Overview and key points
BMC AMI Ops Insight extends its monitoring, originally delivered for z/OS and Db2, to bring the same AI/ML-driven intelligence to IMS Transaction Manager. BMC AMI Ops Insight’s AI/ML-powered observability keeps IMS resilient and SLA-compliant.
BMC AMI Assistant complements this analysis by using GenAI to provide plain‑language explanations derived from the ML, AI, and rules‑based anomaly classification performed by BMC AMI Ops Insight.
- Turn data into action: AI/ML uncovers patterns and delivers meaningful insights that accelerate faster decisions and Mean Time To Detect (MTTD).
- Proactive detection: Find issues before they significantly affect performance or SLAs. For example, BMC AMI Ops Insight detects a gradual increase in CPU utilization or subtle deviations in resource consumption patterns and flags them at an early stage. Proactive alerts catch risks (such as sudden CPU spikes) before they disrupt SLAs.
- View detailed analysis: Early anomaly detection plus key performance indicator (KPI) focused recommendations speed resolution. Built-in domain expertise and the trend correlators help find out what’s really going on, which reduces Mean Time To Resolve (MTTR).
- Reduced false positives: Because of multivariate analysis and trend-based detection, you avoid false positives or non-critical events.
- Bridge the skills gap: Built-in expertise and clear AI/ML algorithm support every experience level. The GenAI explanations from BMC AMI Assistant help new users to understand why anomalies occurred and what actions to take.
Architecture
The integration includes IMS as a monitored subsystem, BMC AMI Ops Monitor for IMS as the data collection layer, and BMC AMI Ops Insight for AI/ML-driven analysis and visualization. BMC AMI Ops Monitor collects and structures IMS data, which is then ingested by BMC AMI Ops Insight to detect anomalies, provide AI/ML-guided probable cause analysis, and deliver actionable insights.
The following table describes the BMC AMI Ops Insight components:
Component | Description |
|---|---|
Data Ingest | Processes historical and real-time raw data |
Data Prep (Data Preparation Address Space (z/OS)) | An interface to fetch data from BMC AMI Ops Monitor products |
BMC AMI Ops Monitor | BMC AMI Ops Insight uses your monitor products for detailed analysis processing |
Historical Data | Historical SMF data from the last 4 to 6 weeks |
Real Time Data | Current SMF data sent to BMC AMI Ops Insight by BMC AMI Datastream for Ops Insight |
Model Generation (Training) | Builds a mathematical model based on historical data |
TOMCAT REST Interface (USS) | A bridge between the Data Ingest or Data Prep component and BMC AMI Manager or Model Generation |
BMC AMI Manager | Processes the real-time data and then uses the scores to perform multivariate analysis to create an event for a detected anomaly |
Container (z/CX or X86 Linux) – For charts and timeseries DB | (Optional) Container for displaying charts using a timeseries database |
Container (z/CX or X86 Linux) – For PostgreSQL DB | (Optional) Container for displaying charts for workload analysis |
Scoring Engine (Use models to evaluate data) | Uses your models and the real-time data to calculate a score, which is a measurement of how much a KPI deviates from the normal values |
HSQL database server (Model Store, History DB) | Stores models and scored data |
SMF Record Handler | An interface between BMC AMI Datastream for Ops Insight and the data ingest component |
BMC AMI Ops UI Discovery server | A server that is installed on the mainframe as part of the BMC AMI Ops Infrastructure standard installation |
BMC AMI Ops UI Server | A web server that authenticates the user during login. It then connects to the service registry to get a list of registered services, and verifies which services the user can access |
BMC AMI Ops User Interface | The user interface of BMC AMI Ops |
Process
The following figure shows the overall process of data analytics:
| Process | Description |
|---|---|
| Build algorithms | BMC domain experts build algorithms to identify KPIs (Key Performance Indicators) and groups of connected KPIs that can indicate problems. This helps minimize your costs because only the relevant KPIs are monitored. |
| Identify normal | Your historical data is used by the product to identify normal levels for the KPIs in your environment and then train the models. This means that the models are not generic but are customized to your specific environment. |
| Detect anomaly | The product then uses multivariate analysis to score your real-time data, comparing it with the data in the models to detect exceptions. |
| Predict future | When the product detects anomalies, it looks for trends to determine whether you are currently experiencing a problem or about to experience it. Reporting trends rather than individual anomalies maximizes accuracy and minimizes false positives. |
Training
Historical data is ingested into the Data Ingest component for processing. After the data is processed, it is sent for the model generation process.
Scoring
The real-time data is collected by BMC AMI Datastream for Ops Insight (a separate license is not required). The data is then sent to the SMF Record Handler. SMF Record Handler passes the data to the data ingest for processing. After the data is processed, it is sent to BMC AMI Manager. BMC AMI Manager evaluates the data against a current model. The results are stored in the database and displayed on the browser-based UI.
(Optional) If you have BMC AMI Ops Monitor products, BMC AMI Ops Insight can connect to the monitors to generate a more detailed analysis. Model Generation generates a set of models based on historical data. The models are stored in the database and are available via the browser-based UI for scoring.