of CEI cybersecurity models: What models exist? What energy services, technical means, and facilities do they encompass? And what algorithms do they include? From an initial set of 1195 articles, 52 studies were selected, which allowed us to identify 49 cybersecurity models classified into seven functional categories: detection, prediction and explanation; risk management; regulatory compliance; collaboration; response and recovery; architecture-based protection; and simulation. These models are related to 10 energy services, 6 technical means, 10 types of critical facilities, and 15 AI algorithms applied transversally. Furthermore, the integrated and systemic relationship of these study aspects has been identified in an IT-OT cybersecurity model for CEIs. The results show a transition from conventional approaches to solutions based on machine learning, deep learning, federated learning, and blockchain. Algorithms such as CNN, RNN, DRL, XAI, and FL are highlighted, which enhance proactive detection and operational resilience. A broader coverage is also observed, ranging from power plants to smart grids. Finally, five key challenges are identified: legacy OT environments, lack of interoperability, advanced threats, emerging IIoT and quantum computing risks, and low adoption of emerging technologies.

Keywords: cybersecurity; critical energy infrastructures; OT models; artificial intelligence; machine learning; operational resilience; technological evolution (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/19/5163/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/19/5163/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:19:p:5163-:d:1760308

Access Statistics for this article

Energies is currently edited by Ms. Cassie Shen

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().

 
Page updated 2025-09-29
Handle: RePEc:gam:jeners:v:18:y:2025:i:19:p:5163-:d:1760308