TY - JOUR
T1 - Unsupervised Learning and online Anomaly detection
T2 - An on-Condition Log-Based Maintenance System
AU - Decker, Leticia
AU - Leite, Daniel
AU - Minarini, Francesco
AU - Tisbeni, Simone Rossi
AU - Bonacorsi, Daniele
N1 - Funding Information:
Abdiansah, A., & Wardoyo, R. (2015). Time Complexity Analysis of Support Vector Machines (SVM) in LibSVM. International Journal Computer and Application, 128(3), 28-34. doi: 10.5120/ijca2015906480
Publisher Copyright:
Copyright © 2022, IGI Global.
PY - 2022
Y1 - 2022
N2 - The large hadron collider (LHC) demands a huge amount of computing resources to deal with petabytes of data generated from high energy physics (HEP) experiments and user logs, which report user activity within the supporting worldwide LHC computing grid (WLCG). An outburst of data and information is expected due to the scheduled LHC upgrad, that is, the workload of the WLCG should increase by 10 times in the near future. Autonomous system maintenance by means of log mining and machine learning algorithms is of utmost importance to keep the computing grid functional. The aim is to detect software faults, bugs, threats, and infrastructural problems. This paper describes a general-purpose solution to anomaly detection in computer grids using unstructured, textual, and unsupervised data. The solution consists in recognizing periods of anomalous activity based on content and information extracted from user log events. This study has particularly compared one-class SVM, isolation forest (IF), and local outlier factor (LOF). IF provides the best fault detection accuracy, 69.5%.
AB - The large hadron collider (LHC) demands a huge amount of computing resources to deal with petabytes of data generated from high energy physics (HEP) experiments and user logs, which report user activity within the supporting worldwide LHC computing grid (WLCG). An outburst of data and information is expected due to the scheduled LHC upgrad, that is, the workload of the WLCG should increase by 10 times in the near future. Autonomous system maintenance by means of log mining and machine learning algorithms is of utmost importance to keep the computing grid functional. The aim is to detect software faults, bugs, threats, and infrastructural problems. This paper describes a general-purpose solution to anomaly detection in computer grids using unstructured, textual, and unsupervised data. The solution consists in recognizing periods of anomalous activity based on content and information extracted from user log events. This study has particularly compared one-class SVM, isolation forest (IF), and local outlier factor (LOF). IF provides the best fault detection accuracy, 69.5%.
KW - Anomaly Detection
KW - Computing Center
KW - Intelligent System
KW - Log Mining
KW - Log-Based System
KW - Machine Learning
KW - On-Condition Maintenance
KW - Predictive Maintenance
UR - http://www.scopus.com/inward/record.url?scp=85138764862&partnerID=8YFLogxK
U2 - 10.4018/IJERTCS.302112
DO - 10.4018/IJERTCS.302112
M3 - Article
AN - SCOPUS:85138764862
SN - 1947-3176
VL - 13
JO - International Journal of Embedded and Real-Time Communication Systems
JF - International Journal of Embedded and Real-Time Communication Systems
IS - 1
M1 - 12
ER -