Autonomous Database is one of the hottest Oracle products where we have attempted to use Machine Learning for several aspects of the service. We will cover some use cases to find anomalies in them to troubleshoot them at a scale of several petabytes a year using Log Anomaly timeline using semi-supervised machine learning techniques to reduce logs and match them in near real time. We will also cover how we detect changing workload, use Zscores to pinpoint faults, use time series analysis to find good times to do backups or maintenance, models to detect performance tuning issues and root cause analysis as well as fleet learning to apply knowledge of trends and issues across multiple symptoms affecting the fleet including rediscovery. We will cover example code where applicable and frameworks we use for this.
展开▼