INFORMATION TECHNOLOGIES FOR COMPUTER-AIDED DESIGN OF ENTERPRISE COMPUTING SYSTEMS: CURRENT STATE AND PROSPECTS
DOI:
https://doi.org/10.28925/2663-4023.2026.34.1390Keywords:
computer-aided design, enterprise computing systems, machine learning, architectural decisions, SHAP, AutoML, surrogate modeling, load testing, cybersecurity, fault tolerance, survivabilityAbstract
The paper investigates the current state and prospects for the development of information technologies for computer-aided design of computing systems for enterprise structures. The relevance of the study is determined by the increasing complexity of enterprise information systems, the widespread adoption of distributed and cloud architectures, and the need to simultaneously address requirements for performance, scalability, cybersecurity, fault tolerance, and survivability. An analytical review and comparative analysis of current approaches are conducted in three interrelated areas: the application of machine learning to support architectural decision-making and predict system characteristics; the integration of load testing into the iterative design cycle; and the provision of cybersecurity and fault tolerance in distributed enterprise systems. The potential of ML classifiers, SHAP-based explainable artificial intelligence, AutoML, and surrogate modeling for the preliminary selection and evaluation of architectural configurations is considered. Load-testing approaches are analyzed, and the feasibility of using their results as feedback for iterative verification of architectural decisions is substantiated. Approaches to cybersecurity, fault tolerance, and survivability are systematized, and their incorporation as criteria for multi-criteria configuration selection is considered. The analysis demonstrates that existing methods and tools are primarily focused on solving individual tasks and remain insufficiently integrated into an end-to-end computer-aided design process. Based on the analysis, a conceptual formalization of such a process is proposed, sequentially combining the formalization of business and technical requirements, ML-based selection of an architectural class, prediction of configuration characteristics, iterative verification through load testing, and multi-criteria selection of a secure and fault-tolerant solution. Prospects for further research are identified, including the development and experimental validation of corresponding methods and information technologies for computer-aided design of enterprise computing systems.
Downloads
References
Bass, L., Clements, P., & Kazman, R. (2021). Software architecture in practice (4th ed.). Addison-Wesley Professional.
Lankhorst, M. (2017). Enterprise architecture at work: Modelling, communication and analysis (4th ed.). Springer. https://doi.org/10.1007/978-3-662-53933-0
Bezemer, C.-P., & Zaidman, A. (2010). Multi-tenant SaaS applications: Maintenance dream or nightmare? In Proceedings of the 4th International Joint ERCIM/IWPSE Symposium on Software Evolution (IWPSE-EVOL 2010) (pp. 88–92). Association for Computing Machinery. https://doi.org/10.1145/1862372.1862393
Gebreyesus, Y., Dalton, D., De Chiara, D., Chinnici, M., & Chinnici, A. (2024). AI for automating data center operations: Model explainability in the data centre context using Shapley Additive Explanations (SHAP). Electronics, 13(9), Article 1628. https://doi.org/10.3390/electronics13091628
Thota, M. R. (2024). Generative artificial intelligence as a catalyst for next-generation infrastructure design: Transforming the way enterprises architect, deploy, and scale digital platforms. European Journal of Advances in Engineering and Technology. https://doi.org/10.5281/zenodo.18183400
Mehla, A., Dahiya, N., & Singh, K. (2025). AI-driven cloud infrastructure provisioning: Leveraging ML, observability, and IaC for autonomous cloud operations. In Proceedings of ETNCC 2025. https://doi.org/10.1109/ETNCC66224.2025.11299663
Kushnir, D., Rehida, P., Klein, O., & Vizhevskyi, P. (2026). Method of organizing the functioning of distributed systems based on the automatic application of security criteria [Metod orhanizatsii funktsionuvannia rozpodilenykh system na osnovi avtomatychnoho zastosuvannia kryteriiv bezpeky]. Measuring and Computing Devices in Technological Processes, (2), 374–386. https://doi.org/10.31891/2219-9365-2026-86-44
Vitui, A., & Chen, T.-H. P. (2021). MLASP: Machine learning assisted capacity planning: An industrial experience report. Empirical Software Engineering, 26(5). https://doi.org/10.1007/s10664-021-09994-0
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017) (pp. 4765–4774).
Hud, O. O., & Kunanets, N. E. (2026). Comparative analysis of the effectiveness of XGBoost and LSTM algorithms in predicting the capacity of Scrum teams at different horizons [Porivnialnyi analiz efektyvnosti roboty alhorytmiv XGBoost ta LSTM u zadachi prohnozuvannia spromozhnosti scrum-komand na riznykh horyzontakh]. Scientific Bulletin of UNFU, 36(1), 162–168. https://doi.org/10.36930/40360118
Oleksiv, T. I. (2025). Application of machine learning for automated assessment of business process management in IT enterprises [Zastosuvannia mashynnoho navchannia dlia avtomatyzovanoho otsiniuvannia upravlinnia biznes-protsesamy v IT-pidpryiemstvakh]. Current Issues in Economic Sciences, (9). https://doi.org/10.5281/zenodo.15164477
Foo, K. C., Jiang, Z. M., Adams, B., Hassan, A. E., Zou, Y., & Flora, P. (2010). Mining performance regression testing repositories for automated performance analysis. In Proceedings of the 10th International Conference on Quality Software (QSIC 2010) (pp. 32–41). IEEE. https://doi.org/10.1109/QSIC.2010.35
Christadoss, J., & Mani, K. (2024). AI-based automated load testing and resource scaling in cloud environments using self-learning agents. Journal of Artificial Intelligence and General Science, 6(1), 604–618. https://doi.org/10.60087/jaigs.v6i1.401
Gaddam, R. R. (2025). AI-augmented dynamic performance engineering: A hybrid platform architecture. Journal of Information Systems Engineering and Management, 10(63s), 14–23. https://doi.org/10.52783/jisem.v10i63s.13804
Grant, O. H. (2025). Resource-aware cloud orchestration using ML-driven predictive scaling for high-demand IT applications. Innovative Research Thoughts, 11(4), 133–140. https://doi.org/10.36676/irt.v11.i4.1716
Dodonov, O. H., Kuznietsova, M. H., & Horbachyk, O. S. (2025). Modeling and evaluation of functional stability of information systems [Modeliuvannia i otsiniuvannia funktsionalnoi stiikosti informatsiinykh system]. Data Recording, Storage & Processing, 27(1), 76–88. https://doi.org/10.35681/1560-9189.2025.27.1.335752
Kuchma, Y., Polinovskyi, V., & Plakhtii, M. (2026). Methods of dynamic optimization of post-quantum digital signatures in authentication protocols for ultra-dense 6G networks [Metody dynamichnoi optymizatsii postkvantovykh tsyfrovykh pidpysiv u protokolakh avtentyfikatsii nadshchilnykh merezh 6G]. Cybersecurity: Education, Science, Technique, 1(33), 156–164. https://doi.org/10.28925/2663-4023.2026.33.1125
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
Olson, R. S., & Moore, J. H. (2016). TPOT: A tree-based pipeline optimization tool for automating machine learning. In Proceedings of the Workshop on Automatic Machine Learning (Proceedings of Machine Learning Research, 64, pp. 66–74). PMLR.
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Вадим Читулян, Світлана Поперешняк
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
