Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization
In recent years, large data centers have increased significantly as data usage has increased because of digital innovations. However, data centers are 24-hour operation facilities that consume large amounts of power, thus causing environmental problems. Recently, research has been conducted using de...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10242069/ |
| _version_ | 1827818091123310592 |
|---|---|
| author | Sang-Gyun Ma Dong-Gun Lee Yeong-Seok Seo |
| author_facet | Sang-Gyun Ma Dong-Gun Lee Yeong-Seok Seo |
| author_sort | Sang-Gyun Ma |
| collection | DOAJ |
| description | In recent years, large data centers have increased significantly as data usage has increased because of digital innovations. However, data centers are 24-hour operation facilities that consume large amounts of power, thus causing environmental problems. Recently, research has been conducted using deep learning methods from various perspectives to predict traffic and reduce power consumption in data centers and servers. However, the traffic processed by servers is highly variable, which is a factor that makes server management difficult. Thus, the traffic processed by servers is irregular, and more research is required on dynamic server management. This study proposes Customized Dynamic Server Management (CDSM) based on Long-Term Short Memory (LSTM), a neural network that is effective in predicting time-series data, to address the aforementioned problem. The proposed method can more effectively save the power used by servers, thereby managing servers more reliably and efficiently than before in the current operating environment. To validate the proposed model, we collected the traffic data at six Wikipedia data centers. We then analyzed the relationship between each traffic data using statistical analysis and conducted experiments. Furthermore, we calculated the server power consumption based on the actual power consumption according to the CPU usage of different servers provided by SPECpower, a benchmark for evaluating server power efficiency. Additionally, we calculated the amount of computation required for the program and deep learning model of the proposed. Based on this, practical results were derived considering the trade-off between the server’s power saving and computation performance. The experiment results showed that the server power consumption could be reduced by an average of 68% and a minimum of 32% with CDSM compared to without. This shows that CDSM can effectively reduce server power, hence saving energy in data centers and contributing to carbon neutrality. |
| first_indexed | 2024-03-12T00:43:03Z |
| format | Article |
| id | doaj.art-483bb24f66f14c2e8e10ac0cc780adcb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:43:03Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-483bb24f66f14c2e8e10ac0cc780adcb2023-09-14T23:01:32ZengIEEEIEEE Access2169-35362023-01-0111979619797710.1109/ACCESS.2023.331255410242069Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency OptimizationSang-Gyun Ma0https://orcid.org/0000-0003-0243-7743Dong-Gun Lee1https://orcid.org/0000-0001-6792-4572Yeong-Seok Seo2https://orcid.org/0000-0002-5319-7674Department of Computer Engineering, Yeungnam University, Gyeongsan, Republic of KoreaDepartment of Computer Engineering, Yeungnam University, Gyeongsan, Republic of KoreaDepartment of Computer Engineering, Yeungnam University, Gyeongsan, Republic of KoreaIn recent years, large data centers have increased significantly as data usage has increased because of digital innovations. However, data centers are 24-hour operation facilities that consume large amounts of power, thus causing environmental problems. Recently, research has been conducted using deep learning methods from various perspectives to predict traffic and reduce power consumption in data centers and servers. However, the traffic processed by servers is highly variable, which is a factor that makes server management difficult. Thus, the traffic processed by servers is irregular, and more research is required on dynamic server management. This study proposes Customized Dynamic Server Management (CDSM) based on Long-Term Short Memory (LSTM), a neural network that is effective in predicting time-series data, to address the aforementioned problem. The proposed method can more effectively save the power used by servers, thereby managing servers more reliably and efficiently than before in the current operating environment. To validate the proposed model, we collected the traffic data at six Wikipedia data centers. We then analyzed the relationship between each traffic data using statistical analysis and conducted experiments. Furthermore, we calculated the server power consumption based on the actual power consumption according to the CPU usage of different servers provided by SPECpower, a benchmark for evaluating server power efficiency. Additionally, we calculated the amount of computation required for the program and deep learning model of the proposed. Based on this, practical results were derived considering the trade-off between the server’s power saving and computation performance. The experiment results showed that the server power consumption could be reduced by an average of 68% and a minimum of 32% with CDSM compared to without. This shows that CDSM can effectively reduce server power, hence saving energy in data centers and contributing to carbon neutrality.https://ieeexplore.ieee.org/document/10242069/Data centerdeep learningcarbon neutralizationquality of serviceserver managementtraffic prediction |
| spellingShingle | Sang-Gyun Ma Dong-Gun Lee Yeong-Seok Seo Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization IEEE Access Data center deep learning carbon neutralization quality of service server management traffic prediction |
| title | Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization |
| title_full | Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization |
| title_fullStr | Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization |
| title_full_unstemmed | Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization |
| title_short | Flexible Carbon Neutralization Strategy: Customized Dynamic Server Management for Energy Efficiency Optimization |
| title_sort | flexible carbon neutralization strategy customized dynamic server management for energy efficiency optimization |
| topic | Data center deep learning carbon neutralization quality of service server management traffic prediction |
| url | https://ieeexplore.ieee.org/document/10242069/ |
| work_keys_str_mv | AT sanggyunma flexiblecarbonneutralizationstrategycustomizeddynamicservermanagementforenergyefficiencyoptimization AT donggunlee flexiblecarbonneutralizationstrategycustomizeddynamicservermanagementforenergyefficiencyoptimization AT yeongseokseo flexiblecarbonneutralizationstrategycustomizeddynamicservermanagementforenergyefficiencyoptimization |