EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Anomaly Detection in Cloud Computing: A Systematic Review of Machine Learning Approaches

Dhananjay Kumar, Jeetendra Singh Yadav

International Journal of Scientific Research in Science, Engineering and Technology · 02.07.2025 · 12 (4) · 15-22

DOI: 10.32628/ijsrset2512402 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 02.07.2025. Verfasst von Dhananjay Kumar und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud computing has become an essential pillar of digital infrastructure, offering on-demand services with high scalability and flexibility. However, ensuring consistent performance and reliability in such dynamic environments remains a significant challenge. Anomaly detection plays a critical role in identifying deviations from normal behavior that could indicate system faults, performance bottlenecks, or security breaches. Recently, machine learning (ML) techniques have shown remarkable success in detecting such anomalies due to their ability to analyze large volumes of heterogeneous data and adapt to evolving patterns. This systematic review explores various ML-based anomaly detection methods applied within cloud computing environments. The paper categorizes the approaches into supervised, unsupervised, and semi-supervised models, examining their performance, scalability, real-time capabilities, and implementation complexity. Additionally, it highlights the challenges related to data labeling, model generalization, and integration into live cloud systems. Key publicly available datasets and evaluation metrics used in the literature are also reviewed. The study concludes by identifying research gaps and proposing future directions to enhance the robustness, interpretability, and efficiency of ML-driven anomaly detection frameworks in cloud settings.

Zitieren

APA

Kumar, D., & Yadav, J. S. (2025). Anomaly Detection in Cloud Computing: A Systematic Review of Machine Learning Approaches. International Journal of Scientific Research in Science, Engineering and Technology, 12(4), 15-22. https://doi.org/10.32628/ijsrset2512402

Vancouver

Kumar D, Yadav JS. Anomaly Detection in Cloud Computing: A Systematic Review of Machine Learning Approaches. International Journal of Scientific Research in Science, Engineering and Technology. 2025;12(4):15-22. doi:10.32628/ijsrset2512402

BibTeX
@article{Kumar2025,
  author = {Kumar, Dhananjay and Yadav, Jeetendra Singh},
  title = {Anomaly Detection in Cloud Computing: A Systematic Review of Machine Learning Approaches},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2025},
  volume = {12},
  number = {4},
  pages = {15--22},
  doi = {10.32628/ijsrset2512402}
}
Kostenlos starten →