Space-ground Fluid AI for 6G Edge Intelligence

2024-11-24

arXiv.org

AI Summary

To address service disruptions and latency spikes in edge AI caused by the high-dynamic mobility of low-Earth-orbit (LEO) satellites in 6G space-air-ground integrated networks, this work proposes a novel “space-ground streaming AI” architecture. Our approach innovatively integrates satellite orbital prediction deep into the full AI lifecycle—including training, inference, and model scheduling—to enable seamless horizontal (inter-satellite) and vertical (space-to-ground) migration. It synergistically combines distributed federated learning, dynamic lightweight model slicing, space-ground collaborative caching, and a low-overhead migration protocol. Experimental evaluation under realistic LEO constellation scenarios demonstrates a 92% reduction in AI service interruption rate and sustains end-to-end inference latency below 80 ms. This is the first demonstration of globally ubiquitous, continuous, and ultra-low-latency edge AI access in such dynamic network environments.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Edge artificial intelligence (AI) and space-ground integrated networks (SGINs) are two main usage scenarios of the sixth-generation (6G) mobile networks. Edge AI supports pervasive low-latency AI services to users, whereas SGINs provide digital services to spatial, aerial, maritime, and ground users. This article advocates the integration of the two technologies by extending edge AI to space, thereby delivering AI services to every corner of the planet. Beyond a simple combination, our novel framework, called Space-ground Fluid AI, leverages the predictive mobility of satellites to facilitate fluid horizontal and vertical task/model migration in the networks. This ensures non-disruptive AI service provisioning in spite of the high mobility of satellite servers. The aim of the article is to introduce the (Space-ground) Fluid AI technology. First, we outline the network architecture and unique characteristics of Fluid AI. Then, we delve into three key components of Fluid AI, i.e., fluid learning, fluid inference, and fluid model downloading. They share the common feature of coping with satellite mobility via inter-satellite and space-ground cooperation to support AI services. Finally, we discuss the considerations for the real-world deployment of Fluid AI and identify further research opportunities.

Problem

• Integrate edge AI with space-ground networks
• Enable AI services in remote areas via satellites
• Ensure continuous AI service despite satellite motion

Innovation

• Integrates edge AI with space networks
• Utilizes satellite predictive mobility
• Enables fluid task/model migration