Research on energy efficiency optimization of data centers based on DC-Bi-LSTM network integration algorithm

OUYANG Shujia; JIA Tao; ZHANG Yaxiong; CHEN Xuezhen; LI Yunshuang

doi:10.11959/j.issn.1000-0801.2025239

您当前的位置：

首页 >

文章列表页 >

Research on energy efficiency optimization of data centers based on DC-Bi-LSTM network integration algorithm

Research and Development | 更新时间：2026-01-20

- Research on energy efficiency optimization of data centers based on DC-Bi-LSTM network integration algorithm
- Telecommunications Science Vol. 41, Issue 11, Pages: 163-174(2025)
- 作者机构：
  
  1.国家电网有限公司信息通信中心（大数据中心），北京 100761
  2.北京中电飞华通信有限公司，北京 100036
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2025239
  CLC： TN911.73;TP308
- Received：01 July 2025，
  
  Revised：2025-10-11，
  
  Accepted：15 October 2025，
  
  Published：20 November 2025
- 稿件说明：
移动端阅览
欧阳述嘉,贾涛,张亚雄等.基于DC-Bi-LSTM网络集成算法的数据中心能效优化研究[J].电信科学,2025,41(11):163-174.

OUYANG Shujia,JIA Tao,ZHANG Yaxiong,et al.Research on energy efficiency optimization of data centers based on DC-Bi-LSTM network integration algorithm[J].Telecommunications Science,2025,41(11):163-174.
欧阳述嘉,贾涛,张亚雄等.基于DC-Bi-LSTM网络集成算法的数据中心能效优化研究[J].电信科学,2025,41(11):163-174. DOI： 10.11959/j.issn.1000-0801.2025239.

OUYANG Shujia,JIA Tao,ZHANG Yaxiong,et al.Research on energy efficiency optimization of data centers based on DC-Bi-LSTM network integration algorithm[J].Telecommunications Science,2025,41(11):163-174. DOI： 10.11959/j.issn.1000-0801.2025239.

摘要

随着云计算与大数据技术的普及，数据中心能耗问题日益凸显，如何通过智能算法实现能效优化成为绿色计算领域的关键课题。传统机器学习模型难以有效捕捉数据中心能耗数据的时序依赖性与多维度耦合特征，导致能效优化精度不足。为此，提出一种基于空洞卷积优化的双向长短期记忆（dilated convolution optimized bi-directional long short-term memory，DC-Bi-LSTM）网络集成算法，通过融合双向循环神经网络的时序特征双向捕捉能力与集成学习的误差修正机制，构建高精度的能耗预测与能效优化模型。实验结果表明，相较于目前最优的预测方法，新算法在平均绝对误差（mean absolute error，MAE）上降低了0.22，在平均绝对百分比误差（mean absolute percentage error，MAPE）上降低了0.43%，在均方根误差（root mean squared error，RMSE）上降低了0.23，DC-Bi-LSTM网络集成算法能够有效克服预测中的数据噪声和不确定性干扰，提高了数据中心能效预测的效果。

Abstract

With the popularization of cloud computing and big data technology

the energy consumption problem of data centers has become increasingly prominent. How to achieve energy efficiency optimization through intelligent algorithms has become a key issue in the field of green computing. Traditional machine learning models are difficult to effectively capture the temporal dependencies and multidimensional coupling characteristics of energy consumption data in data centers

resulting in insufficient accuracy in energy efficiency optimization. To this end

an ensemble algorithm based on dilated convolution optimized bi-directional long short-term memory (DC-Bi-LSTM) network was proposed

which combined the bi-directional capture ability of recurrent neural networks with the error correction mechanism of ensemble learning to construct high-precision energy consumption prediction and energy efficiency optimization models. The experimental results show that compared to the current best prediction methods

the DC-Bi-LSTM network integrated algorithm reduces mean absolute error (MAE) by 0.22

mean absolute percentage error(MAPE) by 0.43%

and root mean squared error (RMSE) by 0.23. It can effectively overcome the interference of data noise and uncertainty in prediction and improve the effectiveness from data center energy efficiency prediction.

关键词

Keywords

references

周峰 , 王芮敏 , 马国远 , 等 . 我国数据中心碳中和路径情景分析 [J ] . 制冷学报 , 2025 , 46 ( 1 ): 79 - 85 .

ZHOU F , WANG R M , MA G Y , et al . Scenario analysis of data centers in China under carbon neutrality target [J ] . Journal of Refrigeration , 2025 , 46 ( 1 ): 79 - 85 .

陈心拓 , 周黎旸 , 张程宾 , 等 . 绿色高能效数据中心散热冷却技术研究现状及发展趋势 [J ] . 中国工程科学 , 2022 , 24 ( 4 ): 94 - 104 .

CHEN X T , ZHOU L Y , ZHANG C B , et al . Research status and future development of cooling technologies for green and energy-efficient data centers [J ] . Strategic Study of CAE , 2022 , 24 ( 4 ): 94 - 104 .

王博 , 郭焱华 , 邵双全 , 等 . 数据中心冷却系统相关能效评价指标综述 [J ] . 制冷学报 , 2023 , 44 ( 2 ): 18 - 27 .

WANG B , GUO Y H , SHAO S Q , et al . Review of energy efficiency evaluation indexes related to data center cooling systems [J ] . Journal of Refrigeration , 2023 , 44 ( 2 ): 18 - 27 .

魏东 , 贾宇辰 , 韩少然 . 数据中心制冷系统强化学习控制 [J ] . 计算机工程与科学 , 2025 , 47 ( 3 ): 422 - 433 .

WEI D , JIA Y C , HAN S R . Reinforcement learning control for data center refrigeration systems [J ] . Computer Engineering & Science , 2025 , 47 ( 3 ): 422 - 433 .

李庆华 , 冉泳屹 , 刘启晨 , 等 . 数据中心冷热电联产系统的前摄式智能节能优化算法 [J ] . 智能系统学报 , 2025 , 20 ( 1 ): 139 - 149 .

LI Q H , RAN Y Y , LIU Q C , et al . Proactive intelligent energy-saving optimization algorithm for data center CCHP system [J ] . CAAI Transactions on Intelligent Systems , 2025 , 20 ( 1 ): 139 - 149 .

张宇 , 李敏霞 , 李君 , 等 . 面向数据中心液冷装置余热回收的卡诺电池储能系统可行性分析 [J ] . 储能科学与技术 , 2024 , 13 ( 11 ): 3921 - 3929 .

ZHANG Y , LI M X , LI J , et al . Feasibility analysis of a Carnot battery energy storage system for waste heat recovery of liquid cooling units in data centers [J ] . Energy Storage Science and Technology , 2024 , 13 ( 11 ): 3921 - 3929 .

袁溪 , 张邵欣 , 张超 , 等 . 基于Transformer的电动汽车充电站能耗预测研究 [J ] . 计算机技术与发展 , 2025 , 35 ( 2 ): 213 - 220 .

YUAN X , ZHANG S X , ZHANG C , et al . Research on electric vehicle charging station energy consumption prediction based on Transformer [J ] . Computer Technology and Development , 2025 , 35 ( 2 ): 213 - 220 .

刘芊 , 周泉 , 叶晓江 . 基于深度学习的数据中心负载能耗预测模型研究 [J ] . 节能 , 2024 , 43 ( 11 ): 98 - 100 .

LIU Q , ZHOU Q , YE X J . Research on data center load energy consumption forecasting models based on deep learning [J ] . Energy Conservation , 2024 , 43 ( 11 ): 98 - 100 .

张婉婷 , 郑晓耘 , 王鹏飞 , 等 . 联合冷却系统的分布式绿色数据中心能量管理 [J ] . 东华大学学报(自然科学版) , 2024 , 50 ( 3 ): 163 - 171 .

ZHANG W T , ZHENG X Y , WANG P F , et al . Distributed green data center energy management with combined cooling system [J ] . Journal of Donghua University (Natural Science Edition) , 2024 , 50 ( 3 ): 163 - 171 .

王辉东 , 高晋坤 , 黄佳斌 , 等 . 考虑数据中心负载灵活性的电力系统运行可靠性评估方法 [J ] . 电力系统保护与控制 , 2023 , 51 ( 21 ): 96 - 105 .

WANG H D , GAO J K , HUANG J B , et al . Power system operational reliability evaluation method considering data center load flexibility [J ] . Power System Protection and Control , 2023 , 51 ( 21 ): 96 - 105 .

王丽莉 , 赵飞龙 . 基于风电升压站的低PUE数据中心实现 [J ] . 电子测量技术 , 2023 , 46 ( 18 ): 16 - 22 .

WANG L L , ZHAO F L . Implementation of low PUE data center based on offshore substation [J ] . Electronic Measurement Technology , 2023 , 46 ( 18 ): 16 - 22 .

高胜强 , 张琳 , 王海鹏 , 等 . 计及CCM和改进GRA的PSO-BiLSTM光伏出力预测模型 [J ] . 电源技术 , 2025 , 49 ( 4 ): 869 - 882 .

GAO S Q , ZHANG L , WANG H P , et al . PSO-BiLSTM PV output prediction model with CCM and improved GRA [J ] . Chinese Journal of Power Sources , 2025 , 49 ( 4 ): 869 - 882 .

胡平生 , 吴泉军 . 基于变分模态分解和BiLSTM-ATT的锂电池健康状态估计模型 [J ] . 科学技术与工程 , 2025 , 25 ( 11 ): 4598 - 4604 .

HU P S , WU Q J . Estimation model for state of health of lithium-ion battery based on VMD and BiLSTM-ATT [J ] . Science Technology and Engineering , 2025 , 25 ( 11 ): 4598 - 4604 .

程光 , 李沛霖 . 基于MSE改进BiLSTM网络算法的工业互联网异常流量时空融合检测 [J ] . 吉林大学学报(工学版) , 2025 , 55 ( 4 ): 1406 - 1411 .

CHENG G , LI P L . Spatio temporal fusion detection of abnormal traffic in industrial Internet based on MSE improved BiLSTM network algorithm [J ] . Journal of Jilin University (Engineering and Technology Edition) , 2025 , 55 ( 4 ): 1406 - 1411 .

高芷蓉 , 杨杉 , 喻希 , 等 . 基于CNN-BiLSTM-Attention的电力系统虚假数据注入攻击检测 [J ] . 智慧电力 , 2025 , 53 ( 4 ): 103 - 111 .

GAO Z R , YANG S , YU X , et al . False data injection attack detection in power systems based on CNN-BiLSTM-Attention [J ] . Smart Power , 2025 , 53 ( 4 ): 103 - 111 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

AI-enabled 5G energy-saving technology

Analysis of value-added services of power communication network in energy internet

SDN solutions for cloud data center

Key point of NFV hardware resource pool planning and construction

Research on the selection of grid data storage technology

Related Author

Lika LI

Weiye MENG

Yu ZENG

Dan XU

Qi SHAO

Hong ZHU

Cui ZHONG

Lei WANG

Related Institution

Pudong Power Supply Company Under Shanghai Municipal Electric Power Corporation

Shanghai Zhongxing Power Construction Development Co.,Ltd.

Guangzhou Research Institute of China Telecom Co., Ltd.

Guangdong Branch of China Telecom Co., Ltd.

Zhongxing Telecommunication Equipment Corporation Central R＆D

⁰