Hierarchical Learning and Computing over Space-Ground Integrated Networks

TL;DR

This paper introduces a hierarchical learning framework for space-ground networks that reduces energy consumption in model aggregation by leveraging satellite connectivity predictability and solving a Directed Steiner Tree problem.

Contribution

It proposes a novel energy-efficient routing algorithm (TAEER) for model aggregation in space-ground networks, addressing satellite topology dynamics and energy constraints.

Findings

TAEER significantly reduces energy consumption compared to benchmarks.

The framework effectively utilizes satellite connectivity predictability.

Simulation results validate the approach's efficiency in real-world settings.

Abstract

Space-ground integrated networks hold great promise for providing global connectivity, particularly in remote areas where large amounts of valuable data are generated by Internet of Things (IoT) devices, but lacking terrestrial communication infrastructure. The massive data is conventionally transferred to the cloud server for centralized artificial intelligence (AI) models training, raising huge communication overhead and privacy concerns. To address this, we propose a hierarchical learning and computing framework, which leverages the lowlatency characteristic of low-earth-orbit (LEO) satellites and the global coverage of geostationary-earth-orbit (GEO) satellites, to provide global aggregation services for locally trained models on ground IoT devices. Due to the time-varying nature of satellite network topology and the energy constraints of LEO satellites, efficiently aggregating the received local models from ground devices on LEO satellites is highly challenging. By leveraging the predictability of inter-satellite connectivity, modeling the space network as a directed graph, we formulate a network energy minimization problem for model aggregation, which turns out to be a Directed Steiner Tree (DST) problem. We propose a topologyaware energy-efficient routing (TAEER) algorithm to solve the DST problem by finding a minimum spanning arborescence on a substitute directed graph. Extensive simulations under realworld space-ground integrated network settings demonstrate that the proposed TAEER algorithm significantly reduces energy consumption and outperforms benchmarks.