METHOD OF ADAPTIVE SCALING OF CLOUD RESOURCES BASED ON REINFORCEMENT LEARNING
DOI:
https://doi.org/10.28925/2663-4023.2026.35.1385Keywords:
cloud infrastructure, adaptive scaling, reinforcement learning, cloud resources, automated management, resource optimization, intelligent systems, distributed computing, workload scaling, decision-makingAbstract
The article considers the problem of adaptive scaling of cloud infrastructure resources under conditions of dynamic workload changes, uneven utilization of computational resources, and the necessity to ensure stable operation of information services. It has been determined that traditional approaches to horizontal and vertical scaling are mainly based on static threshold rules or predictive models that do not provide sufficient flexibility in a changing environment and do not take into account the multicriteria nature of the resource management process. The feasibility of using reinforcement learning methods for the formation of an adaptive cloud infrastructure management strategy is substantiated. The paper analyzes modern methods of automated resource scaling, decision-making models in cloud systems, and approaches to the use of reinforcement learning methods in workload optimization tasks. A method for adaptive scaling of cloud resources is proposed, based on the use of an intelligent agent that evaluates the current state of the infrastructure, analyzes workload parameters, request processing delays, processor resource utilization, and memory usage, and forms an optimal scaling strategy. A state model, reward system, and mechanism for selecting control actions for automated resource allocation have been developed. Within the experimental study, the proposed method was compared with classical automated scaling algorithms. The obtained results confirmed a reduction in request processing delays, improved resource utilization efficiency, and enhanced stability of cloud system operation. The practical significance of the work lies in the possibility of applying the proposed method for automated resource management in large distributed information systems and modern services.
Downloads
References
Qiu, H., Mao, W., Wang, C., Franke, H., Youssef, A., Kalbarczyk, Z. T., Başar, T., & Iyer, R. K. (2023). AWARE: Automate workload autoscaling with reinforcement learning in production cloud systems. In 2023 USENIX Annual Technical Conference (USENIX ATC 23) (pp. 387–402).
Mishra, P., Hans, S., Saha, D., & Moogi, P. (2024). Optimizing cloud workloads: Autoscaling with reinforcement learning. In 2024 IEEE 17th International Conference on Cloud Computing (CLOUD) (pp. 217–222). IEEE. https://doi.org/10.1109/CLOUD62652.2024.00033
Alharthi, S., Alshamsi, A., Alseiari, A., & Alwarafy, A. (2024). Auto-scaling techniques in cloud computing: Issues and research directions. Sensors, 24(17), 5551. https://doi.org/10.3390/s24175551
Pintye, I., Kovács, J., & Lovas, R. (2024). Enhancing machine learning-based autoscaling for cloud resource orchestration. Journal of Grid Computing, 22, 68. https://doi.org/10.1007/s10723-024-09783-1
Feng, X., Zhang, S., Jiao, T., Guo, C., & Song, J. (2025). Adaptive container auto-scaling for fluctuating workloads in cloud. Future Generation Computer Systems, 172, 107872. https://doi.org/10.1016/j.future.2025.107872
Moreno-Vozmediano, R., Huedo, E., Montero, R. S., & Llorente, I. M. (2025). AI-driven resource allocation and auto-scaling of VNFs in edge-5G-IoT ecosystems. Electronics, 14(9), 1808. https://doi.org/10.3390/electronics14091808
Alatawi, M. N. (2025). Optimizing multitenancy: Adaptive resource allocation in serverless cloud environments using reinforcement learning. Electronics, 14(15), 3004. https://doi.org/10.3390/electronics14153004
Skladannyi, P., Kostiuk, Y., Sokolov, V., & Khorolska, K. (2026). Network traffic analysis and management. In Handbook of Cybersecurity Challenges and Solutions for Emerging Technologies (pp. 148–172). https://doi.org/10.1201/9781003640790-9
Xu, M., Song, C., Wu, H., Gill, S. S., Ye, K., & Xu, C. (2022). esdnn: Deep neural network based multivariate workload prediction in cloud computing environments. ACM Transactions on Internet Technology, 22(3). https://doi.org/10.1145/3524114
Kostiuk, Y., Skladannyi, P., Sokolov, V., & Rzaieva, S. (2025). Intelligent system for simulation modeling and research of information objects. In Proceedings of the 1st Workshop Software Engineering and Semantic Technologies (SEST 2025) (Vol. 4053, pp. 237–251). CEUR Workshop Proceedings.
Khan, T., Tian, W., Zhou, G., Ilager, S., Gong, M., & Buyya, R. (2022). Machine learning-centric resource management in cloud computing: A review and future directions. Journal of Network and Computer Applications, 204, 103405.
Kostiuk, Y., Skladannyi, P., Sokolov, V., & Vorokhob, M. (2025). Models and technologies of cognitive agents for decision-making with integration of artificial intelligence. In Proceedings of the Modern Data Science Technologies Doctoral Consortium (MoDaST 2025) (Vol. 4005, pp. 82–96). CEUR Workshop Proceedings.
Zhong, Z., Xu, M., Rodríguez, M., Xu, C.-Z., & Buyya, R. (2022). Machine learning-based orchestration of containers: A taxonomy and future directions. ACM Computing Surveys, 54. https://doi.org/10.1145/3510415
Kostiuk, Y., Skladannyi, P., Korshun, N., Bebeshko, B., & Khorolska, K. (2024). Integrated protection strategies and adaptive resource distribution for secure video streaming over a Bluetooth network. In Workshop on Cybersecurity Providing in Information and Telecommunication Systems II (CPITS-II 2024) (Vol. 3826, pp. 129–138). CEUR Workshop Proceedings.
Dixit, A., Gupta, R. K., Dubey, A., & Misra, R. (2021). Machine learning based adaptive auto-scaling policy for resource orchestration in Kubernetes clusters. In International Conference on Internet of Things and Connected Technologies (pp. 1–16). Springer.
Складанний, П. М., Костюк, Ю. В., Мазур, Н. П., & Пітайчук, М. А. (2025). Дослідження характеристик та продуктивності протоколів доступу до хмарних обчислювальних середовищ на основі універсального тестування. Телекомунікаційні та інформаційні технології, 1(86), 61–74. https://doi.org/10.31673/2412-4338.2025.014649
Garí, Y., Monge, D. A., Pacini, E., Mateos, C., & Garino, C. G. (2021). Reinforcement learning-based application autoscaling in the cloud: A survey. Engineering Applications of Artificial Intelligence, 102, 104288.
Костюк, Ю., Складанний, П., Рзаєва, С., Самойленко, Ю., & Коршун, Н. (2025). Інтелектуальні системи керування та захисту в кіберфізичних і хмарних середовищах Smart Grid. Кібербезпека: освіта, наука, техніка, 2(30), 125–156. https://doi.org/10.28925/2663-4023.2025.30.956
Benedetti, P., Femminella, M., Reali, G., & Steenhaut, K. (2022). Reinforcement learning applicability for resource-based auto-scaling in serverless edge applications. In 2022 IEEE International Conference on Pervasive Computing and Communications Workshops (pp. 674–679). IEEE.
Rzaeva, S., Skladannyi, P., Kostiuk, Y., Abramov, V., & Kravchenko, V. (2025). Adaptive information security management in cloud-oriented intelligent transportation systems. Ukrainian Scientific Journal of Information Security, 31(1), 23–36. https://doi.org/10.18372/2225-5036.31.20634
Schuler, L., Jamil, S., & Kühl, N. (2021). AI-based resource allocation: Reinforcement learning for adaptive auto-scaling in serverless environments. In 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid) (pp. 804–811). IEEE.
Складанний, П., Костюк, Ю., Рзаєва, С., & Мазур, Н. (2025). Паралельна обробка даних у розширюваних хеш-структурах та оцінка їх продуктивності. Кібербезпека: освіта, наука, техніка, 3(31), 242–269. https://doi.org/10.28925/2663-4023.2025.31.1015
Atadoga, A., Umoga, U. J., Lottu, O. A., & Sodiya, E. O. (2024). Evaluating the impact of cloud computing on accounting firms: A review of efficiency, scalability, and data security. Global Journal of Engineering and Technology Advances, 18(2), 065–074.
Довженко, Н., Мазур, Н., Костюк, Ю., & Рзаєва, С. (2024). Інтеграція IОT та штучного інтелекту в інтелектуальні транспортні системи. Кібербезпека: освіта, наука, техніка, 2(26), 430–444. https://doi.org/10.28925/2663-4023.2024.26.708
Patel, Y. S., & Bedi, J. (2023). Mag-d: A multivariate attention network based approach for cloud workload forecasting. Future Generation Computer Systems, 142, 376–392.
Kostiuk, Y., Skladannyi, P., Samoilenko, Y., Khorolska, K., Bebeshko, B., & Sokolov, V. (2024). A system for assessing the interdependencies of information system agents in information security risk management using cognitive maps. In Third International Conference on Cyber Hygiene & Conflict Management in Global Information Networks (CH&CMiGIN’24) (Vol. 3925, pp. 249–264). CEUR Workshop Proceedings.
Chen, X., Zhu, F., Chen, Z., Min, G., Zheng, X., & Rong, C. (2022). Resource allocation for cloud-based software services using prediction-enabled feedback control with reinforcement learning. IEEE Transactions on Cloud Computing, 10(2), 1117–1129. https://doi.org/10.1109/TCC.2020.2992537
Patsias, V., Amanatidis, P., Karampatzakis, D., Lagkas, T., Michalakopoulou, K., & Nikitas, A. (2023). Task allocation methods and optimization techniques in edge computing: A systematic review of the literature. Future Internet, 15(8), 254.
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Андрій Пазинін
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
