To mitigate the complexity of modularized network function (NF) management in 5G, automated network operation and management are indispensable, and, therefore, the 3rd Generation Partnership Project has introduced a network data analytics function (NWDAF). However, a conventional NWDAF needs to conduct both inference and training tasks, and, thus, it is difficult to provide the analytics results to NFs in a timely manner for an increased number of analytics requests. In this article, we propose a hierarchical network data analytics framework (H-NDAF) where inference tasks are distributed to multiple leaf NWDAFs, and training tasks are conducted at the root NWDAF. H-NDAF provides timely inference results while maintaining high accuracy. Furthermore, we present a use case to optimize the policy for user equipment data flows. Extensive simulation results using open source software (i.e., free5GC) demonstrate that H-NDAF can provide sufficiently accurate analytics and faster analytics provision time compared to the conventional NWDAF.
