EUVIMEDEUVIMED entdecken
Crossref

An Adaptive Deep Learning Framework for Real-Time Anomaly Detection in Scalable Cloud Computing Environments

Karan Sukhija

Dandao Xuebao/Journal of Ballistics · 30.06.2026 · 38 (3) · 20-28

DOI: 10.52783/dxjb.v38.490 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 30.06.2026. Verfasst von Karan Sukhija.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid proliferation of cloud computing infrastructure has introduced unprecedented challenges in maintaining operational security, system reliability, and performance integrity across large-scale distributed environments. Anomaly detection has emerged as a critical mechanism for identifying deviations from normal operational behavior that may indicate security breaches, system failures, resource abuse, or service degradation. However, conventional anomaly detection approaches frequently struggle to keep pace with the dynamic, heterogeneous, and high-volume nature of modern cloud workloads. This study proposes and evaluates an adaptive deep learning framework for real-time anomaly detection in scalable cloud computing environments, integrating insights from machine learning, distributed systems, cybersecurity, and cloud architecture research. The framework combines Long Short-Term Memory (LSTM) networks, Autoencoders, and attention-based Transformer models to capture temporal patterns, feature representations, and contextual dependencies within cloud telemetry data. Adaptive mechanisms enable the framework to dynamically adjust detection thresholds and model parameters in response to evolving workload distributions. The study employs an experimental and simulation-based research methodology using publicly available cloud monitoring datasets alongside a controlled private cloud testbed. Evaluation results demonstrate that the proposed framework achieves superior detection accuracy, lower false positive rates, and competitive real-time latency compared to existing baseline approaches. The findings underscore the importance of integrating architectural adaptability, multi-model fusion, and online learning strategies into anomaly detection systems designed for cloud-scale deployments.

Zitieren

APA

Sukhija, K. (2026). An Adaptive Deep Learning Framework for Real-Time Anomaly Detection in Scalable Cloud Computing Environments. Dandao Xuebao/Journal of Ballistics, 38(3), 20-28. https://doi.org/10.52783/dxjb.v38.490

Vancouver

Sukhija K. An Adaptive Deep Learning Framework for Real-Time Anomaly Detection in Scalable Cloud Computing Environments. Dandao Xuebao/Journal of Ballistics. 2026;38(3):20-28. doi:10.52783/dxjb.v38.490

BibTeX
@article{Sukhija2026,
  author = {Sukhija, Karan},
  title = {An Adaptive Deep Learning Framework for Real-Time Anomaly Detection in Scalable Cloud Computing Environments},
  journal = {Dandao Xuebao/Journal of Ballistics},
  year = {2026},
  volume = {38},
  number = {3},
  pages = {20--28},
  doi = {10.52783/dxjb.v38.490}
}
Kostenlos starten →