MetricSifter: Feature Reduction of Multivariate Time Series Data for Efficient Fault Localization in Cloud Applications
Open Access
- 7 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 37398-37417
Abstract
Automated fault localization in large-scale cloud-based applications is challenging because it involves mining multivariate time series data from large volumes of operational monitoring metrics. To improve localization accuracy, automated fault localization methods incorporate feature reduction to reduce the number of monitoring metrics unrelated to a failure. However, these methods have problems with inaccuracy, either from removing too many failure-related metrics or from retaining too few failure-unrelated metrics. In this paper, we present MetricSifter, a feature reduction framework designed to accurately identify anomalous metrics caused by faults. Our framework locates a failure time window with the highest density of fault-induced change point times across monitoring metrics with a focus on their temporal proximity. Experimental results indicate that MetricSifter achieves an accuracy of 0.981, which is significantly better than the selected baseline methods. Furthermore, experiments combining various reduction methods with various localization methods demonstrate that MetricSifter improves the recall and time efficiency over the baseline methods.Keywords
This publication has 56 references indexed in Scilit:
- CausalRCA: Causal inference based precise fine-grained root cause localization for microservice applicationsJournal of Systems and Software, 2023
- Signal propagation in complex networksPhysics Reports, 2023
- TraceRank: Abnormal service localization with dis‐aggregated end‐to‐end tracing data in cloud native systemsJournal of Software: Evolution and Process, 2021
- Report 08-2021Datenschutz und Datensicherheit - DuD, 2021
- Microscope: Pinpoint Performance Issues with Causal Graphs in Micro-service Environments2018
- Time-series clustering – A decade reviewInformation Systems, 2015
- Energy statistics: A class of statistics based on distancesJournal of Statistical Planning and Inference, 2013
- Cloud monitoring: A surveyComputer Networks, 2013
- Density-Based Clustering Based on Hierarchical Density Estimates2013
- Gaussian Mixture Models2009