MLS-C01 · Question #173
A manufacturing company uses machine learning (ML) models to detect quality issues. The models use images that are taken of the company's product at the end of each production step. The company has…
The correct answer is D. Deploy the Lambda function and the ML models onto the AWS IoT Greengrass core that is. Deploying the Lambda function and ML models directly onto each AWS IoT Greengrass core (edge device) is the correct solution because it moves inference to the edge. At thousands of machines each producing one image per second, uploading every image to S3 and calling a…
Question
A manufacturing company uses machine learning (ML) models to detect quality issues. The models use images that are taken of the company's product at the end of each production step. The company has thousands of machines at the production site that generate one image per second on average. The company ran a successful pilot with a single manufacturing machine. For the pilot, ML specialists used an industrial PC that ran AWS IoT Greengrass with a long-running AWS Lambda function that uploaded the images to Amazon S3. The uploaded images invoked a Lambda function that was written in Python to perform inference by using an Amazon SageMaker endpoint that ran a custom model. The inference results were forwarded back to a web service that was hosted at the production site to prevent faulty products from being shipped. The company scaled the solution out to all manufacturing machines by installing similarly configured industrial PCs on each production machine. However, latency for predictions increased beyond acceptable limits. Analysis shows that the internet connection is at its capacity limit. How can the company resolve this issue MOST cost-effectively?
Options
- ASet up a 10 Gbps AWS Direct Connect connection between the production site and the nearest
- BExtend the long-running Lambda function that runs on AWS IoT Greengrass to compress the
- CUse auto scaling for SageMaker. Set up an AWS Direct Connect connection between the
- DDeploy the Lambda function and the ML models onto the AWS IoT Greengrass core that is
How the community answered
(24 responses)- A4% (1)
- B13% (3)
- C17% (4)
- D67% (16)
Explanation
Deploying the Lambda function and ML models directly onto each AWS IoT Greengrass core (edge device) is the correct solution because it moves inference to the edge. At thousands of machines each producing one image per second, uploading every image to S3 and calling a centralized SageMaker endpoint would create enormous bandwidth costs, latency bottlenecks, and a massively overloaded endpoint. IoT Greengrass supports running Lambda functions and ML model inference locally on the device, meaning each machine performs its own inference without any cloud round-trip for every image. Only the inference results (not the images themselves) need to be sent back to the on-site web service. Options A and C involve expensive Direct Connect connections and do not solve the fundamental scale problem. Option B (compressing images) reduces bandwidth but does not eliminate the cloud dependency or latency. Edge inference with Greengrass is the architecturally correct pattern for high-throughput, latency-sensitive industrial ML at scale.
Topics
Community Discussion
No community discussion yet for this question.