A Framework for Tunable Anomaly Detection

被引:5
作者
Alam, Md Rakibul [1 ]
Gerostathopoulos, Ilias [1 ]
Prehofer, Christian [1 ,4 ]
Attanasi, Alessandro [2 ]
Bures, Tomas [3 ]
机构
[1] Tech Univ Munich, Munich, Germany
[2] PTV SISTeMA, Rome, Italy
[3] Charles Univ Prague, Prague, Czech Republic
[4] DENSO Automot Deutschland GmbH, Eching, Germany
来源
2019 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE (ICSA) | 2019年
关键词
anomaly detection; data-driven decisions; data anomalies; experimentation; self-adaptive systems;
D O I
10.1109/ICSA.2019.00029
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
As software architecture practice relies more and more on runtime data to inform decisions in continuous experimentation and self-adaptation, it is increasingly important to consider the quality of the data used as input to the different decision-making and prediction algorithms. One issue in data-driven decisions is that real-life data coming from running systems can contain invalid or wrong values which can bias the result of data analysis. Data-driven decision-making should therefore comprise detection and handling of data anomalies as an integral part of the process. However, currently, anomaly detection is either absent in runtime decision-making approaches for continuous experimentation and self-adaptation or difficult to tailor to domain-specific needs. In this paper, we contribute by proposing a framework that simplifies the detection of data anomalies in timeseries-outputs of running systems. The framework is generic, since it can be employed in different domains, and tunable, since it uses expert user input in tailoring anomaly detection to the needs and assumptions of each domain. We evaluate the feasibility of the framework by successfully applying it to detecting anomalies in a real-life timeseries dataset from the traffic domain.
引用
收藏
页码:201 / 210
页数:10
相关论文
共 31 条
[1]   Unsupervised real-time anomaly detection for streaming data [J].
Ahmad, Subutai ;
Lavin, Alexander ;
Purdy, Scott ;
Agha, Zuha .
NEUROCOMPUTING, 2017, 262 :134-147
[2]  
[Anonymous], UBER EXPT PLATFORM
[3]  
[Anonymous], 2008, Introduction to Statistical Quality Control - 6 edicao
[4]  
[Anonymous], 2009, Data Mining Case Studies
[5]   Designing and Deploying Online Field Experiments [J].
Bakshy, Eytan ;
Eckles, Dean ;
Bernstein, Michael S. .
WWW'14: PROCEEDINGS OF THE 23RD INTERNATIONAL CONFERENCE ON WORLD WIDE WEB, 2014, :283-292
[6]  
Cheboli D., 2010, Anomaly Detection of Time Series
[7]  
Cretu-Ciocarlie GF, 2009, LECT NOTES COMPUT SC, V5758, P41, DOI 10.1007/978-3-642-04342-0_3
[8]  
Ehlers Jens., 2011, Proceedings of the 8th ACM International Conference on Autonomic Computing. ICAC'11. Karlsruhe, P197, DOI DOI 10.1145/1998582.1998628
[9]   Google Vizier: A Service for Black-Box Optimization [J].
Golovin, Daniel ;
Solnik, Benjamin ;
Moitra, Subhodeep ;
Kochanski, Greg ;
Karro, John ;
Sculley, D. .
KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2017, :1487-1496
[10]   Trustworthy Experimentation Under Telemetry Loss [J].
Gupchup, Jayant ;
Hosseinkashi, Yasaman ;
Dmitriev, Pavel ;
Schneider, Daniel ;
Cutler, Ross ;
Jefremov, Andrei ;
Ellis, Martin .
CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2018, :387-396