2. Home
  3. ARCHIVE
  4. 2026
  5. VOL 48, NO 2 (2026)
  6. pp. 103-114

Intelligent Analytics for Enhancing the Resilience of Critical Infrastructure

I. Martyniuk, N. Zaika, M. Komarov, H. Martyniuk

Èlektron. model. 2026, 48(2):103-114

ABSTRACT

This paper addresses the enhancement of resilience of critical infrastructure objects (CIOs) through intelligent analytics and machine learning techniques. The core idea is based on the use of adaptive models for early incident detection and automated load forecasting. The integration of Mean Time to Detect (MTTD) and Mean Time to Recover (MTTR) metrics into a continuous improvement cycle significantly increases the effectiveness of monitoring and risk management, ensuring enhanced cyber resilience and adaptability of critical infrastructure under dynamic operating conditions.

Full text: PDF

KEYWORDS

artificial intelligence, machine learning, critical information infrastructure, resilience, monitoring.

REFERENCES

  1. Martyniuk I., Martyniuk H., Yevchenko Y. (2025). Improving the method of monitoring the state of the website by detecting user interface vulnerabilities and browser errors. CEUR Workshop Proceedings. Vol. 4024. Pp. 157-162.
  2. Zimelewicz E., Biesialska M., Zhang X., Bäck T., Briand L. (2020). Machine learning-enabled systems: model deployment and monitoring challenges. Proceedings of the 42nd International Conference on Software Engineering. Seoul, Republic of Korea. Pp. 38-49. DOI: 10.1145/3377811.3380394.
  3. Ruff L., Kauffmann J., Vandermeulen R. et al. (2022). A unifying review of deep and classical anomaly detection. Proceedings of the IEEE. 110(5). Pp. 756-782. DOI: 10.1109/ JPROC.2022.3158238.
  4. Martyniuk I.V., Okhrimenko T.O. (2025). Methodology and classification of open-source ML methods for IT monitoring based on the Zabbix system. Ukrainian Scientific Journal of Information Security. 31(2). Pp. 87-92.
  5. Narayan A., Kumar R., Singh A. (2021).AI-driven anomaly detection in Nagios and Zabbix logs. International Journal of Computer Applications. 174(27). Pp. 15-22. URL: https://www.ijcaonline.org/archives/volume174/number27/ (date of access: 22.12.2025).
  6. Misnik O. Application container security model. (2020). Information Technology and Security. 8(1). Pp. 58-66. DOI: 10.20535/2411-1031.2020.8.1.218004.
  7. Monitor anything — networks, cloud, websites, IoT, and more. URL: https://www.zabbix.com/ (date of access: 15.12.2025).
  8. Nevolnichenko A. I., Chumachenko S. M., Mykhailova A. V., Pyrikov O. V., Murasov R. K. Modeling threats of emergency situations at critical infrastructure facilities using the system dynamics method. (2022). Tavria Scientific Bulletin. Series: Technical Sciences. 3, pp. 88-99.
  9. Bershchanskyi Y., Klym H., Shevchuk Y. Containerized artificial intelligence system design in cloud and cyber-physical systems. (2024). Advances in Cyber-Physical Systems. 9(2), pp. 151-157. DOI: 10.23939/acps2024.02.151.
  10. Bershchanskyi Y., Stepanov O. Machine learning model development in Kubeflow cloud-native systems. (2025). Advances in Cyber-Physical Systems. 10(1), pp. 83-88. DOI: 10.23939/acps2025.01.083.
  11. Semerikov S. O., Zubov D., Kupin A., Kosei M., Holiver V. Models and technologies for autoscaling based on machine learning for microservices architecture. (2024). Proceedings of the 8th International Conference on Computational Linguistics and Intelligent Systems. Lviv. Pp. 316-330.