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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |