Time series sensor data anomaly detection using Statistical and Machine Learning Techniques: the INFN CNAF data center use case

by Luca Torzi

Wednesday 13 Sept 2023, 15:00 → 16:00 Europe/Rome

Sala Venturi+Prendiparte

Time series modeling for anomaly detection is a challenging task. In this report we describe the approach
followed while studying various sensor time series of the INFN CNAF data center related to chiller, ups and electrical plants. We show how the variables are
correlated and the anomalies identified with the application of traditional statistical technique, and other machine learning techniques, such as
DBSCAN and Graph Neural Network. The anomalies discovered with the various techniques are comparable for some sensors.

CNAF_Presentation_2.pdf

link al meeting