Method and system for discovery of network analytics
A method, a device, and a non-transitory storage medium are described in which a network analytics model service is provided. The service may include ingesting customized models and non-customized models by a network analytics device. The ingestion procedure may include receiving the model and model specification data. The service may include provisioning the model and registering the model for discovery by other network devices. The service may include specifying customized identifiers to be used prospective subscribing network devices for the analytics information. The service may also facilitate the use of the analytics information by the subscribing network devices.
1. A method comprising:
ingesting, by a network device of a Fifth Generation (5G) core network, a customized model and model specification data that includes defining input data and output data, which includes customized analytics information, of the customized model, wherein the customized analytics information is customized relative to analytics information specified by a network standard of the 5G core network;
provisioning, by the network device in response to the ingesting, the customized model;
registering, by the network device in response to the provisioning, the customized model with an other network device that enables discovery of the customized analytics information generated by the customized model by one or more subscribing network devices; and
providing, by the network device after the registering, the customized analytics information of the customized model to the one or more subscribing network devices.
2. The method of claim 1 , wherein the registering occurs before receiving a request to subscribe to the customized analytics information from the one or more subscribing network devices.
3. The method of claim 1 , further comprising:
determining, by the network device, whether the customized model is to be trained based on the model specification data; and
training, by the network device based on determining that the customized model is to be trained, the customized model.
4. The method of claim 1 , where the registering comprises:
registering, by the network device with the other network device, a customized analytics identifier that identifies the customized model and the customized analytics information of the customized model, and wherein a format of the customized analytics identifier is indicated in the model specification data.
5. The method of claim 1 , further comprising:
notifying, by the network device before receiving a request to subscribe to the customized analytics information from the one or more subscribing network devices, the one or more subscribing network devices of the registering.
6. The method of claim 1 , wherein the model specification data includes data indicating at least one of a type of network slice of relevance or a type of prospective subscribing network device of relevance to the customized analytics information of the customized model.
7. The method of claim 1 , wherein the customized analytics information does not include analytic information pertaining to slice load information, observed service experience information, network function load information, network performance information, user equipment (UE) mobility information, UE communication information, expected UE behavioral parameters, UE abnormal behavior information, user data congestion information, and/or quality of service (QOS) sustainability.
8. The method of claim 1 , wherein the network device is a network analytics data function (NWDAF).
9. A network device comprising:
a processor configured to:
ingest a customized model and model specification data that includes defining input data and output data, which includes customized analytics information, of the customized model, wherein the network device is included in a Fifth Generation (5G) core network, and the customized analytics information is customized relative to analytics information specified by a network standard of the 5G core network;
provision, in response to an ingestion, the customized model;
register, in response to a provision, the customized model with an other network device that enables discovery of the customized analytics information generated by the customized model by one or more subscribing network devices; and
provide, after a registration, the customized analytics information of the customized model to the one or more subscribing network devices.
10. The network device of claim 9 , wherein, wherein registering, the processor is further configured to:
register the customized model before receiving a request to subscribe to the customized analytics information from the one or more subscribing network devices.
11. The network device of claim 9 , wherein the processor is further configured to:
determine whether the customized model is to be trained based on the model specification data; and
train, based on the determination that the customized model is to be trained, the customized model.
12. The network device of claim 9 , wherein, when registering, the processor is further configured to:
register, with the other network device, a customized analytics identifier that identifies the customized model and the customized analytics information of the customized model, and wherein a format of the customized analytics identifier is indicated in the model specification data.
13. The network device of claim 9 , wherein the processor is further configured to:
notify, before receiving a request to subscribe to the customized analytics information from the one or more subscribing network devices, the one or more subscribing network devices of the registering.
14. The network device of claim 9 , wherein the customized analytics information does not include analytics information pertaining to slice load information, observed service experience information, network function load information, network performance information, user equipment (UE) mobility information, UE communication information, expected UE behavioral parameters, UE abnormal behavior information, user data congestion information, and/or quality of service (QOS) sustainability.
15. The network device of claim 9 , wherein the model specification data includes data indicating at least one of a type of network slice of relevance or a type of prospective subscribing network device of relevance to the customized analytics information of the customized model.
16. The network device of claim 9 , wherein the network device is a network analytics data function (NWDAF).
17. A non-transitory computer-readable storage medium storing instructions executable by a processor of a network device of a Fifth Generation (5G) core network, wherein the instructions are configured to:
ingest a customized model and model specification data that includes defining input data and output data, which includes customized analytics information, of the customized model, wherein the customized analytics information is customized relative to analytics information specified by a network standard of the 5G core network;
provision, in response to an ingestion, the customized model;
register, in response to a provision, the customized model with an other network device that enables discovery of the customized analytics information generated by the customized model by one or more subscribing network devices; and
provide, after a registration, the customized analytics information of the customized model to the one or more subscribing network devices.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions are further configured to:
register the customized model before receiving a request to subscribe to the customized analytics information.
19. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions are further configured to:
register, with the other network device, a customized analytics identifier that identifies the customized model and the customized analytics information of the customized model, and wherein a format of the customized analytics identifier is indicated in the model specification data.
20. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions are further configured to:
notify, before receiving a request to subscribe to the customized analytics information from the one or more subscribing network devices, the one or more subscribing network devices of the registering.