Search⌘ K
AI Features
Home
Courses
Data Science in Production: Building Scalable Model Pipelines

- Load Balancing

Explore how to configure AWS Application Load Balancers to create scalable and reliable containerized model services. Understand ECS service setup, task management, and cost considerations compared to Lambda. Gain practical skills to deploy reproducible models using load balancing in cloud environments.

We'll cover the following...

There are a number of different load balancer options in AWS that are useful for different deployments. This is also an area where the options are rapidly changing. For our ECS cluster, we can use the application load balancer to provide a static URL for accessing the echo service.

Setting up a load balancer

To set up a load balancer, perform the following steps from the AWS console:

  1. Search for and select “EC2”.
  2. Select “Load Balancer” on the left.
  3. Click “Create Load Balancer”.
  4. Choose “Application Load Balancer”.
  5. Assign the name,
...