EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications

Thang Le Duc, Chanh Nguyen, Per-Olov Östberg

Electronics · 2025-08-21 · 14 (16) · 3333

DOI: 10.3390/electronics14163333 ↗

At a glance

Journal article in Electronics, published online on 2025-08-21. Written by Thang Le Duc and 2 co-authors. Cited 16 times so far (Crossref); 73 references. The full text is freely available (open access, CC BY 4.0). Funded by: EU Horizon 2020 programme, Reliable Capacity Provisioning and Enhanced Remediation for Distributed Cloud Applications (RECAP), Wallenberg AI, Autonomous Systems and Software Programme (WASP) through the project Tools for Autonomic Resource Management in the Cognitive Cloud Continuum (A….

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Accurate workload prediction is essential for proactive resource allocation in large-scale Content Delivery Networks (CDNs), where traffic patterns are highly dynamic and geographically distributed. This paper introduces a CDN-tailored prediction and autoscaling framework that integrates statistical and deep learning models within an adaptive feedback loop. The framework is evaluated using 18 months of real traffic traces from a production multi-tier CDN, capturing realistic workload seasonality, cache–tier interactions, and propagation delays. Unlike generic cloud-edge predictors, our design incorporates CDN-specific features and model-switching mechanisms to balance prediction accuracy with computational cost. Seasonal ARIMA (S-ARIMA), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Online Sequential Extreme Learning Machine (OS-ELM) are combined to support both short-horizon scaling and longer-term capacity planning. The predictions drive a queue-based resource-estimation model, enabling proactive cache–server scaling with low rejection rates. Experimental results demonstrate that the framework maintains high accuracy while reducing computational overhead through adaptive model selection. The proposed approach offers a practical, production-tested solution for predictive autoscaling in CDNs and can be extended to other latency-sensitive edge-cloud services with hierarchical architectures.

Funding

  • EU Horizon 2020 programme
  • Reliable Capacity Provisioning and Enhanced Remediation for Distributed Cloud Applications (RECAP)
  • Wallenberg AI, Autonomous Systems and Software Programme (WASP) through the project Tools for Autonomic Resource Management in the Cognitive Cloud Continuum (A…

Cite

APA

Duc, T. L., Nguyen, C., & Östberg, P. (2025). Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications. Electronics, 14(16), 3333. https://doi.org/10.3390/electronics14163333

Vancouver

Duc TL, Nguyen C, Östberg P. Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications. Electronics. 2025;14(16):3333. doi:10.3390/electronics14163333

BibTeX
@article{Duc2025,
  author = {Duc, Thang Le and Nguyen, Chanh and Östberg, Per-Olov},
  title = {Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {16},
  pages = {3333},
  doi = {10.3390/electronics14163333}
}
Start for free →