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

TL;DR

This paper proposes a scalable, space-based AI infrastructure utilizing satellite fleets with solar power and advanced communication, aiming to meet growing AI compute demands efficiently in space.

Contribution

It introduces a novel design for space-based AI compute systems with satellite constellations, solar energy harvesting, and high-speed inter-satellite links, including control strategies for large formations.

Findings

Trillium TPUs withstand 5-year mission radiation doses

Satellite formation flight can be managed with ML-based control

Launch costs to LEO may drop below $200/kg by mid-2030s

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.