Data driven battery anomaly detection based on shape based clustering for the data centers class

被引:39
作者
Haider, Syed Naeem [1 ]
Zhao, Qianchuan [1 ]
Li, Xueliang [1 ]
机构
[1] Tsinghua Univ, Dept Automat & BNRist, Ctr Intelligent & Networked Syst CFINS, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
Data centres; Data driven model; K shape-based clustering; Anomaly detection; Battery health; LEAD-ACID-BATTERIES; LITHIUM-ION BATTERIES; STATE-OF-HEALTH; TEMPERATURE; RESISTANCE; ALGORITHM; SYSTEMS; STORAGE;
D O I
10.1016/j.est.2020.101479
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Batteries are a significant part of data centers, which ensure the uninterrupted working of a data center. Using online measurement to find out odd batteries in data centers is challenging due to lack of training samples since there are only a very few full charging-discharging cycles during the lifetime of batteries. In this paper, a new battery anomaly detection method based on time series clustering is proposed. This method uses only battery operating data and does not depend on offline testing data, thus provides a way to improve the maintenance efficiency and lessen batteries operating risks in data centers. Effectiveness of the proposed method is demonstrated and confirmed by a case study for 40 batteries in an existent data center.
引用
收藏
页数:10
相关论文
共 39 条
[1]   Time-series clustering - A decade review [J].
Aghabozorgi, Saeed ;
Shirkhorshidi, Ali Seyed ;
Teh Ying Wah .
INFORMATION SYSTEMS, 2015, 53 :16-38
[2]  
[Anonymous], [No title captured]
[3]   Impedance spectra of enhanced flooded batteries for micro-hybrid applications [J].
Boerger, Alexander ;
Ebner, Ellen ;
Calles, Simon ;
Budde-Meiwes, Heide ;
Schulte, Dominik ;
Kowal, Julia ;
Sauer, Dirk Uwe .
JOURNAL OF ENERGY STORAGE, 2017, 13 :457-462
[4]   A new state-of-health estimation method for lithium-ion batteries through the intrinsic relationship between ohmic internal resistance and capacity [J].
Chen, Lin ;
Lu, Zhiqiang ;
Lin, Weilong ;
Li, Junzi ;
Pan, Haihong .
MEASUREMENT, 2018, 116 :586-595
[5]   Data Center Energy Consumption Modeling: A Survey [J].
Dayarathna, Miyuru ;
Wen, Yonggang ;
Fan, Rui .
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2016, 18 (01) :732-794
[6]   An examination of indexes for determining the number of clusters in binary data sets [J].
Dimitriadou, E ;
Dolnicar, S ;
Weingessel, A .
PSYCHOMETRIKA, 2002, 67 (01) :137-159
[7]  
Hasani Z, 2017, MEDD C EMBED COMPUT, P449
[8]  
Hlavac MJ, 1995, INTELEC 95 - SEVENTEENTH INTERNATIONAL TELECOMMUNICATIONS ENERGY CONFERENCE, P284, DOI 10.1109/INTLEC.1995.498966
[9]   Fault prognosis of battery system based on accurate voltage abnormity prognosis using long short-term memory neural networks [J].
Hong, Jichao ;
Wang, Zhenpo ;
Yao, Yongtao .
APPLIED ENERGY, 2019, 251
[10]   Improving particle size of BaSO4 with a unique glycerol base method and its impact on the negative active material of the lead-acid battery [J].
Hosseini, Shadi ;
Farhadi, Khalil ;
Banisaeid, Sepideh .
JOURNAL OF ENERGY STORAGE, 2019, 21 :139-148