High Significant Fault Detection in Azure Core Workload Insights

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lohia, Pranay, Boue, Laurent, Rangappa, Sharath, Agneeswaran, Vijay
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909267130318848
author Lohia, Pranay
Boue, Laurent
Rangappa, Sharath
Agneeswaran, Vijay
author_facet Lohia, Pranay
Boue, Laurent
Rangappa, Sharath
Agneeswaran, Vijay
contents Azure Core workload insights have time-series data with different metric units. Faults or Anomalies are observed in these time-series data owing to faults observed with respect to metric name, resources region, dimensions, and its dimension value associated with the data. For Azure Core, an important task is to highlight faults or anomalies to the user on a dashboard that they can perceive easily. The number of anomalies reported should be highly significant and in a limited number, e.g., 5-20 anomalies reported per hour. The reported anomalies will have significant user perception and high reconstruction error in any time-series forecasting model. Hence, our task is to automatically identify 'high significant anomalies' and their associated information for user perception.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09302
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle High Significant Fault Detection in Azure Core Workload Insights
Lohia, Pranay
Boue, Laurent
Rangappa, Sharath
Agneeswaran, Vijay
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Azure Core workload insights have time-series data with different metric units. Faults or Anomalies are observed in these time-series data owing to faults observed with respect to metric name, resources region, dimensions, and its dimension value associated with the data. For Azure Core, an important task is to highlight faults or anomalies to the user on a dashboard that they can perceive easily. The number of anomalies reported should be highly significant and in a limited number, e.g., 5-20 anomalies reported per hour. The reported anomalies will have significant user perception and high reconstruction error in any time-series forecasting model. Hence, our task is to automatically identify 'high significant anomalies' and their associated information for user perception.
title High Significant Fault Detection in Azure Core Workload Insights
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2404.09302