EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

АНСАМБЛЕВА МОДЕЛЬ ПРОГНОЗУВАННЯ ВІДМОВ ЗАВДАНЬ У ХМАРНИХ ОБЧИСЛЕННЯХ

Vasyl Znaidiuk, Vladyslav Tukhtarov

Системи управління, навігації та зв’язку. Збірник наукових праць · 04.05.2026 · 2 (84) · 95-103

DOI: 10.26906/sunz.2026.2.095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Системи управління, навігації та зв’язку. Збірник наукових праць, online erschienen am 04.05.2026. Verfasst von Vasyl Znaidiuk und 1 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Relevance. Cloud computing is a key component of modern IT infrastructure; however, task failures negatively affect service quality and resource utilization efficiency. The increasing complexity of cloud systems and the growing volume of data necessitate the use of intelligent failure prediction methods, enabling the transition from reactive to proactive and resilient resource management approaches. Object of research: processes of task failure prediction in cloud computing systems. Purpose of the article: development of an ensemble model for task failure prediction in cloud computing based on a combination of machine learning methods. Research results. The paper proposes an ensemble model based on the stacking method, combining the Knearest neighbors algorithm and an artificial neural network with a meta-model based on logistic regression. Data preprocessing and analysis of the Google Cluster Trace dataset were performed, feature engineering was conducted, and a predictive model was developed. Experimental results demonstrated that the proposed ensemble model improves prediction accuracy and enhances F1score, precision, and recall compared to individual models. It was established that the ensemble approach reduces overfitting and increases prediction reliability. Conclusions. The proposed model is an effective tool for task failure prediction in cloud systems and can be applied to optimize resource scheduling and improve fault tolerance. The use of the ensemble approach contributes to reducing resource consumption and supports the concept of green computing. Scope of application: task scheduling systems, resource management, and fault tolerance enhancement in cloud computing and data centers.

Zitieren

APA

Znaidiuk, V., & Tukhtarov, V. (2026). АНСАМБЛЕВА МОДЕЛЬ ПРОГНОЗУВАННЯ ВІДМОВ ЗАВДАНЬ У ХМАРНИХ ОБЧИСЛЕННЯХ. Системи управління, навігації та зв’язку. Збірник наукових праць, 2(84), 95-103. https://doi.org/10.26906/sunz.2026.2.095

Vancouver

Znaidiuk V, Tukhtarov V. АНСАМБЛЕВА МОДЕЛЬ ПРОГНОЗУВАННЯ ВІДМОВ ЗАВДАНЬ У ХМАРНИХ ОБЧИСЛЕННЯХ. Системи управління, навігації та зв’язку. Збірник наукових праць. 2026;2(84):95-103. doi:10.26906/sunz.2026.2.095

BibTeX
@article{Znaidiuk2026,
  author = {Znaidiuk, Vasyl and Tukhtarov, Vladyslav},
  title = {АНСАМБЛЕВА МОДЕЛЬ ПРОГНОЗУВАННЯ ВІДМОВ ЗАВДАНЬ У ХМАРНИХ ОБЧИСЛЕННЯХ},
  journal = {Системи управління, навігації та зв’язку. Збірник наукових праць},
  year = {2026},
  volume = {2},
  number = {84},
  pages = {95--103},
  doi = {10.26906/sunz.2026.2.095}
}
Kostenlos starten →