Telemetry Based Anomaly Detection and Correlation in Data Center
Arun S Jois1, Jayasimha S R2

1Arun S Jois, Department of MCA, RV College of Engineering® Bengaluru, India.
2Jayasimha S. R, Assistant Professor, Department of MCA, RV College of Engineering®, Bangalore, India.

Manuscript received on April 30, 2020. | Revised Manuscript received on May 06, 2020. | Manuscript published on May 30, 2020. | PP: 2146-2148 | Volume-9 Issue-1, May 2020. | Retrieval Number: A2725059120/2020©BEIESP | DOI: 10.35940/ijrte.A2725.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Data center is a complex amalgamation of servers where there are thousands of services, storage, networking, routers, switches and softwares providing services 24×7 to cus- tomers. Services provided can range from websites, storage, cloud platform, Email marketing etc. A team is established to detach the anomaly generated from the monitoring system. Anomaly or issues in servers cause high downtime of service. Detecting these anomalies with high accuracy and performing Root cause analysis has been a major issue. The team often remediates the symptom than the anomaly. With the use of Artificial Neural networks a trained model can provide solutions with high accuracy and scalablility which result in higher uptime and reduced MTTR for customers.
Keywords: AIOps, AI, TechOps, Root cause analysis.
Scope of the Article: Data Analytics