2 OCNWDAF Architecture

This chapter describes the Oracle Communications Network Data Analytics Function (OCNWDAF) architecture.

2.1 Oracle Communications Networks Data Analytics Function Architecture

OCNWDAF comprises of various microservices deployed in a Kubernetes based Cloud Native Environment (for example, CNE). The environment has some common services for logs (or metrics) collection, analysis, graphs or charts visualization, and so on. The OCNWDAF uses standard interfaces from the Service Based Architecture (SBA) to collect data through subscription or request model from other Network Functions (NFs). The microservices integrate with the environment and provide the necessary data analytics.

The following diagram depicts the OCNWDAF architecture:

Figure 2-1 OCNWDAF Architecture


OCNWDAF Architecture

The OCNWDAF architecture aligns with 3GPP Release 17 Technical Specifications.

OCNWDAF Front End

The OCNWDAF Front End (FE) interacts with 5G NFs to gather information through the Service Based Architecture (SBA) or Service Based Interface (SBI) defined in 3GPP 23.288 and 29.520 Technical Specifications.

  • Collects data from 5G NFs
  • Provides the data to backend Converged Analytics Platform for Communication (CAP4C)
  • Collects the processed analytics information from CAP4C
  • Provides the analytics information to the consumer NFs and Application Functions (AFs)

Converged Analytics Platform for Communication (CAP4C)

The Analytics Engine, CAP4C is the core of the OCNWDAF, it supports data collection from the Front End (FE) module. Machine Learning (ML) models process the collected data. The Analytics Engine performs predictive or descriptive data analysis and provides analytics information through real-time stream processing.

  • Processes data from the Front End (FE) or data received from the OCNADD
  • Examines streaming data in real time to allow thresholding and other use cases
  • Generates OCNWDAF analytics information (Statistical, Predictive, and Abnormal Behavior)
  • Automates machine learning models
  • Provides visualization and reports

Oracle Communications Network Analytics Data Director (OCNADD)

  • Receives messages from Oracle NFs such as SCP, SEPP, and NRF.
  • Captures the call flow messages transmitted between the control plane NFs.
  • Filters data from the call flows and sends it to the CAP4C.

A few common services are deployed with the OCNWDAF. The common services are also used by other 5G NFs along with OCNWDAF.

Ingress Gateway

This microservice is an entry point for accessing OCNWDAF supported service operations and provides the functionality of an OAuth validator.

Egress Gateway

This microservice is responsible to route OCNWDAF initiated egress messages to other NFs.

For more information about Ingress and Egress Gateway, see Oracle Communications Cloud Native Core, Cloud Native Environment User Guide.

Scheduler

Offers scheduling services for timed events such as periodic consumer report notifications.

Model Manager

  • Tracks the analytics requests, timeframes, and data items required within the training data set to train the respective ML models
  • Sends model training requests to the CAP4C and tracks the Machine Learning (ML) models that CAP4C builds
Analytics Subscription Service

Enables service consumers to subscribe or unsubscribe to different analytics from the OCNWDAF. It handles all the subscription requests from the consumers and updates or cancels the subscription requests from the consumers. The subscription service sends notifications to the NFs, AFs, and OAM when the subscribed event occurs in the network.

Analytics Information Service

This service enables consumers to request and obtain different analytics information from the OCNWDAF based on the 3GPP defined AnalyticsInfo API. This service is based on the REST API request-response model. This service handles the request for analytics based on the AnalyticsID. The service responds to the request and provides the analytics information if the requested analytics information is available.

Data Collection

The OCNWDAF retrieves data from various sources (for example, NFs such as AMF and SMF). Network analytics is computed using this data. The Data Collection Controller and Data Collection microservices perform data collection for the OCNWDAF. These microservices ensure the OCNWDAF obtains the appropriate data with the proper granularity.

  • Data Collection Controller Service: This service subscribes to all NFs, manages the subscriptions, and updates the Analytics Subscription service. It also manages and prioritizes data collection between 3GPP NFs and the Data Director (OCNADD). The OCNADD has a higher priority than the 3GPP NFs.

  • Data Collection Service: This service collects data from the producer NFs and streams it to the CAP4C for further processing.

NRF Client Service

NRF Client integrates with the NRF for OCNWDAF registration, discovery, and service status or load information, along with application and performance information services. NRF discovery helps in the on-demand discovery of network functions. NRF management helps in the autonomous discovery of NFs.

Redundancy Agent

This microservice maintains communication and controls responsibilities between the mated sites in a georedundant deployment. If there are more than two sites, then the Redundancy Agent is responsible for assigning the hierarchy of control.

Capex Service

This microservice processes the available data and identifies metrics like the active UEs per cell and the aggregated tracking area, the user plane resources (the UPFs) servicing the tracking area, and optionally, the UPFs or AMFs or SMF NF load servicing the tracking area.

cnDBTier MySQL database

cnDBTier performs general configuration, stores microservice data including dynamic data such as states, subscriptions, work lists, and data used for reporting.

Analytics database

This database is based on the MySQL cluster and stores relational and time-series data. The relational data represents all the objects within the telecommunication network, such as UEs, slices, cells, NFs, and so on, and their relationships with each other. The time-series data represents all the KPIs, measurements, and event data collected over time and used in streaming analytics and training ML models.

Kafka

A reliable and scalable distributed event streaming platform. It is used for internal as well as external delivery and consumption of data and events. It exports special measurements and events to external consumers. It also imports measurements and events from operator sources such as a messaging bus and data lake.

Stream Processors

Cleans, merges, and splits data as required and examines data in windows to detect threshold crossings or perform complex calculations.

Model Controller

Receives model generation or execution requests from the OCNWDAF FE. The Model Controller manages and allocates work to the Model Executor pool.

Model Executor

The Model Executor accesses the information in the database based on the instructions received by the Model Controller and trains the ML models.

OCNWDAF Portal

Performs the following functions:

  • Manages the OCNWDAF dashboards
  • Accepts operator input for configuration such as adding new network slices, geofences, and so on.
  • Provides visualization of analytics information

2.2 OCNWDAF Architecture Principles

The OCNWDAF is built using Cloud Native principles. The OCNWDAF is deployed as Cloud Native Core Network Function (NF), similar to other 5G NFs. The OCNWDAF follows best practices for both the industry and customers. For example:

  • OCNWDAF is based on the microservice architecture. The Front End (FE) and Converged Analytics Platform for Communication (CAP4C) are built using a set of microservices.
  • The microservices are designed to perform one specific task or job.
  • The microservices interact through standard interfaces (HTTP or messaging through Kafka).
  • The microservices can be scaled up or down according to Kubernetes programmed rules.
  • No root or elevated access is required.

Modular, Flexible, and Scalable Architecture

The flexibility of an analytics solution depends on the following factors:

  • Flexibility in data collection or ingestion
  • Ability to support diversified use cases
  • Availability of analytics feed to the consumer (on demand, periodic, so on)

The OCNWDAF supports the above mentioned characteristics beyond what is defined in 3GPP Technical Specification for Data Analytics NFs.

  • To support diversified use cases (for example, other than those defined by 3GPP), OCNWDAFs concept of separation of CAP4C from the FE provides the flexibility to support any use case category. The flexibility in creating ML models, training or retraining, model validation and benchmarking, and automated deployment make OCNWDAF the best breed.
  • OCNWDAF provides the analytics report (on demand or periodic) to the consumers in different ways. For example, in the case of 3GPP network elements, the analytics report is provided through 3GPP defined (TS 23.288, TS 29.520) SBI interface.
  • The OCNWDAF is evolving along the lines of 3GPP specifications and customer use case requirements. OCNWDAF is developed as an open and flexible analytics platform to meet customers' future use case requirements.
  • The entire OCNWDAF functionality is modular and independent. Interactions between these entities are enabled through REST APIs, the streaming framework, the time-series database, or the cnDBTier. Direct messaging through REST (where synchronous communication is necessary) or messaging through Kafka (when the communication is asynchronous). Configuration data, dynamic data, and time-based data is stored by one entity and can be accessed by another for usage or display.