Metraipolis › archive › dc_13611009909e
Clockwork: Scheduling Compound AI Systems in Space Data Centers — arXiv:2611.00909
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00909
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:34:28.158Z
- SHA-256 of the archived text
1ee03ab8f9d8d6da96067601fc523186629fce99293cf6f45573b7fd2b54e318- Stable URL of this page
https://metraipolis.com/documento/dc_13611009909e
How to cite
Clockwork: Scheduling Compound AI Systems in Space Data Centers — arXiv:2611.00909 — arXiv (en), https://arxiv.org/abs/2611.00909 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_13611009909e (Metraipolis archive dc_13611009909e, sha256 1ee03ab8f9d8d6da96067601fc523186629fce99293cf6f45573b7fd2b54e318)
BibTeX
@misc{dc13611009909e,
title = {Clockwork: Scheduling Compound AI Systems in Space Data Centers — arXiv:2611.00909},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00909},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_13611009909e; sha256 1ee03ab8f9d8d6da96067601fc523186629fce99293cf6f45573b7fd2b54e318},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00909. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Space data centers built on LEO constellations create an opportunity to serve Compound AI workflows close to where observations are captured. Serving such a workflow for an area of interest (AoI) requires deciding which orbital planes to provision and where to place each workflow component, while orbital motion continuously changes which satellites can serve the AoI. Provisioning must therefore be planned as a sequence of decisions over time, and these decisions are coupled because changing component placements or activating new planes incurs costs. To address this, we present Clockwork, a framework for scheduling Compound AI workflows on space data centers under end-to-end latency SLOs. Clockwork has two components: i) Castor jointly selects active planes and component placements for each constellation snapshot, while ii) Pollux connects Castor's candidate provisioning states across predicted orbital evolution to construct a low-cost schedule over time. On our experimental two-shell constellation, Castor serves 81% of instances at a 300 ms SLO, while Pollux reduces mean total scheduling cost by 56% on average and by up to 63% compared to heuristic baselines. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2611.00909 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:29:48.728Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).