ExpertEasy1 markMultiple Choice
This question is part of a case study — click to read the full scenario(Case 16)
CASE STUDY: ManuIoT
Overview:
Industry: Manufacturing
Size: 100 factories globally
Environment:
- 100,000 sensors
- Local SCADA
- Fragmented SQL Server DBs
- No central analytics
Requirements:
- Predictive maintenance
- Real-time global dashboards
- Edge computing
Exec Statements:
- CEO: Monetize telemetry.
- CFO: Costs must scale linearly.
- VP Ops: Factory lines need local control if internet drops.
Tech Reqs:
- Ingest 1M msgs/sec
- Stream processing
- Offline factory capabilities
- Train ML centrally, deploy to edge
Constraints:
- Low bandwidth/high latency at factories
- Legacy MQTT protocol
- Zero IT staff at factories
QUESTION: How should you architect the ingestion layer to handle 1 million MQTT messages per second from the legacy sensors?
GCP PCA · Question 20 · Advise development and operation teams
CASE STUDY: ManuIoT
Overview:
Industry: Manufacturing
Size: 100 factories globally
Environment:
- 100,000 sensors
- Local SCADA
- Fragmented SQL Server DBs
- No central analytics
Requirements:
- Predictive maintenance
- Real-time global dashboards
- Edge computing
Exec Statements:
- CEO: Monetize telemetry.
- CFO: Costs must scale linearly.
- VP Ops: Factory lines need local control if internet drops.
Tech Reqs:
- Ingest 1M msgs/sec
- Stream processing
- Offline factory capabilities
- Train ML centrally, deploy to edge
Constraints:
- Low bandwidth/high latency at factories
- Legacy MQTT protocol
- Zero IT staff at factories
QUESTION: To meet the requirement of training ML models centrally and deploying them to the edge, which GCP AI service should you utilize?
CASE STUDY: ManuIoT
Overview:
Industry: Manufacturing
Size: 100 factories globally
Environment:
- 100,000 sensors
- Local SCADA
- Fragmented SQL Server DBs
- No central analytics
Requirements:
- Predictive maintenance
- Real-time global dashboards
- Edge computing
Exec Statements:
- CEO: Monetize telemetry.
- CFO: Costs must scale linearly.
- VP Ops: Factory lines need local control if internet drops.
Tech Reqs:
- Ingest 1M msgs/sec
- Stream processing
- Offline factory capabilities
- Train ML centrally, deploy to edge
Constraints:
- Low bandwidth/high latency at factories
- Legacy MQTT protocol
- Zero IT staff at factories
QUESTION: To meet the requirement of training ML models centrally and deploying them to the edge, which GCP AI service should you utilize?
Answer options:
A.
Vertex AI
B.
Cloud Vision API
C.
Dialogflow
D.
AutoML Tables
How to approach this question
Identify GCP's unified machine learning platform.
Full Answer
A.Vertex AI✓ Correct
Vertex AI is Google Cloud's unified machine learning platform. It allows data scientists to train custom predictive maintenance models using cloud compute, and then export those models (e.g., as TensorFlow Lite or Docker containers) to be deployed on edge devices or Anthos clusters in the factories.
Common mistakes
Selecting pre-trained APIs (B, C) instead of a custom model training platform.
Practice the full GCP Professional Cloud Architect Practice Exam 6
50 questions · hints · full answers · grading
More questions from this exam
Q01CASE STUDY: TechStream Gaming
Overview:
Industry: Gaming
Size: 500 employees, $100M revenue
Env...MediumQ02CASE STUDY: TechStream Gaming
Overview:
Industry: Gaming
Size: 500 employees, $100M revenue
Env...MediumQ03CASE STUDY: TechStream Gaming
Overview:
Industry: Gaming
Size: 500 employees, $100M revenue
Env...HardQ04CASE STUDY: TechStream Gaming
Overview:
Industry: Gaming
Size: 500 employees, $100M revenue
Env...MediumQ05CASE STUDY: TechStream Gaming
Overview:
Industry: Gaming
Size: 500 employees, $100M revenue
Env...Easy