Abstract—Workload prediction becomes a key major to improve the management of resources in cloud computing, recent studies have shown that predicting workload in data center positively affect the quality of service, elasticity, Service-Level Agreement (SLA) and power consuming, etc. In this paper, we design an efficient model to predict workload demand in dynamic cloud computing, which is a combination of Variational Mode Decomposition (VMD) and Temporal Convolutional Network (TCN). First, we use VMD to decompose workload extracted from history traces, into multiple cloud workload sequences. Second, the decomposed sequences are fed in a Temporal Convolutional Network. By using Alibaba workload dataset as a case study, the results show that the proposed model outperforms the compared deep learning based model in term of accuracy and achieve the state-of-art.
 

Index Terms—workload prediction, temporal convolutional networks, variational mode decomposition, dilated causal convolution, deep learning, cloud computing

Cite: Amine Mrhari and Youssef Hadi, "Workload Prediction Using VMD and TCN in Cloud Computing," Journal of Advances in Information Technology, Vol. 13, No. 3, pp. 284-289, June 2022.

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.