Designing the Network Intelligence Stratum for 6G Networks

TL;DR

The paper tackles integrating AI-native network intelligence into 6G networks by proposing the Network Intelligence Stratum (NISt) and an end-to-end NI orchestrator. It defines NIF/NIS/NIO abstractions and extends the MAPE-K model to cover NI’s training and inference loops, while detailing internal/external interfaces and lifecycle procedures across multi-domain architectures such as O-RAN and the 5G-Core NWDAF. A reference implementation demonstrates Kubernetes, Kubeflow, and Zenoh-based orchestration, validated through edge-to-cloud deployments and a federated anomaly detection plus service relocation NIS, addressing conflict resolution and knowledge sharing. The work offers a practical, scalable AI-native framework for end-to-end network automation, while highlighting open challenges like data governance, explainability, and digital twins for future research.

Abstract

As network complexity escalates, there is an increasing need for more sophisticated methods to manage and operate these networks, focusing on enhancing efficiency, reliability, and security. A wide range of Artificial Intelligence (AI)/Machine Learning (ML) models are being developed in response. These models are pivotal in automating decision-making, conducting predictive analyses, managing networks proactively, enhancing security, and optimizing network performance. They are foundational in shaping the future of networks, collectively forming what is known as Network Intelligence (NI). Prominent Standard-Defining Organizations (SDOs) are integrating NI into future network architectures, particularly emphasizing the closed-loop approach. However, existing methods for seamlessly integrating NI into network architectures are not yet fully effective. This paper introduces an in-depth architectural design for a Network Intelligence Stratum (NI Stratum). This stratum is supported by a novel end-to-end NI orchestrator that supports closed-loop NI operations across various network domains. The primary goal of this design is to streamline the deployment and coordination of NI throughout the entire network infrastructure, tackling issues related to scalability, conflict resolution, and effective data management. We detail exhaustive workflows for managing the NI lifecycle and demonstrate a reference implementation of the NI Stratum, focusing on its compatibility and integration with current network systems and open-source platforms such as Kubernetes and Kubeflow, as well as on its validation on real-world environments. The paper also outlines major challenges and open issues in deploying and managing NI.

Figures (19)

• Figure 1: The high-level hierarchical taxonomy of NI algorithms. An NIF corresponds to an individual NI instance that assists a specific functionality; for example, it could capture the implementation of a capacity forecasting task, assisting an NI edge orchestration functionality.
• Figure 2: Extended N-MAPE-K abstractions for NI algorithms.
• Figure 3: Architecture of the Network Intelligence Stratum.
• Figure 4: The 5GPPP Architectural WG framework bahare_massod_khorsandi_2023_7313232.
• Figure 5: The NI Stratum and the functional blocks of the NIO and ML pipelines, with the internal and external interfaces of the Stratum.