- A
Deploy to an endpoint with manual scaling, set min nodes to zero and max nodes to 10, and use a cron job to adjust during business hours.
Manual scaling allows setting min to zero, stopping all nodes outside hours, and auto-scheduling via cron or Cloud Scheduler to scale up before 8 AM and down after 6 PM, minimizing cost.
- B
Use a custom prediction routine (CPR) that dynamically requests GPUs from the cluster.
Why wrong: CPR doesn't control when GPUs are allocated; it still requires a deployed model with resources configured.
- C
Deploy to a dedicated endpoint with a GPU machine and configure autoscaling.
Why wrong: A dedicated endpoint always has at least one node running, incurring costs even outside hours.
- D
Use Cloud Functions to invoke the model, and let Google Cloud manage the underlying GPU infrastructure.
Why wrong: Cloud Functions does not support GPU directly; it would need to call a separate service.
Quick Answer
The answer is to deploy to an endpoint with manual scaling, setting min nodes to zero and max nodes to 10, and use a cron job to adjust during business hours. This strategy is correct because it leverages manual scaling to decouple node count from traffic, allowing you to set the minimum replica count to zero outside the 8 AM to 6 PM window, which eliminates GPU costs during idle periods, while the cron job ensures nodes are ready for low-latency predictions exactly when needed. On the Google Professional Data Engineer exam, this scenario tests your understanding of Vertex AI’s scaling options and the trade-off between cost and availability, often appearing as a trap where candidates choose autoscaling—but autoscaling still incurs a minimum charge for one node. The key insight is that manual scaling with a scheduled adjustment gives you fine-grained control over GPU spend without sacrificing performance during the defined window. Memory tip: think “cron to zero” for cost control.
PDE Operationalizing machine learning models Practice Question
This PDE practice question tests your understanding of operationalizing machine learning models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
You are deploying a machine learning model to production using Vertex AI. The model requires GPU acceleration for low-latency predictions. You need to minimize costs while ensuring availability during a defined business hours window (8 AM to 6 PM). Which deployment strategy should you use?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue:
"minimum / minimize"Why it matters: Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Deploy to an endpoint with manual scaling, set min nodes to zero and max nodes to 10, and use a cron job to adjust during business hours.
Option A is correct because it uses manual scaling with a cron job to set min nodes to zero outside business hours (8 AM–6 PM) and scale up to a maximum of 10 nodes during business hours, ensuring GPU availability when needed while minimizing costs by running zero instances when the model is not required. This approach directly addresses the requirement for low-latency GPU predictions during a defined window without paying for idle GPU resources outside that window.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Deploy to an endpoint with manual scaling, set min nodes to zero and max nodes to 10, and use a cron job to adjust during business hours.
Why this is correct
Manual scaling allows setting min to zero, stopping all nodes outside hours, and auto-scheduling via cron or Cloud Scheduler to scale up before 8 AM and down after 6 PM, minimizing cost.
Clue confirmation
The clue word "minimum / minimize" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Use a custom prediction routine (CPR) that dynamically requests GPUs from the cluster.
Why it's wrong here
CPR doesn't control when GPUs are allocated; it still requires a deployed model with resources configured.
- ✗
Deploy to a dedicated endpoint with a GPU machine and configure autoscaling.
Why it's wrong here
A dedicated endpoint always has at least one node running, incurring costs even outside hours.
- ✗
Use Cloud Functions to invoke the model, and let Google Cloud manage the underlying GPU infrastructure.
Why it's wrong here
Cloud Functions does not support GPU directly; it would need to call a separate service.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Google Cloud often tests the misconception that autoscaling alone is sufficient for cost optimization, but the trap here is that autoscaling with a GPU machine typically requires a minimum of one replica, which still incurs 24/7 GPU costs, whereas manual scaling with a cron job to set min nodes to zero is the only way to completely eliminate GPU costs outside the defined business hours.
Detailed technical explanation
How to think about this question
Under the hood, Vertex AI endpoints with manual scaling allow you to set min_replica_count to 0, which means the endpoint can scale down to zero instances when there is no traffic, but you must have a mechanism (like a Cloud Scheduler cron job) to trigger a deployment update that changes min_replica_count to a positive value at the start of business hours. This avoids the 1‑minute billing minimum for GPU VMs that would apply if you kept a single instance running; the cron job can call the Vertex AI API to update the endpoint's traffic split or machine spec, effectively turning the GPU resources on and off. In a real-world scenario, you would pair this with a Cloud Function or Cloud Run job that runs at 8 AM and 6 PM to modify the endpoint's scaling configuration, ensuring zero cost outside the window.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A startup's cloud architect reviews their monthly bill and notices costs are higher than expected for a long-running batch job. Switching from on-demand instances to Reserved Instances — or using Spot/Preemptible VMs — can reduce compute costs by up to 72 %. Questions like this test whether you understand the tradeoffs between commitment, flexibility, and cost across cloud pricing models.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
Operationalizing machine learning models — study guide chapter
Learn the concepts, then practise the questions
- →
Operationalizing machine learning models practice questions
Targeted practice on this topic area only
- →
All PDE questions
499 questions across all exam domains
- →
Google Professional Data Engineer study guide
Full concept coverage aligned to exam objectives
- →
PDE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related PDE practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Designing data processing systems practice questions
Practise PDE questions linked to Designing data processing systems.
Building and operationalizing data processing systems practice questions
Practise PDE questions linked to Building and operationalizing data processing systems.
Operationalizing machine learning models practice questions
Practise PDE questions linked to Operationalizing machine learning models.
Ensuring solution quality practice questions
Practise PDE questions linked to Ensuring solution quality.
PDE fundamentals practice questions
Practise PDE questions linked to PDE fundamentals.
PDE scenario practice questions
Practise PDE questions linked to PDE scenario.
PDE troubleshooting practice questions
Practise PDE questions linked to PDE troubleshooting.
Practice this exam
Start a free PDE practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this PDE question test?
Operationalizing machine learning models — This question tests Operationalizing machine learning models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Deploy to an endpoint with manual scaling, set min nodes to zero and max nodes to 10, and use a cron job to adjust during business hours. — Option A is correct because it uses manual scaling with a cron job to set min nodes to zero outside business hours (8 AM–6 PM) and scale up to a maximum of 10 nodes during business hours, ensuring GPU availability when needed while minimizing costs by running zero instances when the model is not required. This approach directly addresses the requirement for low-latency GPU predictions during a defined window without paying for idle GPU resources outside that window.
What should I do if I get this PDE question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "minimum / minimize". Asks for the least resource use — fewest addresses, smallest subnet, lowest overhead. Eliminate over-provisioned options even if they would technically work.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 30, 2026
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.