You are building an ML model to detect anomalies in real-time sensor data.
You will use Pub/Sub to handle incoming requests.
You want to store the results for analytics and visualization.
How should you configure the pipeline?
Click on the arrows to vote for the correct answerA. B. C. D.
The best configuration for this pipeline would be option D: 1 = BigQuery, 2 = AI Platform, 3 = Cloud Storage.
Here is a detailed explanation of why this is the optimal configuration:
BigQuery: This is the best storage option for the results of the anomaly detection model. BigQuery is a fully-managed, cloud-native data warehouse that enables scalable analysis of large datasets. It can easily handle large volumes of real-time data, making it a great choice for storing the results of the model.
AI Platform: This is where the actual anomaly detection model will be deployed and run. AI Platform is a fully-managed service that enables developers to build, train, and deploy machine learning models at scale. It provides a variety of tools and frameworks for building and training models, as well as a managed runtime environment for running those models in the cloud.
Cloud Storage: This is a great option for storing the raw data that is being fed into the pipeline. Cloud Storage is a highly-scalable and durable object storage service that can store and serve large volumes of data. It can be used to store data from a variety of sources, including sensors, and can easily integrate with other Google Cloud Platform services.
Overall, this configuration provides a highly-scalable, end-to-end solution for detecting anomalies in real-time sensor data. Incoming requests are handled via Pub/Sub, the model is deployed and run on AI Platform, and the results are stored in BigQuery for analytics and visualization. Cloud Storage is used to store the raw data that is being fed into the pipeline, ensuring that it is easily accessible and can be easily integrated with other Google Cloud Platform services.