English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Deployment, operation and maintenance of large IT systems becomesincreasingly complex and puts human experts under extreme stress when problemsoccur. Therefore, utilization of machine learning (ML) and artificialintelligence (AI) is applied on IT system operation and maintenance -summarized in the term AIOps. One specific direction aims at the recognition ofre-occurring anomaly types to enable remediation automation. However, due to ITsystem specific properties, especially their frequent changes (e.g. softwareupdates, reconfiguration or hardware modernization), recognition of reoccurringanomaly types is challenging. Current methods mainly assume a staticdimensionality of provided data. We propose a method that is invariant todimensionality changes of given data. Resource metric data such as CPUutilization, allocated memory and others are modelled as multivariate timeseries. The extraction of temporal and spatial features together with thesubsequent anomaly classification is realized by utilizing TELESTO, our novelgraph convolutional neural network (GCNN) architecture. The experimentalevaluation is conducted in a real-world cloud testbed deployment that ishosting two applications. Classification results of injected anomalies on acassandra database node show that TELESTO outperforms the alternative GCNNs andachieves an overall classification accuracy of 85.1%. Classification resultsfor the other nodes show accuracy values between 85% and 60%.

TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services