2. Home
  3. ARCHIVE
  4. 2025
  5. VOL 47, NO 6 (2025)
  6. pp. 58-68

APPLICATION OF MACHINE LEARNING METHODS IN PREDICTING FACTORS INDICATING POTENTIAL CLUSTER PARTITIONING

D.P. Sinko, K.D. Sinko

Èlektron. model. 2025, 47(6):58-68

https://doi.org/10.15407/emodel.47.06.058

ABSTRACT

It is considered how to use Python in the author's approach, which was suggested in the work. [1]. The results of numerical modeling showed that the Random Forest and CatBoost methods did the best job of predicting factors of point to potential cluster partitioning. Based on the modeling results, conclusions were made that allow architects of complex cluster cybernetic systems to use the proposed approach as a working tool to prevent critical system conditions associated with network partitioning.

KEYWORDS

split brain problem, cluster splitting problem (CSP), partitioning, ML algorithms, cluster.

REFERENCES

  1. Sinko, D.P. & Sinko, K.D. (2025). Analysis of the applicability of machine learning methods in solving the problem of predicting the implementation of cluster batching factors. Electron. modeling, 47(1), 22-39. https://doi.org/10.15407/emodel.47.01.022 [Accessed:19.05.2025].
  2. Bhuiyan, S., & Zheludkov, M. (2019). Apache ignite book. Lulu Press, Inc [Accessed: 04.01.2025].
  3. Twu, P., Egerstedt, M., & Martini, S. (2010). Controllability of homogeneous single-leader networks. У 49th IEEE conference on decision and control (CDC) (с. 5869-5874). https://doi.org/10.1109/CDC.2010.5718103 [Accessed: 20.04.2025].
  4. Zhao, M., Lin, T., Mi, F., Jaggi, M., & Schütze, H. (2020). Masking as an efficient alternative to finetuning for pretrained language models. ArXiv. https://doi.org/10.48550/arXiv.2004.12406 [Accessed: 02.05.2025].
  5. Barabash, O.V. (2024). Comparative analysis of the approximation of a probabilistic indicator of functional stability using Bernstein polynomials and feedforward neural networks. Connectivity, 169(3). https://doi.org/10.31673/2412-9070.2024.033237 [Accessed: 06.06.2025].
  6. Sahai, T., Speranzon, A., & Banaszuk, A. (2009). Hearing the clusters in a graph: A distributed algorithm. URL: https://doi.org/10.48550/arXiv.0911.4729 [Accessed: 25.04.2025].
  7. Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324 [Accessed: 09.01.2025].
  8. He, Z., Lin, D., Lau, T., & Wu, M. (2019). Gradient Boosting Machine: A Survey. arXiv. https://doi.org/10.48550/arXiv.1908.06951 [Accessed: 11.02.2025].
  9. Hancock, J.T., & Khoshgoftaar, T.M. (2020). CatBoost for big data: An interdisciplinary review. Journal of Big Data, 7, 94. https://doi.org/10.1186/s40537-020-00369-8 [Дата звернення: 03.02.2025].
  10. PSnik-Kostiantyn. (2025). SplitBrainDetector. https://github.com/PSnik-Kostiantyn/SplitBrainDetector [Accessed: 20.06.2025].

Full text: PDF