Metraipolis › archive › dc_cdab70cb256b

Predictive Rolling-Horizon Optimization for Commitment-Aware Model-Parallel Inference under Spatio-Temporal Edge Dynamics — arXiv:2609.31018

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31018
License (as archived): CC0-1.0
Archived: 2026-10-08T02:04:52.024Z
SHA-256 of the archived text: b6eb949d1fc48a70af1ab0073a242f0a48c916a7dc33eba11046d28aee75445c
Stable URL of this page: https://metraipolis.com/documento/dc_cdab70cb256b

How to cite

Predictive Rolling-Horizon Optimization for Commitment-Aware Model-Parallel Inference under Spatio-Temporal Edge Dynamics — arXiv:2609.31018 — arXiv (en), https://arxiv.org/abs/2609.31018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdab70cb256b (Metraipolis archive dc_cdab70cb256b, sha256 b6eb949d1fc48a70af1ab0073a242f0a48c916a7dc33eba11046d28aee75445c)

BibTeX

@misc{dccdab70cb256b,
  title = {Predictive Rolling-Horizon Optimization for Commitment-Aware Model-Parallel Inference under Spatio-Temporal Edge Dynamics — arXiv:2609.31018},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdab70cb256b; sha256 b6eb949d1fc48a70af1ab0073a242f0a48c916a7dc33eba11046d28aee75445c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Model-parallel inference over dynamic edge systems requires scheduling decisions that account for not only instantaneous resources but also future resource contention and reliable service commitments. Existing edge-inference designs, however, predominantly optimize performance metrics based on current or short-term system states, without explicitly coupling current assignments with future commitment fulfillment. To address this issue, we propose PROMISE, a predictive rolling-horizon framework for commitment-aware model-parallel inference under spatio-temporal edge dynamics. PROMISE jointly models stochastic task generation, mobility-induced communication variations, privacy-aware model partitioning, and load-dependent edge computing capability. We introduce committed completion time (CCT) as an endogenous service decision and formulate joint SD--ES mapping and CCT determination to balance commitment fulfillment and service reward. To address cross-timeslot coupling, PROMISE estimates future task arrivals and computational workloads over an adaptive horizon and embeds them into certainty-equivalent ES-state rollout. A progress-aware surrogate then evaluates feasible current-stage mappings, while the corresponding CCTs are analytically recovered from predicted completion times. Only the first-stage decisions are committed, and the optimization is repeated with newly observed states in a receding-horizon manner. Numerical experiments demonstrate robust scheduling performance under diverse system scales and workload dynamics, while Raspberry-Pi-based experiments validate the practical feasibility and key system characteristics of model-parallel edge inference.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-28 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.31018 — 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 2026-10-08T01:40:22.289Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).