文献类型：期刊文献

英文题名：Artificial Intelligence-Based Temperature Twinning and Pre-Control for Data Center Airflow Organization

作者：Huang, Na[1,2];Li, Xiang[1,2];Xu, Quanming[3];Chen, Ronghao[4];Chen, Huidong[5];Chen, Aidong[1,2,6]

第一作者：黄娜

通讯作者：Chen, AD[1];Chen, AD[2];Chen, AD[3]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China;[3]Vertiv Tech Co Ltd, Shenzhen 518116, Peoples R China;[4]Peking Univ, Coll Environm & Energy, Shenzhen Grad Sch, Shenzhen 518055, Peoples R China;[5]Beijing Union Univ, Coll Urban Rail Transit & Logist, Beijing 100101, Peoples R China;[6]Beijing Union Univ, Res Ctr Multiintelligent Syst, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]corresponding author), Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China;[3]corresponding author), Beijing Union Univ, Res Ctr Multiintelligent Syst, Beijing 100101, Peoples R China.|[11417]北京联合大学;[1141739]北京联合大学机器人学院;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：2023

卷号：16

期号：16

外文期刊名：ENERGIES

收录：;EI(收录号：20233514642278);Scopus(收录号：2-s2.0-85168783070);WOS:【SCI-EXPANDED(收录号:WOS:001055902800001)】；

语种：英文

外文关键词：digital twin; temperature prediction; long and short-term memory networks; deep reinforcement learning

摘要：Green and low-carbon has become the main theme of global energy development. Data centers are the core of the digital age, carrying huge arithmetic demand. Data centers must implement green low-carbon energy efficiency management to improve energy efficiency, reduce energy waste and carbon emissions, and achieve sustainable development. As a result, an intelligent management strategy for dynamic energy efficiency of data center networks with Artificial Intelligence (AI) fitting control is proposed. Firstly, a Long Short-Term Memory (LSTM) network is used for long sequence trend prediction to predict the temperature of the data center in the next sequence using the temperature of the past 15 sequences and the power consumption of the equipment as parameters. Then, based on the prediction results, the intelligent air conditioning controller based on Deep Q-Network (DQN) is designed to update the parameters by using the gradient of double-Q network and error backpropagation, and the optimal control action is selected by using the e-greedy strategy to ensure that the prediction of the hotspot does not occur. Experiments show that the average absolute errors of temperature prediction for supply air, return air, cold aisle as well as hot aisle are 0.32 degrees C, 0.21 degrees C, 0.36 degrees C and 0.19 degrees C, respectively. The Power Usage Effectiveness (PUE) and Water Usage Effectiveness (WUE) decreased by an average of 2.6% and 2.5%, respectively. The method achieves the purpose of predicting future temperatures and intelligently controlling the output so that the data center can satisfy the premise of normal operation and thus achieve more efficient energy use.