TY - GEN
T1 - Anomaly-based fault detection in Pervasive Computing System
AU - Kim, Byoung Uk
AU - Al-Nashif, Youssif
AU - Fayssal, Samer
AU - Hariri, Salim
AU - Yousif, Mazin
N1 - Funding Information:
The authors would like to thank to Danton da Silva Junior for the tireless assistance with the thermometers; to Sandra Maria Hartz, Andreas Kindel, and Carlos Benhur Kasper for reviewing the manuscript; to the Sesc Pantanal; and to all employees who contributed to this work. We are especially grateful to Sesc managers Leopoldo G. Brandão, Waldir Valutki, Silvia Kataoka, and Cristina Cuiabália. G. S. Hofmann, I. P. Coelho, V. A. G. Bastazini are grateful to Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) for the scholarship. The work by L. F. B. Oliveira was supported by Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) fellowship and grant.
PY - 2008
Y1 - 2008
N2 - The increased complexity of hardware and software resources and the asynchronous interaction among components (such as servers, end devices, network, services and software) make fault detection and recovery very challenging. In this paper, we present innovative concepts for fault detection, root cause analysis and self-healing architectures analyzing the duration of pattern transition sequences during an execution window. In this approach, all interactions among components of Pervasive Computing Systems (PCS) are monitored and analyzed. We use three-dimensional array of features to capture spatial and temporal variability to be used by an anomaly analysis engine to immediately generate an alert when abnormal behavior pattern is captured indicating some kind of software or hardware failure. The main contributions of this paper include the innovative analysis methodology and feature selection to detect and identify anomalous behavior. Evaluating the effectiveness of this approach to detect faults injected asynchronously shows a detection rate of above 99.9% with no occurrences of false alarms for a wide range of scenarios.
AB - The increased complexity of hardware and software resources and the asynchronous interaction among components (such as servers, end devices, network, services and software) make fault detection and recovery very challenging. In this paper, we present innovative concepts for fault detection, root cause analysis and self-healing architectures analyzing the duration of pattern transition sequences during an execution window. In this approach, all interactions among components of Pervasive Computing Systems (PCS) are monitored and analyzed. We use three-dimensional array of features to capture spatial and temporal variability to be used by an anomaly analysis engine to immediately generate an alert when abnormal behavior pattern is captured indicating some kind of software or hardware failure. The main contributions of this paper include the innovative analysis methodology and feature selection to detect and identify anomalous behavior. Evaluating the effectiveness of this approach to detect faults injected asynchronously shows a detection rate of above 99.9% with no occurrences of false alarms for a wide range of scenarios.
KW - Abnormality detection
KW - Faults
KW - Interaction analysis
KW - Pattern profiling
KW - Performance objectives
UR - http://www.scopus.com/inward/record.url?scp=70249121450&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70249121450&partnerID=8YFLogxK
U2 - 10.1145/1387269.1387294
DO - 10.1145/1387269.1387294
M3 - Conference contribution
AN - SCOPUS:70249121450
SN - 9781605581354
T3 - Proceedings of the 5th International Conference on Pervasive Services, ICPS 2008
SP - 147
EP - 155
BT - Proceedings of the 5th International Conference on Pervasive Services, ICPS 2008
T2 - 5th International Conference on Pervasive Services, ICPS 2008
Y2 - 6 July 2008 through 10 July 2008
ER -