Creating an IMS model

Before you start with the operational scenarios, create an IMS model using your historical SMF data and load it. To generate IMS SMF data records, you must have version 5.6 of BMC AMI Ops Monitor for IMS.

Demo video (02:23):

To create an IMS model by using your historical SMF data

1. On the title bar, click Administration.
2. On the Model Management page, click New Model. 
   If you are an advanced user, you can use the Expert Mode to quickly create a model.
3. In step 1 of 4, under Create Models, select IMS Model, then click Next.

4. In step 2 of 4, enter the following details:

   Field	Description
   Wildcard Search	Uses wildcards to search a data set name Select the Wildcard Search checkbox and enter the wildcard input to search for a data set. The allowed wildcard characters are %, *, and * *. For example:  HLQ.MLQ.DATA% HLQ.MLQ.*.DATA HLQ.MLQ.**
   Data Set Name	Name of the historical SMF data set that contains the source data In the Data Set Name field, enter one or more data set names. The data set must follow TSO data set naming conventions. You can use up to 500 data sets for a single model. Enter each data set on a separate line.
   Scan data sets or add filters manually	You can use one of the following options: Add Manually: Add the details manually. Scan & Extract: Click to scan data sets and extract the details.
   Sort SMF	(Recommended) Use BMC's sorting algorithm to sort the model data by date and time, to minimize resource consumption. Unless you have a specific issue that prevents you from using BMC's sorting algorithm, leave this selected. Warning Important  If you select Sort SMF, the Pacing Record Count option is disabled. Before turning off Sort SMF, make sure the data is sorted based on date and time. We recommend that you enable Sort SMF.

5. Click Next.

6. In step 3 of 4, enter the following details based on your selection in the previous step (Add Manually or Scan & Extract), then click Next:

   Field	Description
   Label/Short Description	Description of the model Enter a label or short description. This description is displayed in the list of models. You can use it as an alias for the model name to allow you to easily identify the model and to differentiate it from your other models.
   Output Folder	USS subdirectory path to store the model bundles or playback file The product searches for this folder within the <installedDirectory>/aoidata/aoiinst/dat folder in your product installation. If the folder doesn't exist, the product creates it. Create a path that is compliant with USS naming conventions. You must have write access to the folder and sufficient space to store the data.
   Date Range of Model Data	Start and end dates and time for the historical SMF data used in the model The date range can be smaller than the full date range covered by the data in the data set. Dates and times follow the local date and time of the data.  For models based on SMF 1552 data, we recommend using at least six to eight weeks of data.
   Add Manually	Create IMS member Models (using SMF 1552 data)	Creates an IMS model Select one of the following and enter a name for the model: Filter by IMSplex: Filters data from the historical SMF data set using IMSplex. The IMSplex name can be up to 8 characters long and must match the SMFPRIMSPLX field in the SMF data.   Filter by IMS Member: Filters data from the historical SMF data set using single IMS member. The IMS member name can be up to 4 characters long and must match the SMFPRIMSID field in the SMF data. Warning Important You must enter a valid value for IMSplex.
   Scan & Extract	Select IMS Members to create a model	Select one or more IMS models If the selected model does not have adequate data, you get a warning message. Warning Important You need a minimum of six to eight weeks of data. To ensure that only IMS data with adequate data are used, enable IMSs with adequate data option. The Dataset view displays the data set names and the included IMS data.

7. In step 4 of 4, review the entries and click Submit.
   The process for creating a new Db2 subsystem model starts and is reflected on the progress bar on the Model Management page. The process includes the following steps:
   • Data Ingestion: Displays the number of records processed to create a model.
   • Data Training: Displays the number of records processed to train the model.
     The data ingestion is completed first, and then the data training process starts. The status displays In Progress until the process is complete.
   • Data Evaluation: Evaluates the model health immediately after model creation if sufficient data is available.
     For IMS models, you need at least seven weeks of data, where six weeks of data are for training and the last week's data is for evaluation.
     
     When the training process is complete, the new model is listed under the model tab from which it was created.

To load IMS models for analysis and start real-time scoring

1. On the Model Management page, click IMS tab.
2. Under Model details, click next to the model that you want to upload, and select Load Model (Select).
3. From the options on the left, click Realtime Scoring.
4. Under IMSplex, enable Scoring.