The Machine Learning behind Autonomous Database

Autonomous Database is one of the hottest Oracle products where we have attempted to use Machine Learning for several aspects of the service. We take a view on our current state of ML in the Autonomous Database Cloud and how do we process this data in ADW/ATP with zeppelin notebooks to find anomalies in them to troubleshoot them at a scale of several petabytes a year and conduct AIOps.

We will cover some sample notebooks to some use cases we will cover are a Log Anomaly timeline which we reduce significant amounts of logs using semi-supervised machine learning techniques to reduce logs and match them in near real time. Some of the other use cases is to use convolution filters to determine maintenance windows within the database workloads , determine best times to do database backups , security anomaly timelines and many others. This presentation will accompany several examples with how to apply these techniques , machine learning knowledge is preferred but not a prerequisite