Multi-model approach with vector search in operational management critical IT service
Keywords:
decision making, proactive control, external load uncertainty, neural network, multi-model system, model library, vector searchAbstract
In the work are investigated current problems related to the task of operational management of critical IT services. To improve the quality of management, a new method is proposed, extending the dynamic local approximation approach. It implements linking vector representations of load patterns with trainable neural network models, which allows promptly constructing a predictor for a new pattern based on vector search for semantically close models in the library. Original principles of designing a control system are outlined, which for adaptation to new, uncertainty-related load patterns uses approximation of data obtained in real-time mode. The results of experiments confirmed the effectiveness of the proposed approach and showed that when processing irregular and complex loads, hybrid proactive algorithms in a number of indicators are more effective than reactive ones.
References
- Straesser M, Grohmann J, von Kistowski J, Eismann S, Bauer A, Kounev S. Why is it not solved yet? Challenges for production-ready autoscaling. In: Association for Computing Machinery. ICPE’22. Proceedings of the 2022 ACM/SPEC International conference on performance engineering; 2022 April 9–13; Bejing, China. New York: Association for Computing Machinery; 2022. p. 105–115. DOI: 10.1145/3489525.3511680.
- Krasnoproshin V, Starovoitov A. Real-time management of critical IT service using a multi-model approach. In: Kamil Aida-zade, editor. 2025 6th International conference on problems of cybernetics and informatics (PCI); 2025 August 26–28; Baku, Azerbaijan. [S. l.]: Institute of Electrical and Electronics Engineers; 2025. p. 1–5. DOI: 10.1109/PCI66488.2025.11219764.
- Grassberger Р, Procaccia I. Measuring the strangeness of strange attractors. Physica D: Nonlinear Phenomena. 1983;9(1–2):189–208. DOI: 10.1016/0167-2789(83)90298-1.
- Aslanpour MS, Ghobaei-Arani M, Toosi AN. Auto-scaling web applications in clouds: a cost-aware approach. Journal of Network and Computer Applications. 2017;95:26–41. DOI: 10.1016/j.jnca.2017.07.012.
Downloads
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 Journal of the Belarusian State University. Mathematics and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors who are published in this journal agree to the following:
- The authors retain copyright on the work and provide the journal with the right of first publication of the work on condition of license Creative Commons Attribution-NonCommercial. 4.0 International (CC BY-NC 4.0).
- The authors retain the right to enter into certain contractual agreements relating to the non-exclusive distribution of the published version of the work (e.g. post it on the institutional repository, publication in the book), with the reference to its original publication in this journal.
- The authors have the right to post their work on the Internet (e.g. on the institutional store or personal website) prior to and during the review process, conducted by the journal, as this may lead to a productive discussion and a large number of references to this work. (See The Effect of Open Access.)
