Failure Prediction based on Log Files Using Random Indexing and Support Vector Machines
MetadataShow full item record
SubjectFailure prediction; Random Indexing; Support Vector Machine (SVM); Event sequence data; Log files
Research problem: The impact of failures on software systems can be substantial since the recovery process can require unexpected amounts of time and resources. Accurate failure predictions can help in mitigating the impact of failures. Resources, applications, and services can be scheduled to limit the impact of failures. However, providing accurate predictions sufficiently ahead is challenging. Log files contain messages that represent a change of system state. A sequence or a pattern of messages may be used to predict failures. Contribution: We describe an approach to predict failures based on log files using Random Indexing (RI) and Support Vector Machines (SVMs). Method: RI is applied to represent sequences: each operation is characterized in terms of its context. SVMs associate sequences to a class of failures or non-failures. Weighted SVMs are applied to deal with imbalanced datasets and to improve the true positive rate. We apply our approach to log files collected during approximately three months of work in a large European manufacturing company. Results: According to our results, weighted SVMs sacrifice some specificity to improve sensitivity. Speci- ficity remains higher than 0.80 in four out of six analyzed applications. Conclusions: Overall, our approach is very reliable in predicting both failures and non-failures.
Showing items related by title, author, creator and subject.
A training based Support Vector Machine technique for blood detection in wireless capsule endoscopy images Li J; Ma J; Tillo T; Zhang B; Lim E (IEEE, 2012)Wireless capsule endoscopy (WCE) is a non-invasive technique which could detect variety of abnormalities in the small bowel. However, in many cases it is difficult for doctors to distinguish obscure gastrointestinal bleeding ...
Estimation of Soil Moisture in Vegetation-Covered Floodplains with Sentinel-1 SAR Data Using Support Vector Regression Holtgrave A; Förster M; Greifeneder F; Notarnicola C; Kleinschmit B (2018)Soil moisture (SM) is a significant parameter influencing various environmental processes in hydrology, ecology, and climatology. SAR-derived remote sensing products can be valuable input features for estimating SM. In the ...
Fronza I; Sillitti A; Succi G; Vlasenko J (SciTePress, 2011)Developing software without failures is indeed important. Still, it is also important to detect as soon as possible when a running application is likely to fail, so that corrective actions can be taken. Following the ...