TY - GEN
T1 - Second Order-Based Real-Time Anomaly Detection for Application Maintenance Services
AU - Li, Feng
AU - Li, Qicheng
AU - Mei, Lijun
AU - Li, Shaochun
AU - Rong, Liu
AU - Chen, Weiye
AU - Wang, Fenfei
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/2/5
Y1 - 2016/2/5
N2 - Application Maintenance Services (AMS) is essential for applications executed on servers to function properly. Its objective is to reduce the application incidents happened and quickly recover services from application failures/issues. The application incidents defined as events when there are some application failures/issues happened are major concerns of AMS, therefore we propose a second order-based anomaly detection method to describe and predict application incidents based on analysis of monitored server traffic metrics. The proposed method first detects anomalies for each metric, second builds the linkage between detected anomalies for all metrics of the server and application incidents, and then predicts potential application incidents. Through the experiments, we find that the presented method provides satisfactory results for identify application incident, which gives more than 90 percentage recall rate while about 65 percentage precision rate.
AB - Application Maintenance Services (AMS) is essential for applications executed on servers to function properly. Its objective is to reduce the application incidents happened and quickly recover services from application failures/issues. The application incidents defined as events when there are some application failures/issues happened are major concerns of AMS, therefore we propose a second order-based anomaly detection method to describe and predict application incidents based on analysis of monitored server traffic metrics. The proposed method first detects anomalies for each metric, second builds the linkage between detected anomalies for all metrics of the server and application incidents, and then predicts potential application incidents. Through the experiments, we find that the presented method provides satisfactory results for identify application incident, which gives more than 90 percentage recall rate while about 65 percentage precision rate.
KW - Application Maintenance Services
KW - Incident Prediction
KW - eal time Anomaly Detection
UR - http://www.scopus.com/inward/record.url?scp=84962322900&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962322900&partnerID=8YFLogxK
U2 - 10.1109/ICSS.2015.23
DO - 10.1109/ICSS.2015.23
M3 - Conference contribution
AN - SCOPUS:84962322900
T3 - Proceedings of International Conference on Service Science, ICSS
SP - 37
EP - 44
BT - Proceedings - 2015 International Conference on Services Science, ICSS 2015
T2 - International Conference on Services Science, ICSS 2015
Y2 - 8 May 2015 through 9 May 2015
ER -