Hierarchical Learning and Computing over Space-Ground Integrated Networks

2024-08-26

IEEE Transactions on Mobile Computing

AI Summary

To address the high communication overhead and privacy leakage risks arising from massive IoT data uploads in space-air-ground integrated networks, this paper proposes a satellite-terrestrial collaborative hierarchical federated learning framework. The method models on-orbit model aggregation as a Directed Steiner Tree (DST) problem and introduces, for the first time, a Topology-Aware Energy-Efficient Routing (TAEER) algorithm to compute optimal aggregation paths under dynamic LEO satellite topologies and stringent energy constraints. It jointly incorporates topology prediction, inter-satellite link scheduling, and an edge–proximal–cloud collaborative architecture. Simulation results demonstrate that TAEER reduces satellite node energy consumption by over 40% compared to baseline algorithms, significantly improving aggregation efficiency and system sustainability. This work establishes a scalable, privacy-preserving, and energy-optimal paradigm for enabling distributed learning in low-Earth-orbit satellite networks.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Global connectivity for IoT in remote areas lacking infrastructure
• Reducing communication overhead and privacy risks in centralized AI training
• Efficient model aggregation in dynamic satellite networks with energy constraints

Innovation

• Hierarchical learning framework for space-ground networks
• Topology-aware energy-efficient routing algorithm (TAEER)
• Directed Steiner Tree for model aggregation optimization