Google Cloud Professional Machine Learning Engineer PMLE — Topic 1 Question 83

Question

You need to design an architecture that serves asynchronous predictions to determine whether a particular mission-critical machine part will fail. Your system collects data from multiple sensors from the machine. You want to build a model that will predict a failure in the next N minutes, given the average of each sensor’s data from the past 12 hours. How should you design the architecture?

Accepted Answer

Correct answer: B. The correct answer is B. Option B: 1. Events are sent by the sensors to Pub/Sub, consumed in real time, and processed by a Dataflow stream processing pipeline.2. The pipeline invokes the model for prediction and sends the predictions to another Pub/Sub... Dataflow runs serverless Apache Beam pipelines for stream and batch data processing with autoscaling. Pub/Sub is a serverless, global messaging service that decouples services and ingests high-volume event streams. This option decouples the components so they scale independently and absorb load spikes.

Google Cloud Professional Machine Learning Engineer PMLE — Question 83