Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912126994> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2912126994 abstract "For large Internet companies, it is very important to monitor a large number of KPIs (Key Performance Indicators) and detect anomalies to ensure the service quality and reliability. However, large-scale anomaly detection on millions of KPIs is very challenging due to the large overhead of model selection, parameter tuning, model training, or labeling. In this paper we argue that KPI clustering can help: we can cluster millions of KPIs into a small number of clusters and then select and train model on a per-cluster basis. However, KPI clustering faces new challenges that are not present in classic time series clustering: KPIs are typically much longer than other time series, and noises, anomalies, phase shifts and amplitude differences often change the shape of KPIs and mislead the clustering algorithm. To tackle the above challenges, in this paper we propose a robust and rapid KPI clustering algorithm, ROCKA. It consists of four steps: preprocessing, baseline extraction, clustering and assignment. These techniques help group KPIs according to their underlying shapes with high accuracy and efficiency. Our evaluation using real-world KPIs shows that ROCKA gets F-score higher than 0.85, and reduces model training time of a state-of-the-art anomaly detection algorithm by 90%, with only 15% performance loss." @default.
- W2912126994 created "2019-02-21" @default.
- W2912126994 creator A5002831321 @default.
- W2912126994 creator A5013718214 @default.
- W2912126994 creator A5018636031 @default.
- W2912126994 creator A5046419834 @default.
- W2912126994 date "2018-06-01" @default.
- W2912126994 modified "2023-10-18" @default.
- W2912126994 title "Robust and Rapid Clustering of KPIs for Large-Scale Anomaly Detection" @default.
- W2912126994 cites W1894414046 @default.
- W2912126994 cites W1966266075 @default.
- W2912126994 cites W1970754582 @default.
- W2912126994 cites W2026453187 @default.
- W2912126994 cites W2093606067 @default.
- W2912126994 cites W2097747115 @default.
- W2912126994 cites W2099302229 @default.
- W2912126994 cites W2100718094 @default.
- W2912126994 cites W2109820980 @default.
- W2912126994 cites W2120043163 @default.
- W2912126994 cites W2126052291 @default.
- W2912126994 cites W2128160875 @default.
- W2912126994 cites W2134490011 @default.
- W2912126994 cites W2236871065 @default.
- W2912126994 cites W2531749512 @default.
- W2912126994 cites W3028340924 @default.
- W2912126994 cites W3098957257 @default.
- W2912126994 doi "https://doi.org/10.1109/iwqos.2018.8624168" @default.
- W2912126994 hasPublicationYear "2018" @default.
- W2912126994 type Work @default.
- W2912126994 sameAs 2912126994 @default.
- W2912126994 citedByCount "37" @default.
- W2912126994 countsByYear W29121269942018 @default.
- W2912126994 countsByYear W29121269942019 @default.
- W2912126994 countsByYear W29121269942020 @default.
- W2912126994 countsByYear W29121269942021 @default.
- W2912126994 countsByYear W29121269942022 @default.
- W2912126994 countsByYear W29121269942023 @default.
- W2912126994 crossrefType "proceedings-article" @default.
- W2912126994 hasAuthorship W2912126994A5002831321 @default.
- W2912126994 hasAuthorship W2912126994A5013718214 @default.
- W2912126994 hasAuthorship W2912126994A5018636031 @default.
- W2912126994 hasAuthorship W2912126994A5046419834 @default.
- W2912126994 hasConcept C124101348 @default.
- W2912126994 hasConcept C135510737 @default.
- W2912126994 hasConcept C154945302 @default.
- W2912126994 hasConcept C162324750 @default.
- W2912126994 hasConcept C187736073 @default.
- W2912126994 hasConcept C205649164 @default.
- W2912126994 hasConcept C2778755073 @default.
- W2912126994 hasConcept C41008148 @default.
- W2912126994 hasConcept C58640448 @default.
- W2912126994 hasConcept C73555534 @default.
- W2912126994 hasConcept C739882 @default.
- W2912126994 hasConceptScore W2912126994C124101348 @default.
- W2912126994 hasConceptScore W2912126994C135510737 @default.
- W2912126994 hasConceptScore W2912126994C154945302 @default.
- W2912126994 hasConceptScore W2912126994C162324750 @default.
- W2912126994 hasConceptScore W2912126994C187736073 @default.
- W2912126994 hasConceptScore W2912126994C205649164 @default.
- W2912126994 hasConceptScore W2912126994C2778755073 @default.
- W2912126994 hasConceptScore W2912126994C41008148 @default.
- W2912126994 hasConceptScore W2912126994C58640448 @default.
- W2912126994 hasConceptScore W2912126994C73555534 @default.
- W2912126994 hasConceptScore W2912126994C739882 @default.
- W2912126994 hasLocation W29121269941 @default.
- W2912126994 hasOpenAccess W2912126994 @default.
- W2912126994 hasPrimaryLocation W29121269941 @default.
- W2912126994 hasRelatedWork W1967833105 @default.
- W2912126994 hasRelatedWork W1979871427 @default.
- W2912126994 hasRelatedWork W2187506573 @default.
- W2912126994 hasRelatedWork W2387405106 @default.
- W2912126994 hasRelatedWork W2392374020 @default.
- W2912126994 hasRelatedWork W3015348658 @default.
- W2912126994 hasRelatedWork W3102055965 @default.
- W2912126994 hasRelatedWork W3183283580 @default.
- W2912126994 hasRelatedWork W4206741375 @default.
- W2912126994 hasRelatedWork W4250175685 @default.
- W2912126994 isParatext "false" @default.
- W2912126994 isRetracted "false" @default.
- W2912126994 magId "2912126994" @default.
- W2912126994 workType "article" @default.