AI Lifecycle-Aware Feasibility Framework for Split-RIC Orchestration in NTN O-RAN

2026-03-24

AI Summary

This work addresses the challenges of deploying AI in non-terrestrial networks (NTNs), where stringent satellite size, weight, and power (SWaP) constraints and limited feeder-link capacity hinder support for O-RAN closed-loop control and full AI model lifecycle management. To overcome these limitations, the authors propose a Split-RIC architecture that distributes control functions across terrestrial, low Earth orbit (LEO), and geostationary orbit (GEO) nodes. They develop the first analytical framework capturing end-to-end energy consumption and latency across training, inference, and model update phases. By deriving closed-form models for data transmission, model distribution, and near-real-time inference—and incorporating orbital dynamics and link conditions—they perform sensitivity analyses to quantify the physical regimes where on-board inference and non-terrestrial learning outperform ground-based offloading. The results yield actionable deployment strategies for operators to optimize AI performance under stringent resource constraints.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Integrating Artificial Intelligence (AI) into Non-Terrestrial Networks (NTN) is constrained by the joint limits of satellite SWaP and feeder-link capacity, which directly impact O-RAN closed-loop control and model lifecycle management. This paper studies the feasibility of distributing the O-RAN control hierarchy across Ground, LEO, and GEO segments through a Split-RIC architecture. We compare three deployment scenarios: (i) ground-centric control with telemetry streaming, (ii) ground--LEO Split-RIC with on-board inference and store-and-forward learning, and (iii) GEO--LEO multi-layer control enabled by inter-satellite links. For each scenario, we derive closed-form expressions for lifecycle energy and lifecycle latency that account for training-data transfer, model dissemination, and near-real-time inference. Numerical sensitivity analysis over feeder-link conditions, model complexity, and orbital intermittency yields operator-relevant feasibility regions that delineate when on-board inference and non-terrestrial learning loops are physically preferable to terrestrial offloading.

Problem

• AI lifecycle
• Split-RIC
• Non-Terrestrial Networks
• O-RAN
• feeder-link constraints

Innovation

• Split-RIC
• AI lifecycle
• Non-Terrestrial Networks
• O-RAN orchestration
• on-board inference