NWDAF Is Growing in Importance for the Telecoms Industry

Subscribe To Download This Insight

By Don Alusha | 3Q 2022 | IN-6635

At present, no vendor commands the Network Data Analytics Function (NWDAF) market. Pure-play software vendors (e.g., Sandvine and Guavus) have launched their own offerings, but so have entities like Ericsson and Nokia. Admittedly, it may be a little early for an immediate upswing in vendor revenue. But eventually, NWDAF stands to pave the way for new value creation, but the jury is still out on who will capture what share of that value.

Registered users can unlock up to five pieces of premium content each month.

Log in or register to unlock this Insight.


What Is NWDAF and Why Is It Important?


Specified in The 3rd Generation Partnership Project (3GPP) as part of 5G Service-Based Architecture (SBA), the Network Data Analytics Function (NWDAF) is a standards-based analytics function designed to provide a broad and deep set of analytics to drive actionable insight. NWDAF provides real-time, operational intelligence to requesting Network Functions (NFs) in 5G Core (5GC) (e.g., policy control function, unified data management, etc.) for network automation, service orchestration, and operational intelligence. NWDAF consumes key performance indicators (e.g., load, control, and user statistics) from NFs, processes this stream of information in real time, and provides predictions to NFs and other systems via subscriptions and pull interfaces. NWDAF, unlike other similar functions, is part of the 3GPP standards and does not rely on third-party solutions.

It helps Communication Service Providers (CSPs) obtain clarity in terms of the business value they get from data and analytics, albeit from an operations standpoint. It enables the industry to place data and analytics at the heart of its innovation model. Also, it serves as a stepping-stone for CSPs to build analytics functions that can potentially propel them forward to ride the growth wave associated with the digital economy. NWDAF is a key component of 5G Standalone (SA), especially in terms of new revenue generation. NWDAF use cases, as detailed below, provide CSPs with real-time visibility into how their networks are delivering their services and how to ensure application Quality of Experience (QoE)—packet loss, throughput, and latency for each application.

NWDAF Use Cases


CSPs that are including NWDAF in their Requests for Proposal (RFPs) today are primarily interested in network automation use cases. NWDAF drives decision making, self-optimization, and self-healing based on parameter changes according to specific network policies. NWDAF enables CSPs to deploy a common network data collection and analytics engine that supports the complete set of 3GPP use cases, including network conditions, device behavior, and service experience. See below for more details:

  • Network Performance: NWDAF provides network and User Equipment (UE) performance and congestion-related statistics and predictions to aid CSPs with understanding how network conditions are impacting subscriber QoE and making intelligent policy decisions to improve network performance. Key application areas are network performance analysis, user data congestion, policy optimization, and automated management for 5GC. 5GC focuses on services that are invoked using Application Programming Interfaces (APIs). APIs introduce upper-layer, service-oriented innovation. To that end, Ericsson and Nokia offer solutions that not only streamline core network operations, but also generate insights for upper-layer, northbound applications.
  • Service Experience: 5GC is, to a large extent, a service business today. 5GC has a new service-based architecture, new APIs between them, and Container-as-a-Service (CaaS) layers that were not present in the past. Consequently, a key use case for NWDAF is to effectively facilitate the modernization of operations and deliver a superior service experience. Enea Openwave and ZTE are some vendors, among others, that offer real-time Quality of Service (QoS) management and optimization solutions. These solutions are aimed at propelling CSPs and enterprises forward to complete the digital transformation, reduce the digital gap, and bring about a better user experience for their customers.
  • Load Analysis: With this use case, NWDAF provides real-time operational intelligence in the form of load-related statistics and predictions for network slices. Key application areas are NF load analysis, load balancing, and slice load analysis. These are designed to ensure efficient resource utilization and adjust NF resources by selecting the optimum traffic path/slice.
  • Service Assurance: NWDAF provides current and expected service assurance insights, such as statistics or predictions. Application areas are observed service experience, QoS sustainability analytics, and application-aware performance optimization, with the flexibility to accommodate a rich array of services with heterogeneous (QoS) needs. For example, NWDAF offerings from Sandvine and Guavus already offer service assurance capabilities. This is achieved by monitoring telco core networks, a container platform, and multi-vendor network functions, while performing root cause analysis based on detailed insights and intelligence.
  • UE Behavior Analysis: NWDAF provides insight into UE behavior with respect to mobility and usage patterns. This enables prediction-driven UE control and management to optimize and protect a network from unexpected behavior and improve subscriber QoE. Key application areas are UE communication analytics, UE mobility, UE expected behavioral parameters, and UE unexpected behavior.

Build a Service Indicator for Enterprise Use Cases


5G is a decentralized architecture, as elaborated in ABI Research’ report Decoding Three Key Technological Trends in the Telecoms Industry. Ecosystem decentralization requires that NWDAF functionality for operational intelligence and automation extends to a distributed footprint spanning thousands of edge Data Centers (DCs) and Edge Network Functions (xNFs). This is particularly important when we consider that as much as 75% of data in open, disaggregated ecosystems come from edge deployments and terminals. Further, unlike preceding cellular generations, with 5G, there is a requirement to tightly integrate upper-layer apps and services with not only structured data (e.g., fault/performance Key Performance Indicators (KPIs), probes, logs, telemetry), but also unstructured data repositories. NWDAF processes structured data. But in addition to structured data, NWDAF vendors should consider unstructured data. Unstructured data (e.g., file and object data) are transactional and come from upper-layer apps (e.g., business dashboards, sensors). Unstructured data play a key role when considering that 80% of the world’s data are unstructured and 50% reside outside of a central DC.

NWDAF provides intelligence for lower-layer networks on a real-time basis, whereas other algorithms offer both real-time and off-line capabilities to handle the exponential growth in the amount of network, assurance, and service data produced. This means that specialist NWDAF vendors should pursue a tighter integration with dynamic inventories and orchestration tools for all generations of core networks (e.g., Evolved Packet Core (EPC), 5GC). Furthermore, much like 4G, network-centric use cases like network management, network fault prediction, and a better user experience continue to remain key use cases for 5G NWDAF as mentioned above. But as discussed in ABI Insight “Building a Data Platform for 5G Networks,” 5G provides a foundation for new value creation coming from new vertical industry use cases. Consequently, a 5G network analytics solution, such as NWDAF, should build a service indication system for end-vertical industry use cases (e.g., Industry 4.0, Augmented Reality (AR)/Virtual Reality (VR), smart city, etc.), and provide relevant analysis and management capabilities.

At present, no vendor commands the NWDAF market. Pure-play software vendors (e.g., Sandvine and Guavus) have launched their own offerings, but so have entities like Ericsson and Nokia. Admittedly, it may be a little early for an immediate upswing in vendor revenue. But eventually, NWDAF stands to pave the way for new value creation. For example, although not fully exhaustive of all the areas that NWDAF covers, data and analytics services revenue in 5G Internet of Things (IoT) deployments is expected to grow from US$140 million in 2021 to US$6.4 billion in 2026, at a Compound Annual Growth Rate (CAGR) of 115%. Capturing growth is contingent on the vendor’s positioning, depth in offering (as discussed in ABI Insight “Decoding the Economics of Telecom Big Data and Analytics”), and CSPs’ demand for NWDAF-powered insights. Ultimately, the end goal behind NWDAF adoption is to aid in operations modernization, but equally important, unlock new growth. New value creation abounds with NWDAF, but the jury is still out on who will capture what share of that value.