Metraipolis › archive › dc_7afc5eca353d
Replica-Aware Split Inference for Edge IoT Systems — arXiv:2611.04779
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04779
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:40:11.696Z
- SHA-256 of the archived text
504fb0095ca7fe34f2f58cbd04f2fa1a601b2b103c772beeab6a97c8406075a2- Stable URL of this page
https://metraipolis.com/documento/dc_7afc5eca353d
How to cite
Replica-Aware Split Inference for Edge IoT Systems — arXiv:2611.04779 — arXiv (en), https://arxiv.org/abs/2611.04779 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7afc5eca353d (Metraipolis archive dc_7afc5eca353d, sha256 504fb0095ca7fe34f2f58cbd04f2fa1a601b2b103c772beeab6a97c8406075a2)
BibTeX
@misc{dc7afc5eca353d,
title = {Replica-Aware Split Inference for Edge IoT Systems — arXiv:2611.04779},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04779},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7afc5eca353d; sha256 504fb0095ca7fe34f2f58cbd04f2fa1a601b2b103c772beeab6a97c8406075a2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04779. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Split Inference (SI) addresses the hardware resource limitations of Internet of Things (IoT) devices by distributing tiny Machine Learning (TinyML) model segments across multiple IoT devices. However, a device failure can interrupt the inference pipeline. This paper proposes a replica-aware recovery approach that deploys replicas of TinyML model segments originally hosted on failed devices onto surviving devices. We formulate the joint selection of replica hosts and communication protocols as a mixed-integer linear programming (MILP) problem that minimizes post-reconfiguration inference latency, accounting for computation and transmission latencies, under flash memory and runtime memory constraints. Simulations using MobileNetV2 on heterogeneous IoT networks compare the proposed approach with four baselines. We implement the model in a network of 15 IoT devices with a maximum link-rate reduction of 75%, and show that MILP approach achieves an average modeled end-to-end inference latency that is 6.8% lower than that of Computation Greedy and 18.3% lower than that of Random. Index Terms TinyML, split inference, Internet of Things, fault tolerance, replica placement. 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); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2611.04779 — 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 2026-11-04T21:35:49.688Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).