THE PROBLEM OF STABILITY OF INFORMATION AND COMMUNICATION SYSTEMS IN CONDITIONS OF ENERGY FAILURES
DOI:
https://doi.org/10.32689/maup.it.2025.3.3Keywords:
information and communication networks, information and communication system resilience, power outages, blackouts, cybersecurity, proactive management, risk prediction, machine learning, critical infrastructureAbstract
Scientific novelty. The novelty lies in the development of a proactive risk forecasting system for ICN based on machine learning, which predicts potential blackouts, instead of a reactive response. An integral risk indicator, considering energy, meteorological and operational data, is a unique tool for automatically launching protective scenarios, which reduces dependence on the human factor and expensive equipment. This solution increases the physical and cyber security of networks, minimizing vulnerabilities to cascading failures, which is new compared to traditional approaches.Purpose. The purpose of the article is to analyze the threats to Information-Communication Networks (ICN) due to power outages and develop a proactive system to increase their resilience.Methodology. The study is based on the analysis of statistical data on the increase in the frequency of blackouts (64% more outages in the USA from 2011 to 2021 compared to the previous decade) and the assessment of their consequences, such as economic losses (over 400 million euros in the Iberian Peninsula) and data loss in volatile random access memory (RAM), leading to corruption of system files and cascading failures in cloud data centers. Traditional protection methods (UPS, generators) are assessed as insufficient due to high cost, operating costs, equipment degradation and dependence on the human factor.A proactive risk forecasting system is proposed that uses machine learning methods (ARIMA, LSTM) to analyze historical power grid data (voltage, frequency), meteorological factors, and power system operator data. The system calculates an integral risk indicator and automatically launches protective scenarios to minimize losses.Conclusions. The increase in the frequency and scale of blackouts requires a transition to proactive solutions. The proposed machine learning-based forecasting system provides a timely response to threats, minimizes damage to information, software and hardware components of ICN, increases cybersecurity and ensures continuity of work in conditions of energy failures.
References
Бойко В., Василенко М., Слатвінська В. Моделювання живучості та відновлення інформаційно-комунікаційних мереж в умовах дії кіберзагроз. Інформаційні технології та суспільство. 2024. № 1 (12). С. 13–19. URL: https://journals.maup.com.ua/index.php/it/article/view/3143.
A major Google Cloud outage was caused by uninterruptible power supplies being interrupted. URL: https://www.techradar.com/pro/a-major-google-cloud-outage-was-caused-by-uninterruptible-power-supplies-being-interrupted, 2023.
Aalto University. Machine learning helps to predict blackouts caused by storms. URL: https://www.aalto.fi/en/news/machine-learning-helps-to-predict-blackouts-caused-by-storms-0, 2019.
American Society of Civil Engineers (ASCE). 2021 Report Card for America’s Infrastructure: Energy. American Society of Civil Engineers; URL: https://infrastructurereportcard.org/cat-item/energy-infrastructure/, 2021.
Carreras B. A., Colet P., Reynolds-Barredo J. M., Gomila D. Assessing Blackout Risk With High Penetration of Variable Renewable Energies. IEEE Access. 2021. Vol. 9. P. 132663–132674.
Carreras B. A., Newman D. E., Dobson I. North American Blackout Time Series Statistics and Implications for Blackout Risk. IEEE Transactions on Power Systems. 2016. Vol. 31, No. 6. P. 4406–4414.
Central C. Surging Weather-Related Power Outages. URL: https://www.climatecentral.org/climate-matters/surging-weather-related-power-outages, 2021.
Connexion France. French mobile network operator SFR hit by major outage. URL: https://www.connexionfrance.com/news/french-mobile-network-operator-sfr-hit-by-major-outage/730194, 2023.
Data Center Dynamics. UPS issue caused Google Cloud’s March outage. URL: https://www.datacenterdynamics.com/en/news/ups-issue-caused-google-clouds-march-outage/, 2023.
Farooq U., Bass R. B. Frequency Event Detection and Mitigation in Power Systems: A Systematic Literature Review. IEEE Access. 2022. Vol. 10. P. 61494–61519.
Florin M.-G., Iosif M. R., Daniel F. N., Mihai S. A., Mihai P.-S., Alin C. E., Ioan S., Eugen S. G., Obretenova M. I. Assessment of Vulnerabilities and Risks That May Generate Energy Crises – Blackout. Preprints, 2025. URL: https://doi.org/10.20944/preprints202504.0815.v1.
Ghasemkhani B., Kut R. A., Yilmaz R., Birant D., Arıkök Y. A., Güzelyol T. E., Kut T. Machine Learning Model Development to Predict Power Outage Duration (POD): A Case Study for Electric Utilities. Sensors. 2024. Vol. 24, No. 13.
Google Cloud. Incident Report for us-east5-c outage on March 14, 2023: Incident Report N3Dw7nbJ7rk7qwrtwh7X. Google Cloud; URL: https://status.cloud.google.com/incidents/N3Dw7nbJ7rk7qwrtwh7X, 2023.
Google Cloud. Incident Report for us-east9-a on April 25, 2023: Incident Report dS9ps52MUnxQfyDGPfkY. Google Cloud; URL: https://status.cloud.google.com/incidents/dS9ps52MUnxQfyDGPfkY, 2023.
Hines P., Apt J., Talukdar S. Trends in the history of large blackouts in the United States. 2008. IEEE Power and Energy Society General Meeting – Conversion and Delivery of Electrical Energy in the 21st Century. 2008. Р. 1–8.
Onaolapo A. K., Carpanen R. P., Dorrell D. G., Ojo E. E. Event-Driven Power Outage Prediction using Collaborative Neural Networks. IEEE Transactions on Industrial Informatics. 2023. Vol. 19, no. 3. P. 3079–3087.
Powerquality.blog. UPS Problem at Datacenter. URL: https://powerquality.blog/2025/03/17/ ups-problem-at-datacenter/, 2025.
Ratnam E. L., Baldwin K. G. H., Mancarella P., Howden M., Seebeck L. Electricity system resilience in a world of increased climate change and cybersecurity risk. The Electricity Journal. 2020. Vol. 33, 9. 106833. URL: https://www.sciencedirect.com/science/article/pii/S1040619020301251.
Unipower. What Caused the Big Blackout in Spain and Portugal? URL: https://www.unipower.se/news/what-caused-the-big-blackout-in-spain-and-portugal/, 2025.
Wu Y.-K., Chang S. M., Hu Y.-L. Literature Review of Power System Blackouts. Energy Procedia. 2017. Vol. 141. P. 428–431. URL: https://www.sciencedirect.com/science/article/pii/S1876610217354619.
