Exam AWS Certified Solutions Architect - Professional SAP-C02 topic 1 question 157 discussion

Offline operation: AWS IoT Greengrass supports offline operation by enabling devices to continue processing data even when they are disconnected from the internet.

https://aws.amazon.com/blogs/machine-learning/anomaly-detection-with-amazon-sagemaker-edge-manager-using-aws-iot-greengrass-v2/

Option B

Option B: Greengrass supports offline operation

Offline = IoT Greengrass

B for offline

keyword = WS IoT Greengrass

Can't be D. Amazon Monitron requires Internet connection.Q: Can I use Amazon Monitron when it is not connected to the AWS Region or in a disconnected environment? A: Amazon Monitron Sensors and Gateways, and their use with the Amazon Monitron service, rely on connectivity over internet to the AWS Region. https://aws.amazon.com/monitron/faqs/ Amazon Monitron Sensors and Gateways are not designed for disconnected operations or environments with no connectivity. We recommend that customers have highly available internet connectivity.

AWS IoT Greengrass is software that extends cloud capabilities to local devices. This enables devices to collect and analyze data closer to the source of information, react autonomously to local events, and communicate securely with each other on local networks. Local devices can also communicate securely with AWS IoT Core and export IoT data to the AWS Cloud. AWS IoT Greengrass developers can use AWS Lambda functions and prebuilt connectors to create serverless applications that are deployed to devices for local execution.

The ML model is run locally, so it can still provide feedback when the internet is down.

Quote "The company must be able to provide this feedback even if the factory’s internet connectivity is down" So everything that needs internet can be ignored. Leaves D. While there is a lot of garbage text about how they process date with SargeMaker, the question only asks for a solution to detect failures in the equipment. Amazon Monitron does this plus it can work even when internet is down. All other options provide solutions for things, the question didn't ask for and/or already in place and need internet.

The point is how to offload ML workloads to the local.

Monitron is something different

this is taking about detecting defects from an image that is taken from a camera. I would go for running a ML model on IoT greengras pc and transfer it to IoT core, then store it in s3 bucket, which can be called by api function via lambda to send it to users. option D would monitor only sensor data of machines.

Amazon Monitron is a machine-learning based end-to-end condition monitoring system that detects potential failures within equipment. You can use it to implement a predictive maintenance program and reduce lost productivity from unplanned machine downtime. Amazon Monitron includes purpose-built sensors to capture vibration and temperature data, as well as gateways to automatically transfer data to the AWS Cloud. It also comes with an application in two versions. The mobile application handles system setup, analytics, and notification when tracking equipment conditions. The web application provides all the same functions as the mobile app except setup. Reliability managers can quickly deploy Amazon Monitron to track the machine health of industrial equipment, such as such as bearings, motors, gearboxes, and pumps, without any development work or specialized training.