ANALYSIS AND COMPARISON OF CASCADE EFFECT SCENARIOS IN CRITICAL INFRASTRUCTURE
DOI:
https://doi.org/10.32689/maup.it.2025.3.24Keywords:
critical infrastructure, machine learning, neural network, similarity coefficient, graphs, cascading effect, event modelingAbstract
The study of cascading effects scenarios in critical infrastructure plays an important role in decision-making to reduce negative consequences. Data on the operation of critical infrastructure is closed or limited, which complicates the process of analyzing cascading effects. Various approaches are used to generate and analyze cascading effects scenarios: graphmodels, power flow models, hybrid approaches that are used in accordance with the tasks. The development of machine learningis accompanied by the emergence of new promising approaches used to study the properties of power grids in various scenarios. The aim of the article is to investigate cascading effects in critical infrastructure and to create a method for analyzing andcomparing cascading effects scenarios in the power grid using a graph neural network and similarity coefficient.Methodology. The article describes the process of generating data in power grid scenarios when deriving system components that can potentially lead to a cascade effect. An autoencoder model based on a graph neural network is developed, which is used to form a representation of the scenario step (power grid state). The cosine of similarity is used to compare steps in different scenarios and search for similar network states. Based on the similarity of scenarios about power grid states, it is possible to draw conclusions about the possible development of a cascade effect in the scenario.The scientific novelty of the work lies in the development of a method that improves the process of analyzing cascading effects scenarios, comparing sequences of events in scenarios, and identifying similar situations for decision-making based onexisting experience. Possibilities for expanding the method are identified, using a combination of a graph neural network andLSTM to form a complex representation of the sequence of steps in scenarios.Conclusions. A study of approaches to the analysis of cascading effects in power grids was conducted. Based on theconducted study, promising directions were identified that could potentially improve the process of comparing cascading effectscenarios. To analyze and compare cascading effect scenarios in critical infrastructure (power grid), a method was developed that uses an autoencoder model containing a developed graph neural network layer, which improves the accuracy of themodel when studying connections, the influence of component parameters in the power grid, and forms a representation of thepower grid state in the scenario step. The cosine of similarity was used to search for similar scenarios that could potentially supplement information about the power grid state in subsequent steps of the scenario. The developed method can work with different levels of scenario detail, which ensures its adaptability to input data.
References
Косинус подібності. URL: https://uk.wikipedia.org/wiki/Косинус_подібності
Робота енергосистеми України станом на 20 травня 2022 року. URL: https://www.kmu.gov.ua/news/robota-energosistemi-ukrayini-stanom-na-20-travnya-2022-roku
Робота енергосистеми України на 1 червня 2022 року. URL: https://www.kmu.gov.ua/news/robota-energosistemi-ukrayini-na-1-chervnya-2022-roku
Робота енергосистеми України на 10 червня 2022 року. URL: https://mspu.gov.ua/news/robota-energosistemi-ukrayini-na-10-chervnya-2022-roku
Сенченко В. Р., Бойченко А. В., Коваль О. В., Бисько Р. М., Хоменко О. М. Огляд методів і технологій сценарного аналізу каскадних ефектів. Реєстрація, зберігання і обробка даних, 2024. Том 26. № 1. С. 24–54. DOI 10.35681/1560-9189.2024.26.2.316908
Сенченко В. Р., Бойченко А. В., Коваль О. В., Хоменко О. М. Методологія і архітектура платформи моделювання взаємозалежностей у критичних інфраструктурах при виникненні каскадних ефектів. Реєстрація, зберігання і обробка даних, ІПРІ НАН України, 2025. Том 27. № 1. С. 28–41. DOI: 10.35681/1560-9189.2025.27.1.335624
Хоменко О. М., Сенченко В. Р., Коваль О. В. Мережевий підхід при дослідженні каскадних ефектів критичних інфраструктур. Реєстрація, зберігання і обробка даних, 2024. Том 26. № 2. С. 44–72. DOI 10.35681/1560-9189.2024.26.2.316908
Chadaga S., Wu X., Modiano E. Power Failure Cascade Prediction using Graph Neural Networks. https://doi.org/10.48550/arXiv.2404.16134
Cuadra L, Salcedo-Sanz S, Del Ser J, Jiménez-Fernández S, Geem ZW. A Critical Review of Robustness in Power Grids Using Complex Networks Concepts. Energies. 2015. 8(9), 9211–9265. https://doi.org/10.3390/en8099211
Di Nardo A, Giudicianni C, Greco R, Herrera M, Santonastaso GF. Applications of Graph Spectral Techniques to Water Distribution Network Management. Water. 2018. 10(1), 45. https://doi.org/10.3390/w10010045
Dubey S. R., Singh S. K., Chaudhuri B. B. Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark. https://doi.org/10.48550/arXiv.2109.14545
Ellens W., Kooij R. E., Graph measures and network robustness. https://doi.org/10.48550/arXiv.1311.5064
Gilmer J., Schoenholz S. S., Riley P. F., Vinyals O., Dahl G. E. Neural Message Passing for Quantum Chemistry. https://doi.org/10.48550/arXiv.1704.01212
Guo Z., Sun K., Su X., Simunovic S., “A review on simulation models of cascading failures in power systems,” in iEnergy, vol. 2, no. 4, pp. 284–296, December 2023, doi: 10.23919/IEN.2023.0039
Hines P., Cotilla-Sanchez E., Blumsack S., Do topological models provide good information about electricity infrastructure vulnerability? https://doi.org/10.48550/arXiv.1002.2268
Korkali M., Veneman J. G., Tivnan B. F., Hines P. D. H. Reducing Cascading Failure Risk by Increasing Infrastructure Network Interdependency. https://doi.org/10.48550/arXiv.1410.6836
Mattsson L.-G., Jenelius E. Vulnerability and resilience of transport systems a discussion of recent research. Transportation Research Part A: Policy and Practice, vol. 81, pp. 16–34, 2015. https://doi.org/10.1016/j.tra.2015.06.002
Naeem Md Sami, Mia Naeini. Machine Learning Applications in Cascading Failure Analysis in Power Systems: A Review. https://doi.org/10.48550/arXiv.2305.19390
Noebels M., Preece R., Panteli M., “AC Cascading Failure Model for Resilience Analysis in Power Networks,” in IEEE Systems Journal, vol. 16, no. 1, pp. 374–385, March 2022, doi: 10.1109/JSYST.2020.3037400
Northeast blackout of 2003. URL: https://en.wikipedia.org/wiki/Northeast_blackout_of_2003
Oehlers M, Fabian B. Graph Metrics for Network Robustness—A Survey. Mathematics. 2021. 9(8), 895. https://doi.org/10.3390/math9080895
Rinaldi S. M., Peerenboom J. P., Kelly T. K., “Identifying, understanding, and analyzing critical infrastructure interdependencies”, in IEEE Control Systems Magazine, vol. 21, no. 6, pp. 11–25, Dec. 2001, doi: 10.1109/37.969131
Rusch T. K., Bronstein M. M., Mishra S. A Survey on Oversmoothing in Graph Neural Networks. https://doi.org/10.48550/arXiv.2303.10993
Varbella A., Gjorgiev B., Sansavini G. Geometric deep learning for online prediction of cascading failures in power grids. Reliability Engineering & System Safety, Volume 237, 2023. https://doi.org/10.1016/j.ress.2023.109341
Waikhom L., Patgiri R. Graph Neural Networks: Methods, Applications, and Opportunities. https://doi.org/10.48550/arXiv.2108.10733
Wu Z., Pan S., Chen F., Long G., Zhang C., Yu P. S. A Comprehensive Survey on Graph Neural Networks. https://doi.org/10.48550/arXiv.1901.00596
2003 Italy blackout. URL: https://en.wikipedia.org/wiki/2003_Italy_blackout
2012 India blackouts. URL: https://en.wikipedia.org/wiki/2012_India_blackouts
2016 South Australian blackout. URL: https://en.wikipedia.org/wiki/2016_South_Australian_blackout
