Short-term Power Load Forecasting Method of Data Center Considering PUE
In order to accurately predict the short-term power load of data centers, a short-term load forecasting model based on long- and short-term memory neural networks is proposed, which effectively compensates for the shortcomings of feed forward neural networks that cannot process the correlation infor...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | Chinese |
| Published: |
Harbin University of Science and Technology Publications
2021-12-01
|
| Series: | Journal of Harbin University of Science and Technology |
| Subjects: | |
| Online Access: | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2028 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839606064946872320 |
|---|---|
| author | WU Jin-song ZHANG Shao feng XU Xiang-min LI Shu-tao HUANG Yong LIAO Xiao |
| author_facet | WU Jin-song ZHANG Shao feng XU Xiang-min LI Shu-tao HUANG Yong LIAO Xiao |
| author_sort | WU Jin-song |
| collection | DOAJ |
| description | In order to accurately predict the short-term power load of data centers, a short-term load forecasting model based on long- and short-term memory neural networks is proposed, which effectively compensates for the shortcomings of feed forward neural networks that cannot process the correlation information between sequences and traditional recurrent neural networks cannot remember long-term key information.Through analysis, it is concluded that the power usage effectiveness (PUE) value is correlated with the load. Therefore, the influence of PUE is considered in the prediction model, and the adaptive moment estimation algorithm is used for deep learning. Finally, by predicting the actual power load of the data center computer room of a certain electric power design institute in Guangzhou, introducing the PUE value into the model can effectively improve the accuracy of the short-term load forecast of the data center. |
| format | Article |
| id | doaj-art-38966c2cf6f44f2bb4373b8b51dd2abf |
| institution | Matheson Library |
| issn | 1007-2683 |
| language | zho |
| publishDate | 2021-12-01 |
| publisher | Harbin University of Science and Technology Publications |
| record_format | Article |
| series | Journal of Harbin University of Science and Technology |
| spelling | doaj-art-38966c2cf6f44f2bb4373b8b51dd2abf2025-08-01T11:04:25ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832021-12-0126061910.15938/j.jhust.2021.06.001Short-term Power Load Forecasting Method of Data Center Considering PUEWU Jin-song0ZHANG Shao feng1XU Xiang-min2LI Shu-tao3HUANG Yong4LIAO Xiao5South China University of Technology, Guangzhou 510640, China;China Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, ChinaChina Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, ChinaSouth China University of Technology, Guangzhou 510640, ChinaSouth China University of Technology, Guangzhou 510640, China;China Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, ChinaChina Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, ChinaChina Energy Engineering Group Guangdong Electric Power Design Institute Co., Ltd., Guangzhou 510663, ChinaIn order to accurately predict the short-term power load of data centers, a short-term load forecasting model based on long- and short-term memory neural networks is proposed, which effectively compensates for the shortcomings of feed forward neural networks that cannot process the correlation information between sequences and traditional recurrent neural networks cannot remember long-term key information.Through analysis, it is concluded that the power usage effectiveness (PUE) value is correlated with the load. Therefore, the influence of PUE is considered in the prediction model, and the adaptive moment estimation algorithm is used for deep learning. Finally, by predicting the actual power load of the data center computer room of a certain electric power design institute in Guangzhou, introducing the PUE value into the model can effectively improve the accuracy of the short-term load forecast of the data center.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2028load forecastingdata centerdeep learningpower usage effectivenesslong and short-term memory |
| spellingShingle | WU Jin-song ZHANG Shao feng XU Xiang-min LI Shu-tao HUANG Yong LIAO Xiao Short-term Power Load Forecasting Method of Data Center Considering PUE Journal of Harbin University of Science and Technology load forecasting data center deep learning power usage effectiveness long and short-term memory |
| title | Short-term Power Load Forecasting Method of Data Center Considering PUE |
| title_full | Short-term Power Load Forecasting Method of Data Center Considering PUE |
| title_fullStr | Short-term Power Load Forecasting Method of Data Center Considering PUE |
| title_full_unstemmed | Short-term Power Load Forecasting Method of Data Center Considering PUE |
| title_short | Short-term Power Load Forecasting Method of Data Center Considering PUE |
| title_sort | short term power load forecasting method of data center considering pue |
| topic | load forecasting data center deep learning power usage effectiveness long and short-term memory |
| url | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2028 |
| work_keys_str_mv | AT wujinsong shorttermpowerloadforecastingmethodofdatacenterconsideringpue AT zhangshaofeng shorttermpowerloadforecastingmethodofdatacenterconsideringpue AT xuxiangmin shorttermpowerloadforecastingmethodofdatacenterconsideringpue AT lishutao shorttermpowerloadforecastingmethodofdatacenterconsideringpue AT huangyong shorttermpowerloadforecastingmethodofdatacenterconsideringpue AT liaoxiao shorttermpowerloadforecastingmethodofdatacenterconsideringpue |