Adding real-time ML predictions for your Amazon Aurora database: Part 2
Database Blog
This blog post discusses how to implement Aurora machine learning (ML) performance optimizations to perform real-time inference against a SageMaker endpoint at a large scale. It covers simulating an OLTP workload against a database and using SQL triggers to create an automatic orchestration pipeline for predictive workloads.
Specifically, the article covers:
- Deploying the infrastructure using AWS CloudFormation
- Connecting to the Aurora cluster and setting up the workflow
- Orchestrating a predictive workflow with SQL triggers
- Performing stress testing by simulating a large-scale OLTP workload
- Analyzing performance metrics and optimization suggestions
- Cleaning up resources
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Jun 25
2024
2024
Amazon Aurora now provides additional monitoring information during upgrades
Jul 1
2024
2024
Use Amazon Aurora Global Database to build resilient multi-Region applications
Jul 30
2024
2024
Monitoring Amazon Aurora databases with IBM Guardium
Jul 2
2024
2024
Understanding Amazon Aurora MySQL storage space utilization
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.