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

TL;DR

This paper evaluates the feasibility of distributed AI control in non-terrestrial networks using a Split-RIC architecture across ground and satellite segments, analyzing energy and latency trade-offs for different deployment scenarios.

Contribution

It introduces a comprehensive framework for assessing the feasibility of split-RIC architectures in NTN, including closed-form expressions for energy and latency in various deployment scenarios.

Findings

On-board inference is feasible under certain feeder-link conditions.

Multi-layer control with inter-satellite links can improve latency.

Feasibility regions depend on model complexity and orbital intermittency.

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.