Machine Learning functions
The BMC Helix Edge environment offers a comprehensive suite of features to manage Machine Learning models. You can go through various functionalities of Machine Learning in the BMC Helix Edge environment, including:
- Learn the step-by-step process of defining a Machine Learning model in the environment.
- Understand the intricacies of configuring data to the model and optimizing it for a specific use case.
- Deploy the trained model to edge devices for real-time analytics.
- Define thresholds for anomaly detection and severity classification.
- Learn how to view, edit, or delete models.
In real-time, events are generated through rules and Machine Learning anomaly detection. To enable automated remediation, you must create workflows triggered by these events.
The following diagram illustrates the data flow in the BMC Helix Edge data stream system:
The following list describes the components and their functions in the BMC Helix Edge data stream components and their interactions:
- Device Service: Generates raw metric stream based on data collected from various devices. The raw metrics include multiple data types, such as temperature and RPM.
- Enrichment Pipeline: Enriches the raw metric data with additional device metadata and configuration details. The enriched data is stored in a time-series metric data store and the BMC Helix environment.
- Pipeline Clients: Processes the enriched metric data, applying rules and machine learning predictions. The data workflows through rule execution and Machine Learning prediction stages to generate the BMC Helix Edge event stream.
- Event Clients: Handles the integration with BMC Helix Operations Management and the remediation workflow defined in the workflow builder.
- Command Executors: Takes actions based on the processed data, such as executing device commands and creating tickets for any issues identified.
- BMC Helix Edge Dashboards: Represents data visually for analysis and monitoring purposes.
Each of these components communicates with each other, as depicted by the arrows, indicating the data flow or commands. Redis and other external systems are used for caching and fetching additional data required in the pipeline, ensuring a comprehensive and informed data processing and action execution mechanism.