Skip to main content

2017 | OriginalPaper | Buchkapitel

K-means Application for Anomaly Detection and Log Classification in HPC

verfasst von : Mohamed Cherif Dani, Henri Doreau, Samantha Alt

Erschienen in: Advances in Artificial Intelligence: From Theory to Practice

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Detecting anomalies in the flow of system logs of a high performance computing (HPC) facility is a challenging task. Although previous research has been conducted to identify nominal and abnormal phases; practical ways to provide system administrators with a reduced set of the most useful messages to identify abnormal behaviour remains a challenge. In this paper we describe an extensive study of logs classification and anomaly detection using K-means on real HPC unlabelled data extracted from the Curie supercomputer. This method involves (1) classifying logs by format, which is a valuable information for admin, then (2) build normal and abnormal classes for anomaly detection. Our methodology shows good performances for clustering and detecting abnormal logs.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Morey, J.-M.: Numerical simulation at CEA. In: Proceedings of SNA + MC (2013) Morey, J.-M.: Numerical simulation at CEA. In: Proceedings of SNA + MC (2013)
2.
Zurück zum Zitat David, J.: Building a Monitoring Infrastructure with Nagios. Prentice Hall PTR, Upper Saddle River (2007) David, J.: Building a Monitoring Infrastructure with Nagios. Prentice Hall PTR, Upper Saddle River (2007)
3.
Zurück zum Zitat Bautista, E., Whitney, C., Davis, T.: Big data behind big data. In: Arora, R. (ed.) Conquering Big Data with High Performance Computing, pp. 163–189. Springer, Cham (2016)CrossRef Bautista, E., Whitney, C., Davis, T.: Big data behind big data. In: Arora, R. (ed.) Conquering Big Data with High Performance Computing, pp. 163–189. Springer, Cham (2016)CrossRef
4.
Zurück zum Zitat Sigoure, B.: OpenTSDB scalable time series database (TSDB) (2012) Sigoure, B.: OpenTSDB scalable time series database (TSDB) (2012)
5.
Zurück zum Zitat Kreps, J., Narkhede, N., Rao, J., et al.: Kafka: a distributed messaging system for log processing. In: Proceedings of The NetDB, pp. 1–7 (2011) Kreps, J., Narkhede, N., Rao, J., et al.: Kafka: a distributed messaging system for log processing. In: Proceedings of The NetDB, pp. 1–7 (2011)
6.
Zurück zum Zitat Reelsen, A.: Using elasticsearch, logstash and kibana to create realtime dashboards (2014) Reelsen, A.: Using elasticsearch, logstash and kibana to create realtime dashboards (2014)
7.
Zurück zum Zitat Ning, X., Jiang, G., Chen, H., Yoshihira, K.: HLAer: a system for heterogeneous log analysis Ning, X., Jiang, G., Chen, H., Yoshihira, K.: HLAer: a system for heterogeneous log analysis
8.
Zurück zum Zitat Aggarwal, C.C., Yu, P.: Outlier detection with uncertain data. In: SDM (2008) Aggarwal, C.C., Yu, P.: Outlier detection with uncertain data. In: SDM (2008)
9.
Zurück zum Zitat Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41, 15 (2009)CrossRef Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41, 15 (2009)CrossRef
10.
Zurück zum Zitat Gupta, M., Han, J., Aggarwal, C., Gao, J.: Outlier detection for temporal data: a survey. IEEE Trans. Knowl. Data Eng. 26, 2250–2267 (2014)CrossRefMATH Gupta, M., Han, J., Aggarwal, C., Gao, J.: Outlier detection for temporal data: a survey. IEEE Trans. Knowl. Data Eng. 26, 2250–2267 (2014)CrossRefMATH
11.
Zurück zum Zitat Stearley, J.: Towards informatic analysis of syslogs. In: Cluster Computing. IEEE (2004) Stearley, J.: Towards informatic analysis of syslogs. In: Cluster Computing. IEEE (2004)
12.
Zurück zum Zitat Chuah, E., Jhumka, A., Narasimhamurthy, S., et al.: Linking resource usage anomalies with system failures from cluster log data. IEEE (2013) Chuah, E., Jhumka, A., Narasimhamurthy, S., et al.: Linking resource usage anomalies with system failures from cluster log data. IEEE (2013)
13.
Zurück zum Zitat Gurumdimma, N., Jhumka, A., et al.: CRUDE: combining resource usage data and error logs for accurate error detection in large-scale distributed systems. IEEE (2016) Gurumdimma, N., Jhumka, A., et al.: CRUDE: combining resource usage data and error logs for accurate error detection in large-scale distributed systems. IEEE (2016)
14.
Zurück zum Zitat Rajaraman, A., Ullman, J.D.: Data mining. In: Mining of Massive Datasets (PDF) (2011) Rajaraman, A., Ullman, J.D.: Data mining. In: Mining of Massive Datasets (PDF) (2011)
15.
Zurück zum Zitat MacQueen, J.B.: Some Methods for classification and Analysis of Multivariate Observations. University of California Press, Berkeley (1967)MATH MacQueen, J.B.: Some Methods for classification and Analysis of Multivariate Observations. University of California Press, Berkeley (1967)MATH
16.
Zurück zum Zitat Akaike, H.: Information theory and an extension of the maximum likelihood principle. In: Petrov, B.N., Csáki, F. (eds.) 2nd International Symposium on Information Theory, Tsahkadsor, Armenia, USSR, September 2–8 (1971) Akaike, H.: Information theory and an extension of the maximum likelihood principle. In: Petrov, B.N., Csáki, F. (eds.) 2nd International Symposium on Information Theory, Tsahkadsor, Armenia, USSR, September 2–8 (1971)
18.
Zurück zum Zitat Münz, G., Li, S., Carle, G.: Traffic anomaly detection using k-means clustering. In: GI/ITG-Workshop MMBnet, September 2007 Münz, G., Li, S., Carle, G.: Traffic anomaly detection using k-means clustering. In: GI/ITG-Workshop MMBnet, September 2007
19.
Zurück zum Zitat Larsen, B., Aone, C.: Fast and effective text mining using linear-time document clustering. In: Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (1999) Larsen, B., Aone, C.: Fast and effective text mining using linear-time document clustering. In: Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (1999)
Metadaten
Titel
K-means Application for Anomaly Detection and Log Classification in HPC
verfasst von
Mohamed Cherif Dani
Henri Doreau
Samantha Alt
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-60045-1_23

Premium Partner