NWDAF: Automating the 5G network with machine learning and data analytics

The need for analytics in telco networks can be traced back to the early days of public switched telephone network (PSTN) and signaling system no. 7 (SS7).Simple network-node key performance indicators (KPIs) were used based on stats received from T1/E1 link probes for network monitoring and to ensure no fraudulent activity was happening on the network alon with network performance monitoring.

As part of the 4G evolution, analytics using advanced AI/machine learning (ML) algorithms doing predictive analytics, anomaly detection, trend analysis, and clustering have become a top choice for use cases such as customer experience management, personalized marketing or data monetization in addition to network management. With the addition of 5G and its complexities, there’s an even stronger need for advanced prescriptive analytics to drive closed-loop automation and self-healing networks.

With all of these considerations, there’s a common pain point among communications service providers (CSPs) – how to integrate analytics into the network, currently the analytics are complex from the many non-standardized interfaces and inconsistent data collection techniques across network vendors.

The good news – these concerns may finally be addressed by the network data analytics function (NWDAF) defined as part of the 5G Core (5GC) architecture by 3GPP (the standards development body for mobile networks). So what exactly is NWDAF? What are the use cases? What will be the key challenges for CSPs? How can they overcome them? Surprisingly little has been written about NWDAF but we’re hearing a lot of interest in it from CSPs around the world.

What is NWDAF? - Architecture, services and use cases

NWDAF defined in 3GPP TS 29.520 incorporates standard interfaces from the service-based architecture to collect data by subscription or request model from other network functions and similar procedures. This is to deliver analytics functions in the network for automation or reporting, solving major custom interface or format challenges.

NWDAF is expected to have a distributed architecture providing analytics at the edge in real-time and, a central function for analytics which need central aggregation (e.g., service experience).

NWDAF collects data and provides analytics services using a request or subscription model as outlined in the example below.

3GPP TR 23.791 has currently listed the following formula-based/AI-ML analytics use cases for 5G using NWDAF:

• Load-level computation and prediction for a network slice instance


• Service experience computation and prediction for an application/UE group


• Load analytics information and prediction for a specific NF


• Network load performance computation and future load prediction


• UE Expected behaviour prediction


• UE Abnormal behavior/anomaly detection


• UE Mobility-related information and prediction


• UE Communication pattern prediction


• Congestion information - current and predicted for a specific location


• Quality of service (QoS) sustainability whic involves reporting and predicting QoS change

NWDAF deployment challenges and recommendations

To deploy NWDAF, CSPs may encounter these challenges:

• Some network function vendors may not be standards compliant or have interfaces to provide data or receive analytics services.


• Integrating NWDAF with existing analytics applications until a 4G network is deployed is crucial as aggregated network data is needed to make decisions for centralized analytics use cases.


• Many CSPs have different analytics nodes deployed for various use cases like revenue assurance, subscriber/marketing analytics and subscriber experience/network management. Making these all integrated into one analytics node also serving NWDAF use cases is key to deriving better insights and value out of network data.


• Ensuring the analytics function deployed is integrated to derive value (e.g., with orchestrator for network automation, BI tools/any UI/email/notification apps for reporting).

Here are some ways you can overcome these challenges and deploy efficient next-generation analytics with NWDAF:

• Mandate a distributed architecture for analytics too, this reduces network bandwidth overhead due to analytics and helps real-time use cases by design.


• Ensure RFPs and your chosen vendors for network functions have, or plan to have, NWDAF support for collecting and receiving analytics services.


• Look for carrier-grade analytics solutions with five nines SLAs.


• Choose modular analytics systems that can accommodate multiple use cases including NWDAF as apps and support quick development.


• Resource-efficient solutions are critical for on-premise or cloud as they can decrease expenses considerably.


• Storage comes with a cost, store more processed smart data and not more raw big data unless mandated by law.


• In designing an analytics use case, get opinions from both telco and analytics experts, or ideally an expert in both, as they are viewed from different worlds and are evolving a lot.

The bottom line

CSPs are familiar with the benefits of using analytics in telco networks, which include reducing operations and capital costs and generating new revenue. As they move to 5G, analytics play an even bigger role beyond the traditional boundaries of telco networks including radio access networks (RAN), and core operations/business support systems (OSS/BSS). Hence, having a standards-defined NWDAF for the analytics needs of 5G, deployed with the right scalable, optimized and distributed architecture, will simplify 5G/hybrid network deployment and management and is critical to ensuring the very best customer experience.