用近地卫星群构建可扩展的太空AI算力系统，利用太阳能和星间光通信实现高效训练。
Towards a future space-based, highly scalable AI infrastructure system design
- 以近地卫星集群为计算节点，配备太阳能板与TPU芯片，通过光通信互联。
- 81颗卫星构成1公里半径编队，可通过高精度机器学习模型控制大规模星座。
- 辐射测试显示Trillium TPU可支撑5年太空任务，未来发射成本或降至200美元/公斤以下。
若人工智能是基础性通用技术，其算力与能耗需求将持续增长。太阳是太阳系中最大的能源，因此需探索如何高效利用其能量构建未来AI基础设施。本文提出一种基于太空的可扩展机器学习计算系统：由搭载太阳能阵列、自由空间光通信链路及谷歌张量处理单元（TPU）加速芯片的卫星群组成。为实现高带宽、低延迟星间通信，卫星需保持近距离飞行。文中以81颗卫星组成的1公里半径集群为例，展示编队飞行方案，并提出基于高精度机器学习模型的大规模星座控制方法。Trillium TPU经辐射测试，在等效5年任务寿命的总电离剂量下无永久故障，且已评估位翻转错误。发射成本是系统总成本关键因素，学习曲线分析表明，到2030年代中期，近地轨道（LEO）发射成本可能降至约200美元/公斤以下。
原文摘要 · Abstract (English)
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 an 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。