Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-Open-RAN for Non-Terrestrial Networks

Tri Nhu Do

TL;DR

This paper introduces AIO-RAN-NTN, a unified open, AI-native RAN framework tailored for non-terrestrial networks. It combines 3GPP NG-RAN baselines, Open-RAN extensions, and AI-RAN ideas to expose NTN-capable air/space links via open interfaces, enabling cross-domain interoperability and AI-driven optimization. Through a Standalone NR testbed on OpenAirInterface, it demonstrates mobility-induced KPI variability and presents an AI-based KPI forecasting pipeline to predict and mitigate deteriorating performance, enabling proactive RAN adaptations. The work highlights concrete blueprint options, new NTN-aware components, and a practical demonstration that paves the way for interoperable, AI-guided RAN deployment across terrestrial and non-terrestrial domains with potential for real-time orchestration and optimization.

Abstract

In this paper, we propose the concept of AIO-RAN-NTN, a unified all-in-one Radio Access Network (RAN) for Non-Terrestrial Networks (NTNs), built on an open architecture that leverages open interfaces and artificial intelligence (AI)-based functionalities. This approach advances interoperability, flexibility, and intelligence in next-generation telecommunications. First, we provide a concise overview of the state-of-the-art architectures for Open-RAN and AI-RAN, highlighting key network functions and infrastructure elements. Next, we introduce our integrated AIO-RAN-NTN blueprint, emphasizing how internal and air interfaces from AIO-RAN and the 3rd Generation Partnership Project (3GPP) can be applied to emerging environments such as NTNs. To examine the impact of mobility on AIO-RAN, we implement a testbed transmission using the OpenAirInterface platform for a standalone (SA) New Radio (NR) 5G system. We then train an AI model on realistic data to forecast key performance indicators (KPIs). Our experiments demonstrate that the AIO-based SA architecture is sensitive to mobility, even at low speeds, but this limitation can be mitigated through AI-driven KPI forecasting.

AI-Open-RAN for Non-Terrestrial Networks

TL;DR

This paper introduces AIO-RAN-NTN, a unified open, AI-native RAN framework tailored for non-terrestrial networks. It combines 3GPP NG-RAN baselines, Open-RAN extensions, and AI-RAN ideas to expose NTN-capable air/space links via open interfaces, enabling cross-domain interoperability and AI-driven optimization. Through a Standalone NR testbed on OpenAirInterface, it demonstrates mobility-induced KPI variability and presents an AI-based KPI forecasting pipeline to predict and mitigate deteriorating performance, enabling proactive RAN adaptations. The work highlights concrete blueprint options, new NTN-aware components, and a practical demonstration that paves the way for interoperable, AI-guided RAN deployment across terrestrial and non-terrestrial domains with potential for real-time orchestration and optimization.

Abstract

In this paper, we propose the concept of AIO-RAN-NTN, a unified all-in-one Radio Access Network (RAN) for Non-Terrestrial Networks (NTNs), built on an open architecture that leverages open interfaces and artificial intelligence (AI)-based functionalities. This approach advances interoperability, flexibility, and intelligence in next-generation telecommunications. First, we provide a concise overview of the state-of-the-art architectures for Open-RAN and AI-RAN, highlighting key network functions and infrastructure elements. Next, we introduce our integrated AIO-RAN-NTN blueprint, emphasizing how internal and air interfaces from AIO-RAN and the 3rd Generation Partnership Project (3GPP) can be applied to emerging environments such as NTNs. To examine the impact of mobility on AIO-RAN, we implement a testbed transmission using the OpenAirInterface platform for a standalone (SA) New Radio (NR) 5G system. We then train an AI model on realistic data to forecast key performance indicators (KPIs). Our experiments demonstrate that the AIO-based SA architecture is sensitive to mobility, even at low speeds, but this limitation can be mitigated through AI-driven KPI forecasting.

Paper Structure

This paper contains 36 sections, 9 equations, 7 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Proposed Blueprint of AIO-RAN-NTN: Architecture and Interfaces
  3. Open and AI-RAN Architecture Splitting
  4. 3GPP Open RAN Baseline
  5. Open-RAN Extensions
  6. AI-RAN Integration
  7. Key Interfaces for O-RAN and AI-RAN in NTN
  8. Blueprint for Integrated AIO-RAN-NTN: Proposed Architecture with Open Interfaces
  9. System Blueprint
  10. New Elements Needed in Our Blueprint
  11. Element Blocks and Interfaces
  12. Demo: AI-based KPI Forecasting-empowered OpenAirInterface-based SA Architecture
  13. OpenAirInterface Platform
  14. Experiment Setup and Downlink Test
  15. gNB
  16. ...and 21 more sections

Figures (7)

  • Figure 1: Key elements and interfaces of 3GPP NG-RAN and O-RAN, including the proposed AI-based modules
  • Figure 2: Proposed blueprint of an integrated AIO-RAN-NTN architecture focusing on aggregated NFs and air interfaces
  • Figure 3: (a) OAI-gNB, (b) mobile UE, (c) UE Quectel, and (d) UE dashboard
  • Figure 4: Hardware and signal processing setup at gNB.
  • Figure 5: Key observed KPIs with comments on connectivity
  • ...and 2 more figures