Towards a future space-based, highly scalable AI infrastructure system design

2025-11-21

AI Summary

The escalating demand for AI compute and energy poses significant sustainability challenges for terrestrial infrastructure. Method: This paper proposes a space-based, scalable AI infrastructure leveraging a low-Earth-orbit (LEO) satellite constellation powered exclusively by solar energy. The architecture integrates radiation-hardened Trillium TPUs, free-space optical inter-satellite links, and high-precision, ML-driven formation-flying control algorithms to enable low-latency, intra-cluster collaborative computing. Contribution/Results: An 81-satellite cluster—spanning ~1 km—demonstrates radiation tolerance over a 5-year mission lifetime, with controlled bit-flip rates and no permanent failures. The design establishes the first system-level, engineering-feasible blueprint for solar-system-scale AI infrastructure. With projected launch costs of ≤USD 200/kg by the mid-2030s, this architecture enables sustainable, extensible spaceborne AI compute capacity.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Other Foundations of Human Computation & AI
• 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
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

If AI is a foundational general-purpose technology, we should anticipate that demand for AI compute -- and energy -- will continue to grow. The Sun is by far the largest energy source in our solar system, and thus it warrants consideration how future AI infrastructure could most efficiently tap into that power. This work explores a scalable compute system for machine learning in space, using fleets of satellites equipped with solar arrays, inter-satellite links using free-space optics, and Google tensor processing unit (TPU) accelerator chips. To facilitate high-bandwidth, low-latency inter-satellite communication, the satellites would be flown in close proximity. We illustrate the basic approach to formation flight via a 81-satellite cluster of 1 km radius, and describe an approach for using high-precision ML-based models to control large-scale constellations. Trillium TPUs are radiation tested. They survive a total ionizing dose equivalent to a 5 year mission life without permanent failures, and are characterized for bit-flip errors. Launch costs are a critical part of overall system cost; a learning curve analysis suggests launch to low-Earth orbit (LEO) may reach $lesssim$$200/kg by the mid-2030s.

Problem

• Designing scalable AI compute infrastructure using solar-powered satellite constellations
• Developing high-bandwidth inter-satellite communication for space-based machine learning
• Addressing radiation tolerance and launch cost challenges for space AI systems

Innovation

• Space-based AI satellites with solar power
• Free-space optical links for satellite communication
• Radiation-hardened TPU chips for space operations