MLS-C01 Question 289
Single answerYou are deploying a machine learning inference application on AWS. The application receives intermittent bursts of traffic, and you need to ensure that the incoming requests are properly distributed across multiple instances of your inference model. Additionally, you need to minimize downtime as the application scales to meet demand. Which AWS service or feature should you use to achieve this?
- A
AWS Elastic Load Balancer (ELB)
- B
Amazon S3 Transfer Acceleration
- C
Amazon RDS Multi-AZ
- D
AWS Batch
Show answer and explanation
Correct answer: A
Explanation
To handle intermittent bursts of traffic and distribute requests across multiple instances of an inference model, AWS Elastic Load Balancer (ELB) is the ideal service. ELB ensures that traffic is balanced across targets in one or more availability zones, providing scalability and reducing the risk of downtime. Other options like Amazon S3 Transfer Acceleration, Amazon RDS Multi-AZ, and AWS Batch are unrelated to real-time load balancing for inference applications.
- A. Correct.
AWS Elastic Load Balancer (ELB) is the correct choice because it automatically distributes incoming traffic across multiple targets, such as Amazon EC2 instances, containers, or IP addresses. This ensures high availability and fault tolerance for your inference application.
- B. Incorrect.
Amazon S3 Transfer Acceleration is designed to speed up the transfer of files to and from Amazon S3, but it is not a solution for distributing network traffic across multiple instances.
- C. Incorrect.
Amazon RDS Multi-AZ provides high availability for relational databases by creating standby replicas in another availability zone, but it is not relevant for load balancing inference requests.
- D. Incorrect.
AWS Batch is used for running batch computing workloads at scale, not for distributing real-time traffic across multiple instances.