koz"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"Bulletin of Manash Kozybayev North Kazakhstan University2958-003X2958-0048М. Қозыбаев атындағы СҚУ10.54596/2958-0048-2026-2-278-294koz-2591Research ArticleИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИINFORMATION AND COMMUNICATION TECHNOLOGIESАНАЛИТИЧЕСКИЙ ОБЗОР СОВРЕМЕННЫХ АДАПТИВНЫХ МЕТОДОВ ПОТОКОВОЙ ОБРАБОТКИ ДАННЫХ В СИСТЕМАХ РЕАЛЬНОГО ВРЕМЕНИAN ANALYTICAL REVIEW OF MODERN ADAPTIVE METHODS FOR STREAM DATA PROCESSING IN REAL-TIME SYSTEMShttps://orcid.org/0000-0001-8632-5209ДжумагалиеваА.JumagaliyevaA.

Астана

doctoral student

Astana

jumagalievaainur.m@gmail.comhttps://orcid.org/0000-0001-7494-9794ҚалдароваМ.KaldarovaM.

Астана

PhD

Astana International University

mirakaldarova.zh@gmail.comhttps://orcid.org/0000-0003-0308-2315ИсмаиловаР.IsmailovaR.

Бишкек

PhD, Associate Professor

Bishkek

rita.ismailova@manas.edu.kghttps://orcid.org/0000-0002-1447-4077AбдыкеримоваЭ.AbdykerimovaE.

Актау

Candidate of Pedagogical Sciences, Professor, Department of Computer Science

Aktau

abdykerimovaelmiraa@gmail.comhttps://orcid.org/0000-0002-7401-6887TуркменбаевА.TurkmenbayevA.

Актау

Candidate of Pedagogical Sciences, Professor. Department of Fundamental Sciences

Aktau

assetabdykerimov@gmail.comAstana International UniversityКазахстанAstana International UniversityKazakhstanКыргызско-Турецкий университет МанасКыргызстанKyrgyz-Turkish Manas UniversityKyrgyzstanКаспийский университет технологий и инжиниринга имени Ш. ЕсеноваКазахстанCaspian State University of Technology and Engineering named after Sh. YessenovKazakhstan20260907202602 (70)278294Copyright © Джумагалиева А., Қалдарова М., Исмаилова Р., Aбдыкеримова Э., Tуркменбаев А., 20262026Джумагалиева А., Қалдарова М., Исмаилова Р., Aбдыкеримова Э., Tуркменбаев А.Jumagaliyeva A., Kaldarova M., Ismailova R., Abdykerimova E., Turkmenbayev A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.ku.edu.kz/jour/article/view/2591

Системы реального времени обрабатывают непрерывные, нестационарные потоки данных, соблюдая при этом строгие ограничения по задержке, и используют механизмы адаптивного обучения для обеспечения стабильного уровня надежности прогнозирования. Современные методы достижения этой цели, как правило, отдают приоритет либо точности модели, либо вычислительной масштабируемости, а не интеграции метода адаптивного обучения в потоковую среду. Цель данного исследования – систематический обзор современных методов адаптивного обучения для обработки потоковых данных в реальном времени с использованием многоэтапной методологии, включающей библиометрический анализ, систематический обзор литературы и структурированный сравнительный синтез. Всего было проанализировано 58 исследований для выявления закономерностей в адаптивных возможностях, подходах к архитектурной интеграции и оценке производительности всей системы. Результаты показали постоянный компромисс между адаптивностью и детерминированной задержкой, а также отсутствие межслойной координации и измерения производительности. На основе аналитического синтеза рассмотренной литературы предлагается концептуальный межслойный аналитический фреймворк. Представлены методологические рекомендации по проектированию адаптивных систем, демонстрирующих высокий уровень производительности при сохранении стабильной работы в динамических, нестационарных средах.

Real-time systems process continuous, non-stationary data streams while adhering to strict latency constraints and employ adaptive learning mechanisms to ensure a stable level of prediction reliability. Current methods for achieving this goal typically prioritize either model accuracy or computational scalability over the integration of an adaptive learning method into a streaming environment. The objective of this study is to systematically review state-of-the-art adaptive learning methods for real-time streaming data processing using a multi-step methodology including bibliometric analysis, a systematic literature review, and a structured comparative synthesis. A total of 58 studies were analyzed to identify patterns in adaptive capabilities, architectural integration approaches, and overall system performance evaluation. The results revealed a consistent tradeoff between adaptivity and deterministic latency, as well as a lack of cross-layer coordination and performance measurement. Based on the analytical synthesis of the reviewed literature, a conceptual cross-layer analytical framework supporting the integration of adaptive learning and distributed streaming systems is proposed. Methodological recommendations for the design of adaptive systems demonstrating a high level of performance while maintaining stable operation in dynamic, non-stationary environments are presented.

адаптивное машинное обучениепотоковая обработкасистемы реального временизадержка временистабильностьмежслойная системаadaptive machine learningstream processingreal-time systemstime latencystabilityinterlayer systemReferencesAlam M.A., Nabil A.R., Mintoo A.A., Islam A. Real-time analytics in streaming big data: techniques and applications // Journal of Science and Engineering Research-2024. -Vol. 1(01). -P. 104-122. DOI: https://doi.org/10.70008/jeser.v1i01.56.Alam M.A., Nabil A.R., Mintoo A.A., Islam A. Real-time analytics in streaming big data: techniques and applications // Journal of Science and Engineering Research-2024. -Vol. 1(01). -P. 104-122. DOI: https://doi.org/10.70008/jeser.v1i01.56.Almeida A. et al. Time series big data: a survey on data stream frameworks, analysis and algorithms //Journal of Big Data. – 2023. – Т. 10. – №. 1. – С. 83. DOI: https://doi.org/10.1186/s40537-023-00760-1.Almeida A. et al. Time series big data: a survey on data stream frameworks, analysis and algorithms //Journal of Big Data. – 2023. – Т. 10. – №. 1. – С. 83. DOI: https://doi.org/10.1186/s40537-023-00760-1.Marcu O.C., Bouvry P. Big data stream processing // Proceedings of IEEE Big Data. -2023. DOI:10.1109/bigdata59044.2023.10386254.Marcu O.C., Bouvry P. Big data stream processing // Proceedings of IEEE Big Data. -2023. DOI:10.1109/bigdata59044.2023.10386254.Li S. et al. Federated and distributed learning applications for electronic health records and structured medical data: a scoping review // Journal of the American Medical Informatics Association. – 2023. – Т. 30. – №. 12. – С. 2041-2049. DOI:10.1093/jamia/ocad170Li S. et al. Federated and distributed learning applications for electronic health records and structured medical data: a scoping review // Journal of the American Medical Informatics Association. – 2023. – Т. 30. – №. 12. – С. 2041-2049. DOI:10.1093/jamia/ocad170Aghazadeh Ardebili A., Hasidi O., Bendaouia A., Khalil A., Khalil S., Luceri D., Ficarella A. Enhancing resilience in complex energy systems through real-time anomaly detection // Energy Informatics. - 2024. -Vol. 7(1). -P. 96. DOI:10.1186/s42162-024-00401-8.Aghazadeh Ardebili A., Hasidi O., Bendaouia A., Khalil A., Khalil S., Luceri D., Ficarella A. Enhancing resilience in complex energy systems through real-time anomaly detection // Energy Informatics. - 2024. -Vol. 7(1). -P. 96. DOI:10.1186/s42162-024-00401-8.Muratova G., Jumagaliyeva A., Rystygulova V., Abdykerimova E., Turkmenbayev A., Serimbetov B., Yersultanova Z., Omarkulova G. Development of deep learning framework for complex pattern recognition in big data//Eastern-European Journal of Enterprise Technologies. - 2025. -Vol. 6(9 (138)). - P. 54–66. DOI:10.15587/1729-4061.2025.341468.Muratova G., Jumagaliyeva A., Rystygulova V., Abdykerimova E., Turkmenbayev A., Serimbetov B., Yersultanova Z., Omarkulova G. Development of deep learning framework for complex pattern recognition in big data//Eastern-European Journal of Enterprise Technologies. - 2025. -Vol. 6(9 (138)). - P. 54–66. DOI:10.15587/1729-4061.2025.341468.Hovakimyan G., Bravo J. M. Evolving strategies in machine learning: a systematic review of concept drift detection // Information. – 2024. – Т. 15. – №. 12. – С. 786. DOI: https://doi.org/10.3390/info15120786Hovakimyan G., Bravo J. M. Evolving strategies in machine learning: a systematic review of concept drift detection // Information. – 2024. – Т. 15. – №. 12. – С. 786. DOI: https://doi.org/10.3390/info15120786Ntumba P., Georgantas N., Christophides V. Adaptive scheduling of continuous operators for iot edge analytics // Future Generation Computer Systems. – 2024. – Т. 158. – С. 277-293. DOI: https://doi.org/10.1016/j.future.2024.04.029Ntumba P., Georgantas N., Christophides V. Adaptive scheduling of continuous operators for iot edge analytics // Future Generation Computer Systems. – 2024. – Т. 158. – С. 277-293. DOI: https://doi.org/10.1016/j.future.2024.04.029Mehmood H. et al. A novel edge architecture and solution for detecting concept drift in smart environments // Future Generation Computer Systems. – 2024. – Т. 150. – С. 127-143. DOI: https://doi.org/10.1016/j.future.2023.08.023Mehmood H. et al. A novel edge architecture and solution for detecting concept drift in smart environments // Future Generation Computer Systems. – 2024. – Т. 150. – С. 127-143. DOI: https://doi.org/10.1016/j.future.2023.08.023Sulaiman M. et. al. Online deep learning’s role in conquering the challenges of streaming data: a survey // Knowledge and Information Systems. – 2025. – Т. 67. – №. 4. – С. 3159-3203. DOI: https://doi.org/10.1007/s10115-025-02351-3Sulaiman M. et. al. Online deep learning’s role in conquering the challenges of streaming data: a survey // Knowledge and Information Systems. – 2025. – Т. 67. – №. 4. – С. 3159-3203. DOI: https://doi.org/10.1007/s10115-025-02351-3Rodrigues M.G. et al. A MLOps architecture for near real-time distributed Stream Learning operation deployment // Journal of Network and Computer Applications. – 2025. – Т. 238. – С. 104169. DOI: https://doi.org/10.1016/j.jnca.2025.104169Rodrigues M.G. et al. A MLOps architecture for near real-time distributed Stream Learning operation deployment // Journal of Network and Computer Applications. – 2025. – Т. 238. – С. 104169. DOI: https://doi.org/10.1016/j.jnca.2025.104169Hu L., Lu Y., Feng Y. Concept drift detection based on deep neural networks and autoencoders // Applied Sciences. – 2025. – Т. 15. – №. 6. – С. 3056. DOI: https://doi.org/10.3390/app15063056Hu L., Lu Y., Feng Y. Concept drift detection based on deep neural networks and autoencoders // Applied Sciences. – 2025. – Т. 15. – №. 6. – С. 3056. DOI: https://doi.org/10.3390/app15063056Mahdi O.A. et al. Federated Learning Under Concept Drift: A Systematic Survey of Foundations, Innovations, and Future Research Directions // Electronics. – 2025. – Т. 14. – №. 22. – С. 4480. DOI: https://doi.org/10.3390/electronics14224480Mahdi O.A. et al. Federated Learning Under Concept Drift: A Systematic Survey of Foundations, Innovations, and Future Research Directions // Electronics. – 2025. – Т. 14. – №. 22. – С. 4480. DOI: https://doi.org/10.3390/electronics14224480Rancea A., Anghel I., Cioara T. Edge computing in healthcare: Innovations, opportunities, and challenges // Future internet. – 2024. – Т. 16. – №. 9. – С. 329. DOI: https://doi.org/10.3390/fi16090329Rancea A., Anghel I., Cioara T. Edge computing in healthcare: Innovations, opportunities, and challenges // Future internet. – 2024. – Т. 16. – №. 9. – С. 329. DOI: https://doi.org/10.3390/fi16090329Suárez-Cetrulo A.L., Quintana D., Cervantes A. A survey on machine learning for recurring concept drifting data streams // Expert Systems with Applications. – 2023. – Т. 213. – С. 118934. DOI: https://doi.org/10.1016/j.eswa.2022.118934Suárez-Cetrulo A.L., Quintana D., Cervantes A. A survey on machine learning for recurring concept drifting data streams // Expert Systems with Applications. – 2023. – Т. 213. – С. 118934. DOI: https://doi.org/10.1016/j.eswa.2022.118934

The authors declare that there are no conflicts of interest present.