CASE STUDY: AutoIoT
Overview: Connected car manufacturer. 1M vehicles sending telemetry every 5 seconds.
Business: Predictive maintenance alerts, real-time fleet tracking, monetize anonymized data.
Executives:
Which architecture should you design for the data ingestion and processing layer to replace the crashing MQTT brokers?
GCP PCA · Question 19 · Domain 5: Managing Implementation and Ensuring Solution and Operations Reliability
CASE STUDY: AutoIoT
Overview: Connected car manufacturer. 1M vehicles sending telemetry every 5 seconds.
Business: Predictive maintenance alerts, real-time fleet tracking, monetize anonymized data.
Executives:
To meet the CEO's requirement for predictive maintenance, how should you orchestrate the weekly ML model training pipeline?
Answer options:
Write a bash script on a Compute Engine instance that runs via cron to train the model.
Use Cloud Build to train the ML model and deploy it to Cloud Run.
Use Vertex AI Pipelines to orchestrate the extraction of data from BigQuery, model training, and deployment to a Vertex AI Endpoint.
Use Dataflow to train the machine learning model in real-time.
50 questions · hints · full answers · grading
Expert