Content for  TS 23.288  Word version:  19.0.0

An NWDAF containing AnLF may be locally configured with (a set of) IDs of NWDAFs containing MTLF and the Analytics ID(s) supported by each NWDAF containing MTLF to retrieve trained ML Models or may use the NWDAF discovery procedure specified in clause 5.2 for discovering NWDAFs containing MTLF. An NWDAF containing MTLF may determine that further training for an existing ML Model is needed when it receives the ML Model subscription or the ML Model request. A NWDAF containing MTLF may retrieve trained ML Models from other NWDAF containing MTLF as described in clause 5.3. The NWDAF containing MTLF determines to train a ML Model either based on the request from NWDAF containing AnLF, or based on local configuration. The NWDAF containing MTLF further determines the FL procedure is required but it can not act as an FL server, therefore, the NWDAF containing MTLF should discover an FL server NWDAF as described in clause 5.2 and request the ML Model provisioning from the FL server NWDAF. How to protect the trained ML Model file from being used without authorization e.g. being forwarded by an NWDAF containing MTLF that has retrieved a model from another NWDAF containing MTLF is defined in Annex X, clause X.10 of TS 33.501.

The procedure in Figure 6.2A.1-1 is used by an NWDAF service consumer, i.e.:

• an NWDAF containing AnLF to subscribe/unsubscribe at another NWDAF, i.e. an NWDAF containing MTLF;
• or an NWDAF containing MTLF to subscribe/unsubscribe at another NWDAF containing MTLF, i.e. an FL server NWDAF;
• or an LMF to subscribe/unsubscribe at an NWDAF containing MTLF,

to be notified when ML Model Information related to the ML Model subscription becomes available, using Nnwdaf_MLModelProvision services as defined in clause 7.5. When the service consumer is an NWDAF containing AnLF, the ML Model Information is used by the NWDAF containing AnLF to derive analytics. When the service consumer is an LMF, how the ML Model Information is used by the LMF is described in TS 23.273. The service is also used by an NWDAF Service Consumer to modify existing ML Model Subscription(s). An NWDAF can be at the same time a consumer of this service provided by other NWDAF(s) and a provider of this service to other NWDAF(s).

The consumers of the ML Model provisioning services as described in clause 7.5 and clause 7.6 may provide the input parameters as listed below:

• A list of Analytics IDs: identifies the analytics for which the ML Model is used.
• [OPTIONAL] Vendor ID: identifies the vendor of NWDAF containing AnLF or NWDAF containing MTLF.
  For each Analytics ID, the following parameters may be provided:
  • [OPTIONAL] Use case context: indicates the context of use of the analytics to select the most relevant t ML Model.
  • [OPTIONAL] ML Model Interoperability Information. This is vendor-specific information that conveys, e.g., requested model file format, model execution environment, etc. The encoding, format, and value of ML Model Interoperable Information is not specified since it is vendor specific information, and is agreed between vendors, if necessary for sharing purposes.
  • [OPTIONAL] ML Model Filter Information: enables the NWDAF containing MTLF to select which ML Model for the analytics is requested, e.g. S-NSSAI, Area of Interest. Parameter types in the ML Model Filter Information are the same as parameter types in the Analytics Filter Information which are defined in procedures.
  • [OPTIONAL] Target of ML Model Reporting: indicates the object(s) for which ML Model is requested, e.g. specific UEs i.e. a list of SUPIs, a group of UEs i.e. a list of Internal-Group-Ids or any UE (i.e. all UEs).
  • [OPTIONAL] Requested representative ratio: a minimum percentage of UE(s) in the group whose data is a non-empty set and can be used in the model training when the Target of ML Model Reporting is a group of UEs i.e. a list of Internal-Group-Ids.
  • [OPTIONAL] ML Model Target Period: indicates time interval [start, end] for which ML Model for the Analytics is requested. The time interval is expressed with actual start time and actual end time (e.g. via UTC time).
  • [OPTIONAL] Inference Input Data information: contains information about various settings that are expected to be used by AnLF during inferences such as:
    • the "Input Data" that are expected be used, each of them optionally accompanied by metrics that show the granularity with which this data will be used (i.e., a sampling ratio, the maximum number of input values, and/or a maximum time interval between the samples of this input data).
    • the data sources that are expected to be used, indicated as a list of NF instance (or NF set) identifiers.
  • [OPTIONAL] Number of ML model(s), indicating the maximum number of ML models that the NWDAF containing MTLF could provide to the NWDAF containing AnLF for the Analytics ID.
• ML Model Reporting Information with the following parameters:
  • (Only for Nnwdaf_MLModelProvision_Subscribe) ML Model Reporting Information Parameters as per Event Reporting Information Parameter defined in Table 4.15.1-1, TS 23.502.
• A Notification Target Address (+ Notification Correlation ID) as defined in clause 4.15.1 of TS 23.502, allowing to correlate notifications received from the NWDAF containing MTLF with this subscription.
• [OPTIONAL] Indication of supporting multiple ML Models.
• [OPTIONAL] Accuracy level(s) of Interest.
• [OPTIONAL] Time when model is needed: indicates the latest time when the consumer expects to receive the ML Model(s).
• [OPTIONAL] ML Model Monitoring Information:
  • desired ML Model metric.
  • [OPTIONAL] (only for Nnwdaf_MLModelProvision_Subscribe service operation) ML Model monitoring reporting mode: such as Accuracy reporting interval or pre-determined status. Depending on the reporting mode, the NWDAF containing MTLF reports the ML Model accuracy to NWDAF containing AnLF either periodically or when the ML Model accuracy is crossing an ML Model Accuracy threshold, i.e. the accuracy either becomes higher or lower than the ML Model Accuracy threshold.
  • [OPTIONAL] ML Model Accuracy Threshold: indicating the accuracy threshold of the ML Model requested by the consumer (as a kind of pre-determined status). It also can be used as an indication that the MTLF is triggered to execute the accuracy monitoring operations for the ML Model provisioned to AnLF.
  • [OPTIONAL] DataSetTag and ADRF ID if available: indicates the inference data (including input data, prediction and the ground truth data at the time which the prediction refers to) stored in ADRF which can be used by MTLF to retrain or reprovision of the ML Model.
  • [OPTIONAL] ML Model identifier: indicates the Model that the data corresponding to the DataSetTag is related to (in the case of subscription modification).

The NWDAF containing MTLF provides to the consumer of the ML Model provisioning service operations as described in clause 7.5 and 7.6, the output information as listed below:

• (Only for Nnwdaf_MLModelProvision_Notify) The Notification Correlation Information.
• For each Analytics ID requested by the service consumer, a set of pair (s) of unique ML Model identifier and the following information.
  • ML Model Information, which includes:
    • the ML Model file address; or
    • ADRF (Set) ID.
      When ADRF (Set) ID is provisioned and the MTLF authorizes the NF Service Consumer to retrieve all ML Models corresponding to a Storage Transaction ID, a Storage Transaction ID may also be provisioned.
  • [OPTIONAL] ML Model Filter Information and/or Target of ML Model Reporting may be also provided. They are provided when the ML Model provisioning request include same Analytics IDs but with different Targets of ML Model Reporting and/or ML Model Filter Information.
  • [OPTIONAL] ML Model provide indicator: indicates that the ML Model corresponding to the ML Model identifier is updated (e.g. re-trained ML Model).
  • [OPTIONAL] ML Model degradation indicator: indicates whether the provided ML Model is degraded.
  • [OPTIONAL] Validity period: indicates time period when the provided ML Model Information applies.
  • [OPTIONAL] Spatial validity: indicates Area where the provided ML Model Information applies.
  • [OPTIONAL] ML Model representative ratio: indicating the percentage of UE(s) in the group whose data is used in the ML Model training when the Target of ML Model Reporting is a group of UE(s).
  • [OPTIONAL] Training Input Data Information: contains information about various settings that have been used by MTLF during training, such as:
    • the "Input Data" that have been used, each of them optionally accompanied by metrics that show the data characteristics and granularity with which this data has been used (i.e. a sampling ratio, the maximum number of input values and/or a maximum time interval between the samples of this input data, data range including maximum and minimum values, mean and standard deviation and data distribution when applicable) and the time, i.e. timestamp and duration, when this data was obtained.
    • the data sources related to the "Input Data" that were used for ML Model training, which have been identified by a list of NF instance (or NF set) identifiers.
  • [OPTIONAL] ML Model Accuracy Information: indicates the accuracy of the ML Model if related ML Model Monitoring Information was provided, which includes:
    • the metric value of the ML Model.
    • [OPTIONAL] used ML Model metric.

The procedure in Figure 6.2A.3-1 is used by an NWDAF service consumer, i.e.:

• an NWDAF containing AnLF to request and get from another NWDAF, i.e. an NWDAF containing MTLF ML Model Information;
• or an NWDAF containing MTLF to request and get from another NWDAF containing MTLF worked as FL server ML Model Information;
• or an LMF to request and get from NWDAF containing MTLF ML Model Information,

using Nnwdaf_MLModelInfo services as defined in clause 7.6. When the service consumer is an NWDAF containing AnLF, the ML Model is used by the NWDAF containing AnLF to derive analytics. When the service consumer is an LMF, the ML Model Information is used by the LMF as described in TS 23.273. An NWDAF can be at the same time a consumer of this service provided by other NWDAF(s) and a provider of this service to other NWDAF(s).

The content of ML Model Information that can be provided by the NWDAF containing MTLF is specified in clause 6.2A.2.