Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage

Addressing the critical need for enhanced power usage effectiveness in data centers (DCs), this study pioneers an improved convolutional long short-term memory with deep neural network (CLDNN) model, enriched with attention mechanisms for precise DC performance prediction. We rigorously evaluate our...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang-Cheng Shih, Sathesh Tamilarasan, Chin-Sheng Chen, Omid Ali Zargar, Yean-Der Kuan
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:International Journal of Thermofluids
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666202724003070
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846125171187908608
author Yang-Cheng Shih
Sathesh Tamilarasan
Chin-Sheng Chen
Omid Ali Zargar
Yean-Der Kuan
author_facet Yang-Cheng Shih
Sathesh Tamilarasan
Chin-Sheng Chen
Omid Ali Zargar
Yean-Der Kuan
author_sort Yang-Cheng Shih
collection DOAJ
description Addressing the critical need for enhanced power usage effectiveness in data centers (DCs), this study pioneers an improved convolutional long short-term memory with deep neural network (CLDNN) model, enriched with attention mechanisms for precise DC performance prediction. We rigorously evaluate our model against leading architectures – long short-term memory (LSTM), attention-based (att-LSTM), convolutional LSTM (CNN-LSTM), gated recurrent unit (GRU), and CNN-GRU – to affirm its superiority in predictive accuracy and robustness. The integration of convolutional layers processes hourly data inputs efficiently, reducing complexity and improving pattern detection. A subsequent flattening layer optimizes accuracy, while a dual-layered LSTM and a deep neural network delve into frequency, temporal dynamics, and complex data relationships. Incorporating an attention mechanism into the att-CLDNN model has revolutionized predictive analytics in DC energy management, significantly enhancing accuracy by highlighting crucial data interdependencies. This model's unparalleled precision, evidenced by achieving the lowest Mean Squared Error (MSE) of 0.000179, the minimum Mean Absolute Error (MAE) of 0.01048, and the highest R2 Score of 0.977031, underscores its effectiveness. Crucially, this breakthrough fosters sustainability in energy management, promoting greener DC operations through precise energy use predictions, leading to substantial energy savings and reduced carbon emissions, in alignment with global sustainability objectives.
format Article
id doaj-art-769bbfd7e1a44168bae679af65ada56a
institution Kabale University
issn 2666-2027
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series International Journal of Thermofluids
spelling doaj-art-769bbfd7e1a44168bae679af65ada56a2024-12-13T11:04:07ZengElsevierInternational Journal of Thermofluids2666-20272024-11-0124100866Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usageYang-Cheng Shih0Sathesh Tamilarasan1Chin-Sheng Chen2Omid Ali Zargar3Yean-Der Kuan4Department of Energy and Refrigerating Air-Conditioning Engineering, National Taipei University of Technology, 1, Sec. 3, Zhongxiao E. Rd., Taipei, 10608, Taiwan; Research Center of Energy Conservation for New Generation of Residential, Commercial, and Industrial Sectors, National Taipei University of Technology, 1, Sec. 3, Zhongxiao E. Rd., Taipei, 10608, TaiwanDepartment of Refrigeration, Air Conditioning and Energy Engineering, National Chin-Yi University of Technology, 57, Sec.2, Zhongshan Rd, Taiping Dist., Taichung City, 411030, Taiwan; Corresponding author at: Department of Refrigeration, Air Conditioning and Energy Engineering, National Chin-Yi University of Technology, No.57, Sec.2, Zhongshan Rd., Taiping Dist., Taichung, 411030, Taiwan.Graduate Institute of Automation Technology, National Taipei University of Technology, 1, Sec. 3, Zhongxiao E. Rd., Taipei, 10608, TaiwanDepartment of Mechanical Engineering, National Chin-Yi University of Technology, 57, Sec.2, Zhongshan Rd, Taiping Dist., Taichung City, 411030, TaiwanDepartment of Refrigeration, Air Conditioning and Energy Engineering, National Chin-Yi University of Technology, 57, Sec.2, Zhongshan Rd, Taiping Dist., Taichung City, 411030, TaiwanAddressing the critical need for enhanced power usage effectiveness in data centers (DCs), this study pioneers an improved convolutional long short-term memory with deep neural network (CLDNN) model, enriched with attention mechanisms for precise DC performance prediction. We rigorously evaluate our model against leading architectures – long short-term memory (LSTM), attention-based (att-LSTM), convolutional LSTM (CNN-LSTM), gated recurrent unit (GRU), and CNN-GRU – to affirm its superiority in predictive accuracy and robustness. The integration of convolutional layers processes hourly data inputs efficiently, reducing complexity and improving pattern detection. A subsequent flattening layer optimizes accuracy, while a dual-layered LSTM and a deep neural network delve into frequency, temporal dynamics, and complex data relationships. Incorporating an attention mechanism into the att-CLDNN model has revolutionized predictive analytics in DC energy management, significantly enhancing accuracy by highlighting crucial data interdependencies. This model's unparalleled precision, evidenced by achieving the lowest Mean Squared Error (MSE) of 0.000179, the minimum Mean Absolute Error (MAE) of 0.01048, and the highest R2 Score of 0.977031, underscores its effectiveness. Crucially, this breakthrough fosters sustainability in energy management, promoting greener DC operations through precise energy use predictions, leading to substantial energy savings and reduced carbon emissions, in alignment with global sustainability objectives.http://www.sciencedirect.com/science/article/pii/S2666202724003070Data centerPower usage effectivenessConvolutional long short-term memoryDeep neural networkIntegrated modelAttention mechanism
spellingShingle Yang-Cheng Shih
Sathesh Tamilarasan
Chin-Sheng Chen
Omid Ali Zargar
Yean-Der Kuan
Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage
International Journal of Thermofluids
Data center
Power usage effectiveness
Convolutional long short-term memory
Deep neural network
Integrated model
Attention mechanism
title Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage
title_full Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage
title_fullStr Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage
title_full_unstemmed Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage
title_short Attention-based integrated deep neural network architecture for predicting the effectiveness of data center power usage
title_sort attention based integrated deep neural network architecture for predicting the effectiveness of data center power usage
topic Data center
Power usage effectiveness
Convolutional long short-term memory
Deep neural network
Integrated model
Attention mechanism
url http://www.sciencedirect.com/science/article/pii/S2666202724003070
work_keys_str_mv AT yangchengshih attentionbasedintegrateddeepneuralnetworkarchitectureforpredictingtheeffectivenessofdatacenterpowerusage
AT satheshtamilarasan attentionbasedintegrateddeepneuralnetworkarchitectureforpredictingtheeffectivenessofdatacenterpowerusage
AT chinshengchen attentionbasedintegrateddeepneuralnetworkarchitectureforpredictingtheeffectivenessofdatacenterpowerusage
AT omidalizargar attentionbasedintegrateddeepneuralnetworkarchitectureforpredictingtheeffectivenessofdatacenterpowerusage
AT yeanderkuan attentionbasedintegrateddeepneuralnetworkarchitectureforpredictingtheeffectivenessofdatacenterpowerusage