MLS-C01 Question 266
Select 2You are deploying a machine learning model for a global e-commerce application that needs low latency predictions in multiple regions. The deployment must ensure high availability and fault tolerance across AWS Regions and Availability Zones. Which of the following strategies would best meet these requirements?
- A
Use Amazon SageMaker hosting to deploy the model in multiple AWS Regions and configure a Route 53 latency-based routing policy.
- B
Deploy the model to a single AWS Region and use Amazon CloudFront to distribute predictions globally.
- C
Use Amazon SageMaker hosting to deploy the model across multiple Availability Zones within a single AWS Region.
- D
Deploy the model in multiple AWS Regions with SageMaker and use AWS Global Accelerator for traffic routing.
Show answer and explanation
Correct answers: A, D
Explanation
To meet the requirements of low latency, high availability, and fault tolerance for a global application, deploying the model in multiple AWS Regions is essential. Combining this with a traffic routing solution such as Route 53 latency-based routing or AWS Global Accelerator ensures that user requests are directed to the nearest and most performant region. Additionally, using multiple Availability Zones within each region enhances fault tolerance and availability.
- A. Correct.
This is correct. Deploying the model in multiple AWS Regions ensures low latency for users in different geographic areas. Using Route 53 latency-based routing enables directing requests to the closest region, optimizing latency.
- B. Incorrect.
This is incorrect. Deploying to a single AWS Region and using CloudFront can help with static content delivery, but it is not suitable for real-time, low-latency ML predictions globally.
- C. Incorrect.
This is partially correct but incomplete. Deploying across multiple Availability Zones ensures high availability within a single region but does not address global latency requirements.
- D. Correct.
This is correct. Deploying in multiple AWS Regions ensures low latency globally, and AWS Global Accelerator provides intelligent traffic routing, improving performance and availability for global users.