
Ultimate access to all questions.
You work for a textile manufacturing company that operates hundreds of machines, each equipped with multiple sensors. Your team has utilized the data from these sensors to construct numerous machine learning models designed to detect anomalies in machine operations. These models undergo daily retraining, necessitating a deployment strategy that is both cost-effective and reliable. The deployment must ensure continuous 24/7 operation without any downtime and should be capable of delivering predictions in sub-millisecond timeframes. What deployment strategy should you choose?
A
Deploy a Dataflow batch pipeline and a Vertex AI Prediction endpoint.
B
Deploy a Dataflow batch pipeline with the RunInference API, and use model refresh.
C
Deploy a Dataflow streaming pipeline and a Vertex AI Prediction endpoint with autoscaling.
D
Deploy a Dataflow streaming pipeline with the RunInference API, and use automatic model refresh.