| Revision as of 17:27, 22 November 2021 edit198.118.198.210 (talk) Fix typos← Previous edit | Latest revision as of 14:27, 13 October 2024 edit undoChristian75 (talk | contribs)Extended confirmed users, New page reviewers, Pending changes reviewers, Rollbackers114,303 edits {{R with history}} - Was not merged despite the Afd was closed as merge | ||
| (23 intermediate revisions by 19 users not shown) | |||
| Line 1: | Line 1: | ||
| #Redirect ] | |||
| {{Unreliable sources|date=March 2021}} | |||
| '''Artificial Intelligence for IT Operations''' ('''AIOps''') is a term coined by Gartner in 2016 as an industry category for machine learning analytics technology that enhances ].<ref>{{Cite web|url=https://diginomica.com/moogsoft-ceo-phil-tee-aiops-and-service-assurance-age-digital-transformation|title=AIOps and service assurance in the age of digital transformation|publisher=Diginomica|author=Jerry Bowles|date=January 28, 2020}}</ref> AIOps<ref name="CXO Today">{{cite web |url=http://www.cxotoday.com/story/algorithmic-it-operations-drives-digital-business-gartner/ |title=Algorithmic IT Operations Drives Digital Business: Gartner - CXOtoday.com |newspaper=Cxotoday.com |date= |author= |accessdate=January 28, 2018 |archive-url=https://web.archive.org/web/20180128074703/http://www.cxotoday.com/story/algorithmic-it-operations-drives-digital-business-gartner/ |archive-date=January 28, 2018 |url-status=dead }}</ref> is the acronym of "'''Algorithmic IT Operations'''".<ref name="Gartner">{{cite web |url=https://www.gartner.com/doc/3772124/market-guide-aiops-platforms |title=Market Guide for AIOps Platforms |website=] |date= |author= |accessdate= January 28, 2018}}</ref><ref name="Deloitte">{{cite web |url=https://www2.deloitte.com/content/dam/Deloitte/pl/Documents/Brochures/pl_en_Moogsoft_Deloitte_brochure.pdf |title= Comprehensive approach for Artificial Intelligence for IT Operations transformation|website=] |date= |author= |accessdate= January 28, 2018}}</ref><ref name="Tech">{{cite web |url=http://searchnetworking.techtarget.com/feature/ITOA-to-AIOps-The-next-generation-of-network-analytics |title=ITOA to AIOps: The next generation of network analytics |website=] |date= |author= |accessdate= January 28, 2018}}</ref> Such operation tasks include automation, performance monitoring and event correlations among others.<ref name="Register">{{cite web |url=https://whitepapers.theregister.co.uk/paper/view/6048/an-introduction-to-aiops |title=An Introduction to AIOps |newspaper=] |date= |author= |accessdate= January 28, 2018}}</ref><ref name="Dataconomy">{{cite web |url=http://dataconomy.com/2017/03/aiops-type-ai-nothing-artificial/ |title=AIOps - The Type of 'AI' with Nothing Artificial About It - Dataconomy |website=Dataconomy.com |date= |author= |accessdate= January 28, 2018}}</ref> | |||
| {{R with history}} | |||
| There are two main aspects of an AIOps platform: ] and ]. In order to collect ] and engagement data that can be found inside a big data platform and requires a shift away from sectionally segregated IT data, a holistic machine learning and ] is implemented against the combined IT data.<ref>{{cite web|url=https://devops.com/aiops-second-law-ops/|title=AIOps: Managing the Second Law of IT Ops - DevOps.com|date=22 September 2017|website=devops.com|accessdate=24 January 2018}}</ref> | |||
| The goal is to enable IT transformation,<ref>{{Cite web|title=What is AIOps or Artificial Intelligence for IT Operations. Top 10 Common AIOps Use Cases|url=https://cloudfabrix.com/blog/aiops/what-is-aiops-top-10-common-use-cases/|url-status=live}}</ref> receive continuous insights which provide ] via automation. This is why AIOps can be viewed as ] for core IT functions.<ref>{{cite web|url=https://appdevelopermagazine.com/5047/2017/3/13/explaining-what-aiops-is-and-why-it-matters-to-developers/|title=Explaining what AIOps is and why it matters to developers|first=Richard|last=Harris|website=appdevelopermagazine.com|accessdate=24 January 2018}}</ref> | |||
| Given the inherent nature of IT operations being closely tied to cloud deployment and the management of distributed applications, AIOps has increasingly led to the coalescence of ] and ].<ref>{{Citation|last=Masood|first=Adnan|title=AIOps: Predictive Analytics & Machine Learning in Operations|date=2019|work=Cognitive Computing Recipes: Artificial Intelligence Solutions Using Microsoft Cognitive Services and TensorFlow|pages=359–382|editor-last=Masood|editor-first=Adnan|publisher=Apress|language=en|doi=10.1007/978-1-4842-4106-6_7|isbn=978-1-4842-4106-6|last2=Hashmi|first2=Adnan|editor2-last=Hashmi|editor2-first=Adnan}}</ref><ref>{{Cite journal|last=Duc|first=Thang Le|last2=Leiva|first2=Rafael García|last3=Casari|first3=Paolo|last4=Östberg|first4=Per-Olov|date=September 2019|title=Machine Learning Methods for Reliable Resource Provisioning in Edge-Cloud Computing: A Survey|journal=ACM Comput. Surv.|volume=52|issue=5|pages=94:1–94:39|doi=10.1145/3341145|issn=0360-0300|url=https://zenodo.org/record/3471441|doi-access=free}}</ref> | |||
| ==Process== | |||
| The ] data is suitable to be processed through machine learning algorithms to automatically reduce noise and identify the probable root cause of incidents. The main output of such stage is the detection of any abnormal behavior from users, devices or applications. | |||
| Noise reduction can be done by various methods, but most of the researches in the field points to the following actions: | |||
| # Analysis of all incoming alerts; | |||
| # Remove duplicates; | |||
| # Identify the false positives; | |||
| # Early anomaly, fault and failure (AFF) detection and analysis.<ref></ref> | |||
| Anomaly detection - another step in any AIOps process is based on the analysis of past behavior of users, equipment and applications. Anything that strays from that behavior baseline is considered unusual and flagged as abnormal. | |||
| Root cause determination is done usually by passing incoming alerts through algorithms that takes into consideration correlated events as well as topology dependencies. The algorithms on which AI are basing their functioning can be influenced directly, essentially by "training" them.<ref></ref> | |||
| ==Use== | |||
| A very important use of AIOps platforms is related to the analysis of large and unconnected datasets, such as the Johns Hopkins Covid-19's data published through GitHub.<ref></ref> The data in this example is pulled from a large number of ] - aggregated data (10 sources), US regional data (113 sources) and Non-US data (37 sources), which are unuseable considering the needed emergency response time by the traditional analysis models. | |||
| Generally, the main areas of use for AIOps platforms and principles are<ref></ref> | |||
| * Automation of tasks (]) | |||
| * ] platforms | |||
| * ] | |||
| * ] | |||
| * ] (IoT) | |||
| * AI Optimized Hardware | |||
| * ] | |||
| * ] platforms | |||
| * Conversational ] and ] | |||
| ==References== | |||
| {{reflist}} | |||
| ] | |||
Latest revision as of 14:27, 13 October 2024
Redirect to:
- With history: This is a redirect from a page containing substantive page history. This page is kept as a redirect to preserve its former content and attributions. Please do not remove the tag that generates this text (unless the need to recreate content on this page has been demonstrated), nor delete this page.
- This template should not be used for redirects having some edit history but no meaningful content in their previous versions, nor for redirects created as a result of a page merge (use {{R from merge}} instead), nor for redirects from a title that forms a historic part of Misplaced Pages (use {{R with old history}} instead).