EUVIMEDEUVIMED entdecken
Crossref

MSCNet: Multi-Scale Network With Convolutions for Long-Term Cloud Workload Prediction

Feiyu Zhao, Weiwei Lin, Shengsheng Lin, Shaomin Tang, Keqin Li

IEEE Transactions on Services Computing · 2025-03 · 18 (2) · 969-982

DOI: 10.1109/tsc.2025.3536313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2025-03. Verfasst von Feiyu Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Guangdong Major Project of Basic and Applied Basic Research, National Natural Science Foundation of China, Guangzhou Development Zone Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate workload prediction is crucial for resource allocation and management in large-scale cloud data centers. While many approaches have been proposed, most existing methods are based on Recurrent Neural Networks (RNNs) or their variants, focusing on short-term cloud workload prediction without considering or identifying the long-term changes and different periodic patterns of cloud workloads. Due to variations in user demands or workload dynamics, cloud workloads that appear stable in the short term often exhibit distinct patterns in the long term. This can lead to a significant decline in prediction accuracy for existing methods when applied to long-term cloud workload forecasting. To address these challenges and overcome the limitations of current approaches, we propose a Multi-Scale Network with Convolutions (MSCNet) for accurate long-term cloud workload prediction. MSCNet employs multi-scale modeling of the original cloud workload to effectively extract multi-scale features and different periodic patterns, learning the long-term dependencies among the cloud workload. Our core component, the Multi-Scale Block, combines the Multi-Scale Patch Block, Transformer Encoder, and Multi-Scale Convolutions Block for comprehensive multi-scale learning. This enables MSCNet to adaptively learn both short-term and long-term features and patterns of cloud workloads, resulting in accurate long-term cloud workload predictions. Extensive experiments are conducted using real-world cloud workload data from Alibaba, Google, and Azure to validate the effectiveness of MSCNet. The experimental results demonstrate that MSCNet achieves accurate long-term cloud workload prediction with a computational complexity of $O(L^{2}d)$ O ( L 2 d ) , outperforming existing state-of-the-art methods.

Förderung

  • Guangdong Major Project of Basic and Applied Basic Research
  • National Natural Science Foundation of China
  • Guangzhou Development Zone Science and Technology
  • Major Key Project of PCL

Zitieren

APA

Zhao, F., Lin, W., Lin, S., Tang, S., & Li, K. (2025). MSCNet: Multi-Scale Network With Convolutions for Long-Term Cloud Workload Prediction. IEEE Transactions on Services Computing, 18(2), 969-982. https://doi.org/10.1109/tsc.2025.3536313

Vancouver

Zhao F, Lin W, Lin S, Tang S, Li K. MSCNet: Multi-Scale Network With Convolutions for Long-Term Cloud Workload Prediction. IEEE Transactions on Services Computing. 2025;18(2):969-982. doi:10.1109/tsc.2025.3536313

BibTeX
@article{Zhao2025,
  author = {Zhao, Feiyu and Lin, Weiwei and Lin, Shengsheng and Tang, Shaomin and Li, Keqin},
  title = {MSCNet: Multi-Scale Network With Convolutions for Long-Term Cloud Workload Prediction},
  journal = {IEEE Transactions on Services Computing},
  year = {2025},
  volume = {18},
  number = {2},
  pages = {969--982},
  doi = {10.1109/tsc.2025.3536313}
}
Kostenlos starten →