Machinery & Energetics

Performance trade-offs between predictive and reactive autoscaling in stateful microservices

Khrystyna Terletska
Download article
Abstract

The relevance of studying the trade-offs between reactive and predictive autoscaling of stateful microservices was due to the need to improve stability, resource performance and reliability of cloud systems in dynamic conditions. The aim of the study was to assess the effectiveness of reactive, predictive and hybrid autoscaling strategies in stateful microservice architectures. The methodological basis of the research relied on comparative, content, systems and structural-functional analyses, as well as modelling, which made it possible to comprehensively investigate the performance and stability of different approaches to autoscaling in stateful microservices. Theoretical analysis showed that autoscaling in microservice systems provides adaptive performance, and the choice of strategy depends on the nature of the workload, latency sensitivity and consistency requirements. The review of models demonstrated that reactive autoscaling responds quickly to changes but is accompanied by high latency, performance fluctuations and the risk of state divergence between replicas, whereas predictive autoscaling reduces scaling delay and increases stability and resource efficiency but requires accurate models and additional computational resources. Analysis of the results revealed that hybrid strategies integrate the advantages of both approaches, providing both flexibility and stability, and that system efficiency is determined by a trade-off between latency, stability, state consistency, resource efficiency and financial costs. The results of the study may be useful for developers and architects of cloud microservice systems, IT engineers and DevOps teams for optimising scaling strategies, increasing service stability and ensuring efficient resource use in different cloud environments

Keywords

Kubernetes, resource optimisation, cloud performance, dynamic resource allocation, system stability, observability metrics

Suggested citation
Terletska, Kh. (2025). Performance trade-offs between predictive and reactive autoscaling in stateful microservices. Machinery & Energetics, 16(4), 21-33. https://doi.org/10.31548/machinery/4.2025.21
References
  1. Almeida, F., & Bálint, B. (2024). Approaches for hybrid scaling of agile in the IT industry: A systematic literature review and research agenda. Information, 15(10), article number 592. doi: 10.3390/info15100592.
  2. Baarzi, A.F. (2021). Efficient service deployment on public cloud: A cost, performance, and security perspective. University Park: Pennsylvania State University.
  3. Babenko, T., Kolesnikova, K., Abramkina, O., & Vitulyova, Y. (2025). Automated OSINT techniques for digital asset discovery and cyber risk assessment. Computers, 14(10), article number 430. doi: 10.3390/computers14100430.
  4. Betti Pillippuge, T.L., Khan, Z., & Munir, K. (2025). Horizontal autoscaling of virtual machines in hybrid cloud infrastructures: Current status, challenges, and opportunities. Encyclopedia, 5(1), article number 37. doi: 10.3390/encyclopedia5010037.
  5. Boyapati, S., & Szabo, C. (2022). Self-adaptation in microservice architectures: A case study. In Proceedings of the 26th international conference on engineering of complex computer systems (pp. 42-51). Hiroshima: IEEE. doi: 10.1109/ICECCS54210.2022.00014.
  6. Chaudhari, A.V., & Charate, P.A. (2025). Dynamic orchestration of microservices across multi-cloud environments for low-latency applications. International Research Journal of Advanced Engineering and Science, 10(2), 165-172.
  7. Chilakala, H.S., Preeti, N., Marri, S.P., & Murali, K. (2024). Kalman integration with ARIMA & LSTM. In A. Kumar, G. Sharma, A. Sharma, P. Chopra & P. Rattan (Eds.), Advances in networks, intelligence and computing (pp. 562-569). London: CRC Press. doi: 10.1201/9781003430421.
  8. Guntupalli, B., & Vamshi, S. (2023). Designing microservices that handle high-volume data loads. International Journal of AI, BigData, Computational and Management Studies, 4(4), 76-87. doi: 10.63282/3050-9416.IJAIBDCMS-V4I4P109.
  9. Islam, M. (2025). The impact of data-driven web frameworks on performance and scalability of US enterprise applications. International Journal of Business and Economics Insights, 5(3), 523-558. doi: 10.63125/f07n4p12.
  10. Kanwal, N., Khoraminia, F., Kiraz, U., Mosquera-Zamudio, A., Monteagudo, C., Janssen, E., Zuiverloon, T., Rong, C., & Engan, K. (2024). Equipping computational pathology systems with artifact processing pipelines: A showcase for computation and performance trade-offs. BMC Medical Informatics and Decision Making, 24(1), article number 288. doi: 10.1186/s12911-024-02676-z.
  11. Karol Santos Nunes, J.P., Nejati, S., Sabetzadeh, M., & Nakagawa, E.Y. (2024). Self-adaptive, requirements-driven autoscaling of microservices. In L. Baresi (Ed.), Proceedings of the 19th international symposium on software engineering for adaptive and self-managing systems (pp. 168-174). New York: Association for Computing Machinery. doi: 10.1145/3643915.3644094.
  12. Khaleq, A., & Ra, I. (2021). Intelligent autoscaling of microservices in the cloud for real-time applications. IEEE Access, 9, 35464-35476. doi: 10.1109/ACCESS.2021.3061890.
  13. Kumari, A., Anand, A.K., & Sahoo, B. (2023). From stateless to stateful: a comparative analysis of stateful serverless computing frameworks. In R. Tiwari, M. Saraswat & M. Pavone (Eds.), International conference on computational intelligence (pp. 223-237). Singapore: Springer. doi: 10.1007/978-981-97-3526-6_19.
  14. Maliakel, P.J., Ilager, S., & Brandic, I. (2025). Investigating energy efficiency and performance trade-offs in LLM inference across tasks and DVFS settings. arXiv. doi: 10.48550/arXiv.2501.08219.
  15. Mekki, M., Ksentini, A., & Meliani, A.E. (2025). Resiliency focused proactive lifecycle management for stateful microservices in multi-cluster containerized environments. Computer Communications, 236, article number 108111. doi: 10.1016/j.comcom.2025.108111.
  16. Meng, C., Song, S., Tong, H., Pan, M., & Yu, Y. (2023). Deepscaler: Holistic autoscaling for microservices based on spatiotemporal GNN with adaptive graph learning. In Proceedings of the 38th IEEE/ACM international conference on automated software engineering (pp. 53-65). Luxemburg: IEEE. doi: 10.1109/ASE56229.2023.00038.
  17. Oleti, C.S. (2023). Enterprise AI at scale: Architecting secure microservices with spring boot and AWS. International Journal of Research in Computer Applications and Information Technology, 6(1), 133-154. doi: 10.34218/IJRCAIT_06_01_011.
  18. Palamarchuk, Yu. (2022). Methods of building microservice architecture of e-learning systems. Information Technologies and Computer Engineering, 19(2), 43-54. doi: 10.31649/1999-9941-2022-53-1-43-54
  19. Pavlenko, A., Cahoon, J., Zhu, Y., Kroth, B., Nelson, M., Carter, A., Liao, D., Wright, T., Camacho-Rodriguez, J., & Saur, K. (2024). Vertically autoscaling monolithic applications with CaaSPER: Scalable container-a s-a-service performance enhanced resizing algorithm for the cloud. In P. Barcelo & N. Sanchez-Pi (Eds.), Companion of the 2024 international conference on management of data (pp. 241-254). New York: Association for Computing Machinery. doi: 10.1145/3626246.3653378.
  20. Prasad, T.A. (2023). AI-driven predictive scaling for performance optimization in cloud-native architectures. Journal of Electrical Systems, 19(4), 607-617.
  21. Prodanov, J., Bertalanič, B., Fortuna, C., Chou, S.K., Jurič, M.B., Sanchez-Iborra, R., & Hribar, J. (2025). Multi-agent reinforcement learning-based in-place scaling engine for edge-cloud systems. In Proceedings of the 18th international conference on cloud computing (pp. 32-42). Helsinki: IEEE. doi: 10.1109/CLOUD67622.2025.00014.
  22. Quattrocchi, G., Incerto, E., Pinciroli, R., Trubiani, C., & Baresi, L. (2024). Autoscaling solutions for cloud applications under dynamic workloads. IEEE Transactions on Services Computing, 17(3), 804-820. doi: 10.1109/TSC.2024.3354062.
  23. Rampérez, V., Soriano, J., Lizcano, D., & Lara, J.A. (2021). FLAS: A combination of proactive and reactive auto-scaling architecture for distributed services. Future Generation Computer Systems, 118, 56-72. doi: 10.1016/j.future.2020.12.025.
  24. Rao, A. (2021). Architectural trade-offs between stateless and stateful microservices in large-scale cloud systems. International Journal of Innovation Studies, 5(1), 135-141.
  25. Razavi, K., Salmani, M., Mühlhäuser, M., Koldehofe, B., & Wang, L. (2024). A tale of two scales: Reconciling horizontal and vertical scaling for inference serving systems. arXiv. doi: 10.48550/arXiv.2407.14843.
  26. Rodrigues, S., Rosas, M., Delbianco, N., Cláudia, C., Peterson, B., & Grácio, M.C. (2025). Latency vs. cost trade-offs in serverless ETL: A decision-theoretic framework for architecture design. Retrieved from https://www.researchgate.net/publication/393003364_Latency_vs_Cost_Trade-offs_in_Serverless_ETL_A_Decision-Theoretic_Framework_for_Architecture_Design.
  27. Romanov, O., Mankivskyi, V., Romanov, A., Nesterenko, M., & Pidpaly, O. (2024). Performance assessing of dynamic scaling of containerized applications when using kubernetes cluster autoscaler and auto scaling group together. In M. Ilchenko, L. Uryvsky & L. Globa (Eds.), Advanced smart information and communication technology and systems (pp. 111-136). Cham: Springer. doi: 10.1007/978-3-031-94799-5_7.
  28. Tabilo Alvarez, J., & Ramírez-Correa, P. (2023). A brief review of systems, cybernetics, and complexity. Complexity, 2023(1), article number 8205320. doi: 10.1155/2023/8205320.
  29. Thompson, M.A., Carter, J.L., Nguyen, D.R., Bennett, S.K., Miller, R.J., & James, A. (2023). Intelligent workload balancing across multi-cloud providers. Retrieved from https://tinyurl.com/4x7sebkh.
  30. Tutuncuoglu, B.T. (2025). Phoenix stack: A self-healing microservice architecture for real-time web applications. Retrieved from https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5343101.
  31. Varzhanskiy, I., Melnychenko, A., Naiev, S., & Kapustynskyi, O. (2025). Foresight and active forecast potential for improving defense capability. European Journal of Interdisciplinary Studies, 17(1). doi: 10.24818/ejis.2025.01.
  32. Vasireddy, I., Wankar, R., & Chillarige, R. (2025). Improving scalability, energy efficiency, and cost-effectiveness in Kubernetes clusters using a nonlinear regression-based predictive replica model and ORLE algorithm. Egyptian Informatics Journal, 31, article number 100732. doi: 10.1016/j.eij.2025.100732.
  33. Yang, M., Wang, X., Cai, B., Wang, Y., & Guo, Y. (2025). Full stack optimization of microservice architecture: Systematic review and research opportunity. Cluster Computing, 28, article number 1005. doi: 10.1007/s10586-025-05690-6.
  34. Zou, D., Lu, W., Zhu, Z., Lu, X., Zhou, J., Wang, X., Liu, K., Sun, R., & Wang, H. (2024). OptScaler: A collaborative framework for robust autoscaling in the cloud. Proceedings of the VLDB Endowment, 17(12), 4090-4103. doi: 10.14778/3685800.3685829.