Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning

Workload prediction is one of the most basic requirements in developing cost and energy-efficient Cloud Data Centers (CDCs). Most traditional approaches have suffered from noise and failed to capture the complex dynamic patterns in workload data, reducing their accuracy. To improve this, we introduc...

Full description

Saved in:
Bibliographic Details
Main Authors: Dalal Alqahtani, Hamidreza Imani, Tarek El-Ghazawi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10960295/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699956007370752
author Dalal Alqahtani
Hamidreza Imani
Tarek El-Ghazawi
author_facet Dalal Alqahtani
Hamidreza Imani
Tarek El-Ghazawi
author_sort Dalal Alqahtani
collection DOAJ
description Workload prediction is one of the most basic requirements in developing cost and energy-efficient Cloud Data Centers (CDCs). Most traditional approaches have suffered from noise and failed to capture the complex dynamic patterns in workload data, reducing their accuracy. To improve this, we introduce CVCBM which blends signal processing techniques Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD) with advanced deep learning models like Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. CVCBM utilizes a hierarchical two-stage decomposition process, beginning with CEEMDAN. We use the capability of CEEMDAN for denoising by additive white noise to clean the noisy workload data and further decompose it into several Intrinsic Mode Functions (IMFs), ranging from high to low frequencies. Then, we propose a partitional clustering approach based on Sample Entropy (SE) to select components of similar complexity to increase the effectiveness of the second-stage denoising. After that, VMD is a method based on the center frequency applied to decompose further the high-frequency components, which may contain fluctuations that obscure underlying trends, thus enhancing the model’s overall accuracy. A novel hybrid model is utilized to forecast future workloads, incorporating two sets of three distinct parallel Conv1D layers with varying kernel sizes. These layers extract patterns from the input data, capturing short-term, medium-term, and long-term workload information, allowing the model to learn variations at different scales. Following this, Bi-LSTM layers capture the temporal dependencies within the patterns identified by the Conv1D layers. Extensive experiments on various real-world datasets from Google and Alibaba show that CVCBM significantly outperforms the other methods, which makes it a solution for future workload prediction in cloud data centers.
format Article
id doaj-art-08eeb6c4666343448d42d005ad6b9d69
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-08eeb6c4666343448d42d005ad6b9d692025-08-20T03:18:26ZengIEEEIEEE Access2169-35362025-01-0113641156413210.1109/ACCESS.2025.355874310960295Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep LearningDalal Alqahtani0https://orcid.org/0009-0002-1296-0028Hamidreza Imani1https://orcid.org/0000-0002-8938-3284Tarek El-Ghazawi2Department of Electrical and Computer Engineering, The George Washington University, Washington, DC, USADepartment of Electrical and Computer Engineering, The George Washington University, Washington, DC, USADepartment of Electrical and Computer Engineering, The George Washington University, Washington, DC, USAWorkload prediction is one of the most basic requirements in developing cost and energy-efficient Cloud Data Centers (CDCs). Most traditional approaches have suffered from noise and failed to capture the complex dynamic patterns in workload data, reducing their accuracy. To improve this, we introduce CVCBM which blends signal processing techniques Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD) with advanced deep learning models like Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. CVCBM utilizes a hierarchical two-stage decomposition process, beginning with CEEMDAN. We use the capability of CEEMDAN for denoising by additive white noise to clean the noisy workload data and further decompose it into several Intrinsic Mode Functions (IMFs), ranging from high to low frequencies. Then, we propose a partitional clustering approach based on Sample Entropy (SE) to select components of similar complexity to increase the effectiveness of the second-stage denoising. After that, VMD is a method based on the center frequency applied to decompose further the high-frequency components, which may contain fluctuations that obscure underlying trends, thus enhancing the model’s overall accuracy. A novel hybrid model is utilized to forecast future workloads, incorporating two sets of three distinct parallel Conv1D layers with varying kernel sizes. These layers extract patterns from the input data, capturing short-term, medium-term, and long-term workload information, allowing the model to learn variations at different scales. Following this, Bi-LSTM layers capture the temporal dependencies within the patterns identified by the Conv1D layers. Extensive experiments on various real-world datasets from Google and Alibaba show that CVCBM significantly outperforms the other methods, which makes it a solution for future workload prediction in cloud data centers.https://ieeexplore.ieee.org/document/10960295/Cloud data centerworkload predictiondeep learninghybrid predictiondata decomposition
spellingShingle Dalal Alqahtani
Hamidreza Imani
Tarek El-Ghazawi
Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning
IEEE Access
Cloud data center
workload prediction
deep learning
hybrid prediction
data decomposition
title Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning
title_full Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning
title_fullStr Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning
title_full_unstemmed Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning
title_short Enhanced Workload Prediction in Data Centers Using Two-Stage Decomposition and Hybrid Parallel Deep Learning
title_sort enhanced workload prediction in data centers using two stage decomposition and hybrid parallel deep learning
topic Cloud data center
workload prediction
deep learning
hybrid prediction
data decomposition
url https://ieeexplore.ieee.org/document/10960295/
work_keys_str_mv AT dalalalqahtani enhancedworkloadpredictionindatacentersusingtwostagedecompositionandhybridparalleldeeplearning
AT hamidrezaimani enhancedworkloadpredictionindatacentersusingtwostagedecompositionandhybridparalleldeeplearning
AT tarekelghazawi enhancedworkloadpredictionindatacentersusingtwostagedecompositionandhybridparalleldeeplearning