analiza aiqbench
This paper is about scheduling Compound AI workflows across LEO satellite constellations, with orbital motion and placement costs driving the planning. The AI workloads are the central object, and the contribution is infrastructure orchestration: deciding which orbital planes to activate and where to place each model component under latency SLOs. The reported results (81% of instances meeting a 300 ms SLO, and 56% lower mean scheduling cost versus heuristics) come from a single experimental two-shell constellation, so they should be read as simulation-scale evidence rather than deployment-ready performance.
Clockwork: Scheduling Compound AI Systems in Space Data Centers
arXiv:2611.00909v1 Announce Type: cross Abstract: 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.
Abstract: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.
Accepted at the IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2026). 10 pages, 5 figures
Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
arXiv:2611.00909 [cs.DC]
(or arXiv:2611.00909v1 [cs.DC] for this version)
https://doi.org/10.48550/arXiv.2611.00909 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 297 cuvinte
